Upload folder using huggingface_hub

.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

README.md

@@ -0,0 +1,111 @@
+---
+base_model:
+- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B
+- mistralai/Mistral-Nemo-Base-2407
+- nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
+- nbeerbower/mistral-nemo-bophades-12B
+- HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
+- mergekit-community/MN-Sappho-g3-12B
+- Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
+- mergekit-community/MN-Hekate-Daidalos-17B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mergekit-community/MN-Hekate-Daidalos-17B](https://huggingface.co/mergekit-community/MN-Hekate-Daidalos-17B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B](https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B)
+* [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407)
+* [nbeerbower/Lyra-Gutenberg-mistral-nemo-12B](https://huggingface.co/nbeerbower/Lyra-Gutenberg-mistral-nemo-12B)
+* [nbeerbower/mistral-nemo-bophades-12B](https://huggingface.co/nbeerbower/mistral-nemo-bophades-12B)
+* [HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407](https://huggingface.co/HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407)
+* [mergekit-community/MN-Sappho-g3-12B](https://huggingface.co/mergekit-community/MN-Sappho-g3-12B)
+* [Nitral-AI/Captain-Eris_Violet-GRPO-v0.420](https://huggingface.co/Nitral-AI/Captain-Eris_Violet-GRPO-v0.420)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: float32
+out_dtype: bfloat16
+merge_method: model_stock
+base_model: mergekit-community/MN-Hekate-Daidalos-17B
+slices:
+  - sources:
+    - model: mergekit-community/MN-Hekate-Daidalos-17B
+      layer_range: [0, 20]
+
+  - sources:
+    - model: mergekit-community/MN-Hekate-Daidalos-17B
+      layer_range: [20, 36]
+      parameters:
+        weight: 3
+    - model: mistralai/Mistral-Nemo-Base-2407
+      layer_range: [16, 32]
+      parameters:
+        weight: 2
+    - model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
+      layer_range: [16, 32]
+      parameters:
+        weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1]
+    - model: nbeerbower/mistral-nemo-bophades-12B
+      layer_range: [16, 32]
+      parameters:
+        weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1]
+    - model: mergekit-community/MN-Sappho-g3-12B
+      layer_range: [16, 32]
+      parameters:
+        weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5]
+    - model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
+      layer_range: [16, 32]
+      parameters:
+        weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5]
+
+  - sources:
+    - model: mergekit-community/MN-Hekate-Daidalos-17B
+      layer_range: [36, 56]
+      parameters:
+        weight: 3
+    - model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B
+      layer_range: [20, 40]
+      parameters:
+        weight: [1, 0.75]
+    - model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
+      layer_range: [20, 40]
+      parameters:
+        weight: [1, 0.5]
+    - model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
+      layer_range: [20, 40]
+      parameters:
+        weight: [1, 0.75]
+
+tokenizer:
+  source: union
+  tokens:
+    "[INST]":
+      source: mergekit-community/MN-Hekate-Daidalos-17B
+      force: true
+    "[/INST]":
+      source: mergekit-community/MN-Hekate-Daidalos-17B
+      force: true
+    "<|im_start|>":
+      source: mergekit-community/MN-Hekate-Daidalos-17B
+      force: true
+    "<|im_end|>":
+      source: mergekit-community/MN-Hekate-Daidalos-17B
+      force: true
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mergekit-community/MN-Hekate-Daidalos-17B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 131075
+}

mergekit_config.yml

@@ -0,0 +1,68 @@
+dtype: float32
+out_dtype: bfloat16
+merge_method: model_stock
+base_model: mergekit-community/MN-Hekate-Daidalos-17B
+slices:
+  - sources:
+    - model: mergekit-community/MN-Hekate-Daidalos-17B
+      layer_range: [0, 20]
+
+  - sources:
+    - model: mergekit-community/MN-Hekate-Daidalos-17B
+      layer_range: [20, 36]
+      parameters:
+        weight: 3
+    - model: mistralai/Mistral-Nemo-Base-2407
+      layer_range: [16, 32]
+      parameters:
+        weight: 2
+    - model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
+      layer_range: [16, 32]
+      parameters:
+        weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1]
+    - model: nbeerbower/mistral-nemo-bophades-12B
+      layer_range: [16, 32]
+      parameters:
+        weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1]
+    - model: mergekit-community/MN-Sappho-g3-12B
+      layer_range: [16, 32]
+      parameters:
+        weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5]
+    - model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
+      layer_range: [16, 32]
+      parameters:
+        weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5]
+
+  - sources:
+    - model: mergekit-community/MN-Hekate-Daidalos-17B
+      layer_range: [36, 56]
+      parameters:
+        weight: 3
+    - model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B
+      layer_range: [20, 40]
+      parameters:
+        weight: [1, 0.75]
+    - model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
+      layer_range: [20, 40]
+      parameters:
+        weight: [1, 0.5]
+    - model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
+      layer_range: [20, 40]
+      parameters:
+        weight: [1, 0.75]
+
+tokenizer:
+  source: union
+  tokens:
+    "[INST]":
+      source: mergekit-community/MN-Hekate-Daidalos-17B
+      force: true
+    "[/INST]":
+      source: mergekit-community/MN-Hekate-Daidalos-17B
+      force: true
+    "<|im_start|>":
+      source: mergekit-community/MN-Hekate-Daidalos-17B
+      force: true
+    "<|im_end|>":
+      source: mergekit-community/MN-Hekate-Daidalos-17B
+      force: true

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6dc5870a40fd02e51815d3698acf83cb6b99f6fe3694c1d52bf5a5f52679b7c
+size 4865550776

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c11ed6343883793c9dfe23492b91ff6236384db364e13ab28dcb9ce95569b94
+size 4907529456

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe60b9017e462420191601fa1cd1e7f389c76573da29c0594fcdf52e9ed7cb97
+size 4907529464

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239a54fbb1df4f9f4d1fdbf0d4be2f4037a214ef578e25c549b5cee2b15cccf4
+size 4907529456

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ba9ac645b4ebe1c4783509fa4f9830b98334f2e8fd45937cf981664bde4582
+size 4907529456

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9747c685f828aae2af0760c5c04ae4e437b8b3057784de791fbb27ed3644d07a
+size 4907529456

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7ab2e07f9bc7976f9753f5e90c53027e1976df97b4a0128884b4cde8edbc03
+size 3816967304

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"lm_head.weight": "model-00001-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b1d6aa594c86f3ec69f06beab8a3e91bb6fb859107bbec96abe1fe9916fb5b
+size 17078856