Initial commit: Upload pretrained LLM

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.48.2"
+}

latest

@@ -0,0 +1 @@
+global_step40

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26fa8df4641fe5c9d6f9eb5fb513a65c005a43119d5457d77deecc3b469ac0f
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd4d5d600740e52e31918a637b85c76110edba3a01b258148851e11abd42ca8
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db1e42537aa96b2f75ad63e65d30eb73d663910238e4adea7622d3a02d3aea3
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a6882248ab522d7c6d89d92dd4664dcdbd1522281851685787dcaf11c1fc7c
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f5b7a2d4a83452f891e66f1b323324a6f9da548d3b3a41191dc4b8490cadc36
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38218a2d6aab96ecb44e6e66296cbf325c3625b573a457b3c132ea039532120f
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,753 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.39603960396039606,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9300.9375,
+      "epoch": 0.009900990099009901,
+      "grad_norm": 0.2749840021133423,
+      "kl": 0.0,
+      "learning_rate": 3.999032564583976e-06,
+      "loss": 0.009333692491054535,
+      "max_completion_length": 14084.125,
+      "min_completion_length": 5729.875,
+      "num_updates": 1,
+      "rewards": 1.173762883991003,
+      "rewards/cosine_scaled_reward": 0.27115931920707226,
+      "rewards/format_reward2": 0.8515625,
+      "rewards/len_reward": 0.051041055703535676,
+      "rewards_std": 0.5518537946045399,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9752.296875,
+      "epoch": 0.019801980198019802,
+      "grad_norm": 0.23711691796779633,
+      "kl": 0.0007762908935546875,
+      "learning_rate": 3.996131194267188e-06,
+      "loss": 0.016636773943901062,
+      "max_completion_length": 14506.25,
+      "min_completion_length": 3615.875,
+      "num_updates": 2,
+      "rewards": 1.011244721710682,
+      "rewards/cosine_scaled_reward": 0.1618131911382079,
+      "rewards/format_reward2": 0.8203125,
+      "rewards/len_reward": 0.02911903988569975,
+      "rewards_std": 0.6834513954818249,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 10513.359375,
+      "epoch": 0.0297029702970297,
+      "grad_norm": 0.26973867416381836,
+      "kl": 0.0009961128234863281,
+      "learning_rate": 3.9912986959380376e-06,
+      "loss": -0.002310425043106079,
+      "max_completion_length": 14084.875,
+      "min_completion_length": 5952.75,
+      "num_updates": 3,
+      "rewards": 0.8836403228342533,
+      "rewards/cosine_scaled_reward": 0.06623293040320277,
+      "rewards/format_reward2": 0.84375,
+      "rewards/len_reward": -0.026342609897255898,
+      "rewards_std": 0.590987540781498,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 10638.6484375,
+      "epoch": 0.039603960396039604,
+      "grad_norm": 0.3450890779495239,
+      "kl": 0.0011034011840820312,
+      "learning_rate": 3.9845397447265526e-06,
+      "loss": 2.3186206817626953e-05,
+      "max_completion_length": 15636.125,
+      "min_completion_length": 6815.75,
+      "num_updates": 4,
+      "rewards": 0.8896834207698703,
+      "rewards/cosine_scaled_reward": 0.17461357091087848,
+      "rewards/format_reward2": 0.7109375,
+      "rewards/len_reward": 0.004132358357310295,
+      "rewards_std": 0.6534126400947571,
+      "step": 4
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9484.03125,
+      "epoch": 0.04950495049504951,
+      "grad_norm": 0.245803564786911,
+      "kl": 0.0010962486267089844,
+      "learning_rate": 3.975860879481513e-06,
+      "loss": -0.025934472680091858,
+      "max_completion_length": 14890.25,
+      "min_completion_length": 5349.375,
+      "num_updates": 5,
+      "rewards": 0.9708382207900286,
+      "rewards/cosine_scaled_reward": 0.10498641454614699,
+      "rewards/format_reward2": 0.859375,
+      "rewards/len_reward": 0.0064767999574542046,
+      "rewards_std": 0.655558355152607,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9448.5859375,
+      "epoch": 0.0594059405940594,
+      "grad_norm": 0.24996301531791687,
+      "kl": 0.0013685226440429688,
+      "learning_rate": 3.965270496444528e-06,
+      "loss": 0.005861759185791016,
+      "max_completion_length": 15323.625,
+      "min_completion_length": 3290.125,
+      "num_updates": 6,
+      "rewards": 0.9613782716915011,
+      "rewards/cosine_scaled_reward": 0.2207801272161305,
+      "rewards/format_reward2": 0.7734375,
+      "rewards/len_reward": -0.03283937182277441,
+      "rewards_std": 0.8270582258701324,
+      "step": 6
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9011.703125,
+      "epoch": 0.06930693069306931,
+      "grad_norm": 0.24825839698314667,
+      "kl": 0.0017271041870117188,
+      "learning_rate": 3.952778841127214e-06,
+      "loss": -0.010295629501342773,
+      "max_completion_length": 12310.875,
+      "min_completion_length": 4909.25,
+      "num_updates": 7,
+      "rewards": 1.1428990792483091,
+      "rewards/cosine_scaled_reward": 0.24160153639968485,
+      "rewards/format_reward2": 0.8515625,
+      "rewards/len_reward": 0.04973505577072501,
+      "rewards_std": 0.5509255714714527,
+      "step": 7
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 11187.453125,
+      "epoch": 0.07920792079207921,
+      "grad_norm": 0.2318185567855835,
+      "kl": 0.0022907257080078125,
+      "learning_rate": 3.938397998399332e-06,
+      "loss": 0.007296696305274963,
+      "max_completion_length": 14553.875,
+      "min_completion_length": 4561.375,
+      "num_updates": 8,
+      "rewards": 0.8727323254570365,
+      "rewards/cosine_scaled_reward": 0.09352816140744835,
+      "rewards/format_reward2": 0.796875,
+      "rewards/len_reward": -0.01767082791775465,
+      "rewards_std": 0.6038715615868568,
+      "step": 8
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 10907.1484375,
+      "epoch": 0.0891089108910891,
+      "grad_norm": 0.23230598866939545,
+      "kl": 0.002445220947265625,
+      "learning_rate": 3.922141880797449e-06,
+      "loss": 0.016454651951789856,
+      "max_completion_length": 15823.125,
+      "min_completion_length": 4670.375,
+      "num_updates": 9,
+      "rewards": 0.8584917988628149,
+      "rewards/cosine_scaled_reward": 0.12224693153984845,
+      "rewards/format_reward2": 0.7421875,
+      "rewards/len_reward": -0.0059426589868962765,
+      "rewards_std": 0.7407274544239044,
+      "step": 9
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 10617.234375,
+      "epoch": 0.09900990099009901,
+      "grad_norm": 0.3195263147354126,
+      "kl": 0.0034656524658203125,
+      "learning_rate": 3.90402621506546e-06,
+      "loss": 0.022236675024032593,
+      "max_completion_length": 14234.125,
+      "min_completion_length": 6616.625,
+      "num_updates": 10,
+      "rewards": 0.9227555003017187,
+      "rewards/cosine_scaled_reward": 0.16829395852982998,
+      "rewards/format_reward2": 0.765625,
+      "rewards/len_reward": -0.011163473129272461,
+      "rewards_std": 0.5515045262873173,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 11003.5703125,
+      "epoch": 0.10891089108910891,
+      "grad_norm": 0.22265592217445374,
+      "kl": 0.0044879913330078125,
+      "learning_rate": 3.884068526939978e-06,
+      "loss": -0.013431079685688019,
+      "max_completion_length": 14716.25,
+      "min_completion_length": 5951.375,
+      "num_updates": 11,
+      "rewards": 0.8861873494461179,
+      "rewards/cosine_scaled_reward": 0.16878368379548192,
+      "rewards/format_reward2": 0.765625,
+      "rewards/len_reward": -0.04822135902941227,
+      "rewards_std": 0.5935308411717415,
+      "step": 11
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7835.3984375,
+      "epoch": 0.1188118811881188,
+      "grad_norm": 0.3398093581199646,
+      "kl": 0.0051021575927734375,
+      "learning_rate": 3.862288124195319e-06,
+      "loss": -0.013615414500236511,
+      "max_completion_length": 13709.5,
+      "min_completion_length": 2604.5,
+      "num_updates": 12,
+      "rewards": 1.274961642920971,
+      "rewards/cosine_scaled_reward": 0.32682749163359404,
+      "rewards/format_reward2": 0.890625,
+      "rewards/len_reward": 0.0575091321952641,
+      "rewards_std": 0.7341729030013084,
+      "step": 12
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9435.609375,
+      "epoch": 0.12871287128712872,
+      "grad_norm": 0.2820684313774109,
+      "kl": 0.006267547607421875,
+      "learning_rate": 3.8387060779644725e-06,
+      "loss": 0.015070796012878418,
+      "max_completion_length": 13926.75,
+      "min_completion_length": 3093.375,
+      "num_updates": 13,
+      "rewards": 0.9852710571140051,
+      "rewards/cosine_scaled_reward": 0.22535304143093526,
+      "rewards/format_reward2": 0.7578125,
+      "rewards/len_reward": 0.0021055126562714577,
+      "rewards_std": 0.7060699462890625,
+      "step": 13
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 6023.7421875,
+      "epoch": 0.13861386138613863,
+      "grad_norm": 0.3811286985874176,
+      "kl": 0.006252288818359375,
+      "learning_rate": 3.8133452023541447e-06,
+      "loss": 0.032392144203186035,
+      "max_completion_length": 15730.75,
+      "min_completion_length": 1983.375,
+      "num_updates": 14,
+      "rewards": 1.5124556943774223,
+      "rewards/cosine_scaled_reward": 0.5594989098608494,
+      "rewards/format_reward2": 0.875,
+      "rewards/len_reward": 0.07795678498223424,
+      "rewards_std": 0.7117869555950165,
+      "step": 14
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9897.4609375,
+      "epoch": 0.1485148514851485,
+      "grad_norm": 0.2323319911956787,
+      "kl": 0.006938934326171875,
+      "learning_rate": 3.786230032373583e-06,
+      "loss": -0.02542346715927124,
+      "max_completion_length": 14731.125,
+      "min_completion_length": 4343.625,
+      "num_updates": 15,
+      "rewards": 1.046268306672573,
+      "rewards/cosine_scaled_reward": 0.24649553978815675,
+      "rewards/format_reward2": 0.7890625,
+      "rewards/len_reward": 0.010710292495787144,
+      "rewards_std": 0.6413916498422623,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 8641.328125,
+      "epoch": 0.15841584158415842,
+      "grad_norm": 0.2797869145870209,
+      "kl": 0.009868621826171875,
+      "learning_rate": 3.7573868001985375e-06,
+      "loss": 0.00245087593793869,
+      "max_completion_length": 14046.0,
+      "min_completion_length": 2590.0,
+      "num_updates": 16,
+      "rewards": 1.0253378190100193,
+      "rewards/cosine_scaled_reward": 0.18167185690253973,
+      "rewards/format_reward2": 0.8515625,
+      "rewards/len_reward": -0.007896540686488152,
+      "rewards_std": 0.7439497336745262,
+      "step": 16
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9286.7734375,
+      "epoch": 0.16831683168316833,
+      "grad_norm": 0.2538006007671356,
+      "kl": 0.009235382080078125,
+      "learning_rate": 3.7268434097933267e-06,
+      "loss": 0.012023478746414185,
+      "max_completion_length": 14357.0,
+      "min_completion_length": 4187.625,
+      "num_updates": 17,
+      "rewards": 1.116831500083208,
+      "rewards/cosine_scaled_reward": 0.26869785273447633,
+      "rewards/format_reward2": 0.8046875,
+      "rewards/len_reward": 0.04344612918794155,
+      "rewards_std": 0.6232936978340149,
+      "step": 17
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7877.734375,
+      "epoch": 0.1782178217821782,
+      "grad_norm": 0.27215102314949036,
+      "kl": 0.01183319091796875,
+      "learning_rate": 3.6946294099155545e-06,
+      "loss": 0.00474470853805542,
+      "max_completion_length": 14090.375,
+      "min_completion_length": 2752.125,
+      "num_updates": 18,
+      "rewards": 1.222687341272831,
+      "rewards/cosine_scaled_reward": 0.3153993431478739,
+      "rewards/format_reward2": 0.875,
+      "rewards/len_reward": 0.032287961803376675,
+      "rewards_std": 0.7518719509243965,
+      "step": 18
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7099.703125,
+      "epoch": 0.18811881188118812,
+      "grad_norm": 0.3579545319080353,
+      "kl": 0.013427734375,
+      "learning_rate": 3.6607759655295948e-06,
+      "loss": 0.01689109206199646,
+      "max_completion_length": 14201.875,
+      "min_completion_length": 1985.625,
+      "num_updates": 19,
+      "rewards": 1.2932276129722595,
+      "rewards/cosine_scaled_reward": 0.3619839735329151,
+      "rewards/format_reward2": 0.8515625,
+      "rewards/len_reward": 0.07968113431707025,
+      "rewards_std": 0.7946057394146919,
+      "step": 19
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7809.1328125,
+      "epoch": 0.19801980198019803,
+      "grad_norm": 0.3970443904399872,
+      "kl": 0.0154876708984375,
+      "learning_rate": 3.6253158276565003e-06,
+      "loss": 0.013616234064102173,
+      "max_completion_length": 13511.875,
+      "min_completion_length": 1854.125,
+      "num_updates": 20,
+      "rewards": 1.3438544012606144,
+      "rewards/cosine_scaled_reward": 0.41305189533159137,
+      "rewards/format_reward2": 0.875,
+      "rewards/len_reward": 0.055802563671022654,
+      "rewards_std": 0.5804904215037823,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9812.9296875,
+      "epoch": 0.2079207920792079,
+      "grad_norm": 0.5228389501571655,
+      "kl": 0.01609039306640625,
+      "learning_rate": 3.5882833016895067e-06,
+      "loss": -0.00042431801557540894,
+      "max_completion_length": 12778.25,
+      "min_completion_length": 4778.0,
+      "num_updates": 21,
+      "rewards": 1.136468593031168,
+      "rewards/cosine_scaled_reward": 0.18093573104124516,
+      "rewards/format_reward2": 0.875,
+      "rewards/len_reward": 0.08053285209462047,
+      "rewards_std": 0.5555343925952911,
+      "step": 21
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 10106.0,
+      "epoch": 0.21782178217821782,
+      "grad_norm": 0.3004865050315857,
+      "kl": 0.01863861083984375,
+      "learning_rate": 3.5497142142057796e-06,
+      "loss": 0.0011682212352752686,
+      "max_completion_length": 13495.75,
+      "min_completion_length": 5747.125,
+      "num_updates": 22,
+      "rewards": 1.1095520546659827,
+      "rewards/cosine_scaled_reward": 0.20947218214860186,
+      "rewards/format_reward2": 0.875,
+      "rewards/len_reward": 0.025079891085624695,
+      "rewards_std": 0.4830879457294941,
+      "step": 22
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 8428.5078125,
+      "epoch": 0.22772277227722773,
+      "grad_norm": 0.36966538429260254,
+      "kl": 0.01552581787109375,
+      "learning_rate": 3.509645878306514e-06,
+      "loss": 0.0047097280621528625,
+      "max_completion_length": 14159.0,
+      "min_completion_length": 1964.5,
+      "num_updates": 23,
+      "rewards": 1.1670421473681927,
+      "rewards/cosine_scaled_reward": 0.29000907950103283,
+      "rewards/format_reward2": 0.8515625,
+      "rewards/len_reward": 0.025470565538853407,
+      "rewards_std": 0.615565050393343,
+      "step": 23
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 5892.2109375,
+      "epoch": 0.2376237623762376,
+      "grad_norm": 125.0189208984375,
+      "kl": 0.43308258056640625,
+      "learning_rate": 3.4681170575189206e-06,
+      "loss": 0.00223734974861145,
+      "max_completion_length": 11146.375,
+      "min_completion_length": 1771.125,
+      "num_updates": 24,
+      "rewards": 1.4564557410776615,
+      "rewards/cosine_scaled_reward": 0.44786818977445364,
+      "rewards/format_reward2": 0.90625,
+      "rewards/len_reward": 0.10233754548244178,
+      "rewards_std": 0.6475037336349487,
+      "step": 24
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 6293.140625,
+      "epoch": 0.24752475247524752,
+      "grad_norm": 0.4965859651565552,
+      "kl": 0.0188446044921875,
+      "learning_rate": 3.425167928295014e-06,
+      "loss": 0.019756004214286804,
+      "max_completion_length": 11885.375,
+      "min_completion_length": 2043.5,
+      "num_updates": 25,
+      "rewards": 1.2420116439461708,
+      "rewards/cosine_scaled_reward": 0.24037119653075933,
+      "rewards/format_reward2": 0.921875,
+      "rewards/len_reward": 0.07976543391123414,
+      "rewards_std": 0.768707849085331,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7320.9765625,
+      "epoch": 0.25742574257425743,
+      "grad_norm": 0.32264769077301025,
+      "kl": 0.0201263427734375,
+      "learning_rate": 3.3808400411434935e-06,
+      "loss": 0.007990241050720215,
+      "max_completion_length": 14976.25,
+      "min_completion_length": 1978.0,
+      "num_updates": 26,
+      "rewards": 1.2049608379602432,
+      "rewards/cosine_scaled_reward": 0.328420914709568,
+      "rewards/format_reward2": 0.8671875,
+      "rewards/len_reward": 0.009352410677820444,
+      "rewards_std": 0.7654620930552483,
+      "step": 26
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 5956.828125,
+      "epoch": 0.26732673267326734,
+      "grad_norm": 0.3196789026260376,
+      "kl": 0.0207061767578125,
+      "learning_rate": 3.335176280432307e-06,
+      "loss": -0.00398920476436615,
+      "max_completion_length": 10882.125,
+      "min_completion_length": 2554.375,
+      "num_updates": 27,
+      "rewards": 1.3529352433979511,
+      "rewards/cosine_scaled_reward": 0.30559817608445883,
+      "rewards/format_reward2": 0.9609375,
+      "rewards/len_reward": 0.08639959944412112,
+      "rewards_std": 0.7427709549665451,
+      "step": 27
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 6028.84375,
+      "epoch": 0.27722772277227725,
+      "grad_norm": 0.3432248532772064,
+      "kl": 0.02164459228515625,
+      "learning_rate": 3.2882208229007955e-06,
+      "loss": -0.015418417751789093,
+      "max_completion_length": 11848.0,
+      "min_completion_length": 2110.75,
+      "num_updates": 28,
+      "rewards": 1.3594568185508251,
+      "rewards/cosine_scaled_reward": 0.35286577604711056,
+      "rewards/format_reward2": 0.90625,
+      "rewards/len_reward": 0.10034103039652109,
+      "rewards_std": 0.7156434431672096,
+      "step": 28
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 8682.453125,
+      "epoch": 0.2871287128712871,
+      "grad_norm": 0.2364882528781891,
+      "kl": 0.024139404296875,
+      "learning_rate": 3.24001909492155e-06,
+      "loss": 0.0035642534494400024,
+      "max_completion_length": 13773.375,
+      "min_completion_length": 3882.25,
+      "num_updates": 29,
+      "rewards": 1.13150573708117,
+      "rewards/cosine_scaled_reward": 0.195555618731305,
+      "rewards/format_reward2": 0.9140625,
+      "rewards/len_reward": 0.021887621260248125,
+      "rewards_std": 0.6196031682193279,
+      "step": 29
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 9472.0859375,
+      "epoch": 0.297029702970297,
+      "grad_norm": 0.23454353213310242,
+      "kl": 0.029876708984375,
+      "learning_rate": 3.190617728553332e-06,
+      "loss": 0.0017639100551605225,
+      "max_completion_length": 14098.75,
+      "min_completion_length": 4757.875,
+      "num_updates": 30,
+      "rewards": 1.0655029881745577,
+      "rewards/cosine_scaled_reward": 0.137826404068619,
+      "rewards/format_reward2": 0.8984375,
+      "rewards/len_reward": 0.029239090159535408,
+      "rewards_std": 0.5960428677499294,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 6721.03125,
+      "epoch": 0.3069306930693069,
+      "grad_norm": 0.36463433504104614,
+      "kl": 0.02364349365234375,
+      "learning_rate": 3.140064516427565e-06,
+      "loss": 0.02541273832321167,
+      "max_completion_length": 11538.875,
+      "min_completion_length": 3436.5,
+      "num_updates": 31,
+      "rewards": 1.2696323096752167,
+      "rewards/cosine_scaled_reward": 0.264737417222932,
+      "rewards/format_reward2": 0.921875,
+      "rewards/len_reward": 0.08301988849416375,
+      "rewards_std": 0.7188399098813534,
+      "step": 31
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7162.3828125,
+      "epoch": 0.31683168316831684,
+      "grad_norm": 0.5464898347854614,
+      "kl": 0.02471923828125,
+      "learning_rate": 3.0884083655120544e-06,
+      "loss": 0.01196742057800293,
+      "max_completion_length": 10615.375,
+      "min_completion_length": 4111.875,
+      "num_updates": 32,
+      "rewards": 1.05987061932683,
+      "rewards/cosine_scaled_reward": 0.07295701105613261,
+      "rewards/format_reward2": 0.96875,
+      "rewards/len_reward": 0.018163591157644987,
+      "rewards_std": 0.6865731440484524,
+      "step": 32
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 8008.421875,
+      "epoch": 0.32673267326732675,
+      "grad_norm": 67.73995208740234,
+      "kl": 0.0318756103515625,
+      "learning_rate": 3.0356992497966503e-06,
+      "loss": -0.01266103982925415,
+      "max_completion_length": 12517.5,
+      "min_completion_length": 2955.875,
+      "num_updates": 33,
+      "rewards": 1.1564012691378593,
+      "rewards/cosine_scaled_reward": 0.18674227688461542,
+      "rewards/format_reward2": 0.9453125,
+      "rewards/len_reward": 0.024346530437469482,
+      "rewards_std": 0.5944486074149609,
+      "step": 33
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 5801.1328125,
+      "epoch": 0.33663366336633666,
+      "grad_norm": 0.44804856181144714,
+      "kl": 0.0241241455078125,
+      "learning_rate": 2.981988161946644e-06,
+      "loss": -0.0008684098720550537,
+      "max_completion_length": 13239.625,
+      "min_completion_length": 1896.5,
+      "num_updates": 34,
+      "rewards": 1.5373370498418808,
+      "rewards/cosine_scaled_reward": 0.4724404886364937,
+      "rewards/format_reward2": 0.9609375,
+      "rewards/len_reward": 0.10395912081003189,
+      "rewards_std": 0.5325119644403458,
+      "step": 34
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7891.390625,
+      "epoch": 0.3465346534653465,
+      "grad_norm": 0.395713746547699,
+      "kl": 0.0246734619140625,
+      "learning_rate": 2.9273270639706544e-06,
+      "loss": 0.009494274854660034,
+      "max_completion_length": 13065.75,
+      "min_completion_length": 3577.25,
+      "num_updates": 35,
+      "rewards": 1.2487693056464195,
+      "rewards/cosine_scaled_reward": 0.21439548954367638,
+      "rewards/format_reward2": 0.9609375,
+      "rewards/len_reward": 0.0734363030642271,
+      "rewards_std": 0.6400604620575905,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 8915.25,
+      "epoch": 0.3564356435643564,
+      "grad_norm": 0.33517077565193176,
+      "kl": 0.0334320068359375,
+      "learning_rate": 2.871768836950742e-06,
+      "loss": -0.018658161163330078,
+      "max_completion_length": 12554.875,
+      "min_completion_length": 5071.375,
+      "num_updates": 36,
+      "rewards": 1.1192209478467703,
+      "rewards/cosine_scaled_reward": 0.15578080737031996,
+      "rewards/format_reward2": 0.9296875,
+      "rewards/len_reward": 0.03375265281647444,
+      "rewards_std": 0.5714416801929474,
+      "step": 36
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 6871.40625,
+      "epoch": 0.36633663366336633,
+      "grad_norm": 0.3194531202316284,
+      "kl": 0.0283966064453125,
+      "learning_rate": 2.8153672298833772e-06,
+      "loss": 0.027765318751335144,
+      "max_completion_length": 11280.625,
+      "min_completion_length": 2181.75,
+      "num_updates": 37,
+      "rewards": 1.2906805723905563,
+      "rewards/cosine_scaled_reward": 0.289469544775784,
+      "rewards/format_reward2": 0.9609375,
+      "rewards/len_reward": 0.04027354822028428,
+      "rewards_std": 0.6187824495136738,
+      "step": 37
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7555.359375,
+      "epoch": 0.37623762376237624,
+      "grad_norm": 0.329673707485199,
+      "kl": 0.03289794921875,
+      "learning_rate": 2.7581768076807586e-06,
+      "loss": 0.00029387325048446655,
+      "max_completion_length": 13576.25,
+      "min_completion_length": 3269.75,
+      "num_updates": 38,
+      "rewards": 0.9393773451447487,
+      "rewards/cosine_scaled_reward": 0.02606131136417389,
+      "rewards/format_reward2": 0.9375,
+      "rewards/len_reward": -0.024183956440538168,
+      "rewards_std": 0.7055792585015297,
+      "step": 38
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 7003.8125,
+      "epoch": 0.38613861386138615,
+      "grad_norm": 0.3149705231189728,
+      "kl": 0.03338623046875,
+      "learning_rate": 2.700252898382781e-06,
+      "loss": 0.00039067864418029785,
+      "max_completion_length": 12233.875,
+      "min_completion_length": 2225.0,
+      "num_updates": 39,
+      "rewards": 1.323565311729908,
+      "rewards/cosine_scaled_reward": 0.23708410863764584,
+      "rewards/format_reward2": 0.9609375,
+      "rewards/len_reward": 0.12554369773715734,
+      "rewards_std": 0.639260545372963,
+      "step": 39
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 5583.1171875,
+      "epoch": 0.39603960396039606,
+      "grad_norm": 0.4048033356666565,
+      "kl": 0.027130126953125,
+      "learning_rate": 2.641651539630735e-06,
+      "loss": 0.015950188040733337,
+      "max_completion_length": 9941.625,
+      "min_completion_length": 1826.0,
+      "num_updates": 40,
+      "rewards": 1.4943003356456757,
+      "rewards/cosine_scaled_reward": 0.4848987963050604,
+      "rewards/format_reward2": 0.921875,
+      "rewards/len_reward": 0.08752657752484083,
+      "rewards_std": 0.636099562048912,
+      "step": 40
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 101,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": true,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": null,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645eb1f2a6977df3f64905f109d54d6f457b9a645e4f958a1cb779812aa238c1
+size 7928

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)