Upload folder using huggingface_hub

README.md

@@ -0,0 +1,23 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- _load_in_8bit: True
+- _load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+- load_in_4bit: False
+- load_in_8bit: True
+### Framework versions
+
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1 @@
+{"auto_mapping": null, "base_model_name_or_path": "atsuki-yamaguchi/bloom-7b1-random-ar", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layers_pattern": null, "layers_to_transform": null, "lora_alpha": 32, "lora_dropout": 0.05, "modules_to_save": ["lm_head", "word_embeddings"], "peft_type": "LORA", "r": 8, "revision": null, "target_modules": ["query_key_value", "dense", "dense_h_to_4h", "dense_4h_to_h"], "task_type": "CAUSAL_LM"}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d0d66bcecae602d4d4121eb8d5321d8ff6cd069110c0056c2091ab020cd886
+size 2160101408

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-7b1",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 30,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float64",
+  "transformers_version": "4.39.0.dev0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8579f7700de9aaa4b6673e195c60c871cf59b720075f215452768ef36e3dbc82
+size 4782314936

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36d105ab7647131ac8737c9463748718f35911253aaf54e542aba5dfb11db70
+size 4833124632

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61d54d82c6c2b0d4d98cdcae29857920c633b971d68fdbbfdceb0f405fb3ade
+size 4833124672

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71fe9f171c7c2cb51bbd9a8f375620e7af9d41e87c3c480ef27db822c655147
+size 4833124704

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35161ddbc901b254899cdc7ec9cb875adf11ac0e57894ef96017480852c086ca
+size 4833124704

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b802a54279c7dca50ca82e6b9a85069822a8b12e4dc7e0a429ef23ce37e162
+size 2148027832

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 26262798336
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.15.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.21.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.27.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.self_attention.dense.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.self_attention.query_key_value.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.dense.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.query_key_value.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.9.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.ln_f.bias": "model-00006-of-00006.safetensors",
+    "transformer.ln_f.weight": "model-00006-of-00006.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00006.safetensors",
+    "transformer.word_embeddings_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.word_embeddings_layernorm.weight": "model-00001-of-00006.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368bbe9554f75e7af2beb9d553c8c76744b4779a6fbcaa643d7541ae367ec56d
+size 1082426362

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1f008bed7c329dee94735404f1883401cf3582f4e850550a07062c4c28bc14
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b21283c3db24950204115ac348f58e53c6d0488c1b3816d199a477f9c0931a6
+size 1064

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76197678401a94871093a05aa0bb8840f0c5c40b5b2c2af3479b7531f2f16db4
+size 4984