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 +1,41 @@
+---
+base_model:
+- Qwen/Qwen2-72B-Instruct
+- dfurman/Qwen2-72B-Orpo-v0.1
+- MaziyarPanahi/calme-2.1-qwen2-72b
+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 [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [dfurman/Qwen2-72B-Orpo-v0.1](https://huggingface.co/dfurman/Qwen2-72B-Orpo-v0.1)
+* [MaziyarPanahi/calme-2.1-qwen2-72b](https://huggingface.co/MaziyarPanahi/calme-2.1-qwen2-72b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: MaziyarPanahi/calme-2.1-qwen2-72b
+  - model: dfurman/Qwen2-72B-Orpo-v0.1
+base_model: Qwen/Qwen2-72B-Instruct
+merge_method: model_stock
+parameters:
+  normalize: true
+dtype: bfloat16
+
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2-72B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,8 @@
+models:
+  - model: MaziyarPanahi/calme-2.1-qwen2-72b
+  - model: dfurman/Qwen2-72B-Orpo-v0.1
+base_model: Qwen/Qwen2-72B-Instruct
+merge_method: model_stock
+parameters:
+  normalize: true
+dtype: bfloat16

model-00001-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3065c1960fe1bea9d747a79c22452558581a5db200ac6ab938ec2157edbf9a79
+size 4969152856

model-00002-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bce33ccb3d66888a86409bc863b75d6623d5a2221c9c150231b9cbdb271b7fb
+size 4980864400

model-00003-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854eeda45313f3e03d5192d5de95b1af1e5da31c0ee277b1df774cb738fc882a
+size 4764874368

model-00004-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02df83cff1cc07aa7f11cadbef6b18b65573e087d189880532596569dce9a934
+size 4781670352

model-00005-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de3ef998730cc4e6b0c5974e00174b16dadc88bdbe62458a1f3513152b69ebba
+size 4781670368

model-00006-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8688df03bc5c7c680c4fefa7e306f1c5dad07ada7373c91c08cad292355655
+size 4980864408

model-00007-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be244dc84e4ba5c64c0a97c15c2a2b594216502cd50343aa62b7374218e1f48b
+size 4764874368

model-00008-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b96eb95f710266b1822da40f0500e1001e161c3c99ff242f40acf40058da4c7
+size 4781670352

model-00009-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3da9057183bbf9307a9dbfbdfccae262fb81963e62bd5cda1a84e9ee802462
+size 4781670368

model-00010-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c48afc056daec9bcc60cd15516b56ad41e695cb8de1bfca13011039fee2f372
+size 4980864408

model-00011-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0c870b1756a648770bbc1a6c8548d787e7e4b2194f3af39c5e918cd8da3b1c7
+size 4764874368

model-00012-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9a1508657ffd1d1fae6dafcc60e3b27fae33f411b67b690d8d126ccf354139
+size 4781670352

model-00013-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77a12f57b798515d8a5f27884522915ecbfd9797c7a4ccf1f2373edc1ad6884
+size 4781670368

model-00014-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e792c1c2ae2f92790063d43d43b8e6fc03d034c03d4c487c640af4b055654e
+size 4980864408

model-00015-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078a0cef7a2de2ca212111fc879813c87d9f8ac0705c98b60bcab3b40d750136
+size 4764874368

model-00016-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c8d8651b0a0f18cac6fc864baab6f6117f090cafb5ddd54c8b706b5532bb76
+size 4781670352

model-00017-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96eb211f4ecb74c56e3a511d46a74db9693876e4a235e86419ac85df648e9040
+size 4781670368

model-00018-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:797676a00beb5a271f1c6f948928a38ab66f2f43c4d8d5508a6c81699dfe75fa
+size 4980864408

model-00019-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78eef4781470867a6a1c42cd0c88ecb44912903ad25e9610fa19415be0959e68
+size 4764874368

model-00020-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6a20d04cc8459df6f8ab1b476d6fd84f4a107974ef45478259f581d6c2f1aa
+size 4781670352

model-00021-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62e5d31742cac8d23fe4838d35b1142d6a96bdc03087f0093535568431f178f
+size 4781670368

model-00022-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300f786558257b6bba3c59a61a1b8a94795fe4499e9f0f422c2e498ef413afc8
+size 4980864408

model-00023-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e0c195a1401d49a59fe4c959e87188e7c8226bbebc6bf420fb00588ea68fcb
+size 4764874368

model-00024-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c03f3bd177137252540118572da2394ddd8c67ed53a8f9bd9428f6aa4b0945d
+size 4781670352

model-00025-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e465a55a24c637b700eaf20d59776f25c3e32124bda650bbd4074919d7d4a223
+size 4781670368

model-00026-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2790392a07400a65c62d7623b996141784454e68d881ada48e8429b20d6cb55
+size 4980864408

model-00027-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ea40c4306c1e85ac31c2556c2eba477d7e384d86df907d20b0da84097dfa71
+size 4764874368

model-00028-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9184a3bdaabb733af1cde25477dd136406000eb07b9393572a02fd65630ecfd
+size 4781670352

model-00029-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2c62f286e94e04016fb8eac4174e0f891c448f0e2d7fd710374afbc6a33edf
+size 4781670368

model-00030-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf52162575dcc41100337ede38d4ef0b8b5200ff7ffdcd0dfbc9bcfd03b42ed
+size 4980864400

model-00031-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3018cff2f3c7e2f67aefe0a5bd130c51e2346e49d8427bd284da8d81d7f19b7a
+size 285248176

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 145398710272}, "weight_map": {"lm_head.weight": "model-00001-of-00031.safetensors", "model.embed_tokens.weight": "model-00001-of-00031.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00031-of-00031.safetensors", "model.norm.weight": "model-00031-of-00031.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "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:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}