Update model files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/media/data5/hf_models/Mistral-7B-v0.1",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -15,11 +16,11 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.36.0",
+  "transformers_version": "4.36.1",
   "use_cache": true,
   "vocab_size": 32000
 }

merge.yml

@@ -3,60 +3,60 @@ models:
     # no parameters necessary for base model
   - model: /media/data5/hf_models/dolphin-2.2.1-mistral-7b
     parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/SciPhi-Mistral-7B-32k
     parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/samantha-1.2-mistral-7b
     parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/docsgpt-7b-mistral
     parameters:
-      weight: 0.1
-      density: 0.6
-  - model: /media/data5/hf_models/Mistral-7B-code-16k-qlora
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/zephyr-7b-beta
     parameters:
-      weight: 0.1
-      density: 0.6
-  - model: /media/data5/hf_models/speechless-code-mistral-7b-v2.0
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/MetaMath-Mistral-7B
     parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/Mistral-7B-OpenOrca
     parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/openchat-3.5-1210
+    parameters:
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/MistralHermes-CodePro-7B-v1
     parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/MAmmoTH-7B-Mistral
     parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/OpenHermes-2.5-Mistral-7B
     parameters:
-      weight: 0.1
-      density: 0.6
-  - model: /media/data5/hf_models/jackalope-7b
-    parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/OpenHermes-2.5-neural-chat-v3-3-Slerp
     parameters:
-      weight: 0.3
-      density: 0.8
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/NeuralHermes-2.5-Mistral-7B
     parameters:
-      weight: 0.1
-      density: 0.6
+      weight: 0.08
+      density: 0.4
   - model: /media/data5/hf_models/Mistral-7B-Instruct-v0.2
     parameters:
-      weight: 0.5
-      density: 0.8
+      weight: 0.08
+      density: 0.5
 merge_method: dare_ties
 base_model: /media/data5/hf_models/Mistral-7B-v0.1
 parameters:

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf117d3e8c890a08afc4e2cc680abb984375d1b237d6c6012f7d270913d1c3a
+oid sha256:d32f5ac00d0b82479635c5ce0cb00812fd4b2a75a4232cd82375c53528b50800
 size 9976544080

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f866df5b0db36cff3d5269ea8e5d1671b3197d9119c9107e36b3153477ffcf
+oid sha256:cdaf5e0b5dd63ebf888fb480c2238ed57fa84a1c9edce281a19001f6ccd4a705
 size 4506953960

model.safetensors.index.json

@@ -1,298 +1 @@
-{
-    "metadata": {
-        "total_size": 14483464192
-    },
-    "weight_map": {
-        "lm_head.weight": "model-00003-of-00003.safetensors",
-        "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.norm.weight": "model-00003-of-00003.safetensors"
-    }
-}
+{"metadata": {"mergekit_version": "0.0.3.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors"}}

special_tokens_map.json

@@ -1,5 +1,23 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -38,6 +38,5 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
+  "use_default_system_prompt": false
 }