[WIP] Upload folder using huggingface_hub (multi-commit be7b2e993a25946bc4eed61be65cc5e5c06d4711088ce0f869def2e13e099da8)

README.md

@@ -1,59 +0,0 @@
----
-license: apache-2.0
-language:
-- zh
-- en
-metrics:
-- accuracy
-pipeline_tag: text-generation
-tags:
-- chat
-- evaluate
-- GenRM
----
-# flageval_judgemodel Card
-
-## Model Details
-
-flageval_judgemodel is a judgeLLM (also GenRM -- generative reward model) developed by FlagEval team (https://flageval.baai.ac.cn/#/home).
-
-- **Developed by:** [FlagEval](https://flageval.baai.ac.cn/#/home), [BAAI](https://www.baai.ac.cn/english.html)
-- **Model type:** An auto-regressive language model based on the transformer architecture.
-- **License:** Non-commercial license
-- **Finetuned from model:** [Vicuna](https://vicuna.lmsys.org).
-
-## Uses
-
-The flageval_judgemodel is designed to evaluate the performance of large language models on CLCC dataset. This dataset (https://huggingface.co/datasets/eyuansu71/CLCC_v1) is a Chinese Linguistics & Cognition Challenge dataset. The flageval_judgemodel aims to provide an automated evaluation, potentially replacing human judgment in assessing the models' outputs.
-
-
-## Quickstart
-
-
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-def promptify(prompt, pred, gold):
-    sys = "We would like to request your feedback on the performance of two AI assistants in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only two values indicating the scores for Assistant 1 and 2, respectively. The two scores are separated by a space. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment."
-    prompt_template = f"You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\n{prompt}\n\n[The Start of Assistant 1's Answer]\n{gold}\n\n[The End of Assistant 1's Answer]\n\n[The Start of Assistant 2's Answer]\n{pred}\n\n[The End of Assistant 2's Answer]\n\n[System]\n{sys}\n\n### Response:10"
-
-    return prompt_template
-
-model = AutoModelForCausalLM.from_pretrained("FlagEval/flageval_judgemodel", torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, attn_implementation="flash_attention_2").cuda()
-tokenizer = AutoTokenizer.from_pretrained("FlagEval/flageval_judgemodel")
-
-prompt, pred, gold = '1、约翰喜欢看电影，玛丽也喜欢。\n2、约翰也喜欢看足球比赛。\n请问以上两句话是否是一个意思？', "不一样", "不一样"
-
-with torch.no_grad():
-    data_sample = promptify(prompt, pred, gold)
-    input_ids = tokenizer(data_sample, return_tensors="pt").input_ids
-    output_ids = model.generate(
-        torch.as_tensor(input_ids).cuda(),
-        max_new_tokens=128,
-    )
-    text = tokenizer.decode(output_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)
-    prompt_length = len(data_sample)
-    ans = text[prompt_length:].strip()
-    pred_label = 1 if int(ans) == 10 else 0
-```

config.json

@@ -1,10 +1,8 @@
 {
-  "_name_or_path": "/home/qinbowen/llm_judge/aquila_judge/JudgeLM/judgelm/output/judgelm-debug-evaluator-v12/checkpoint-460",
+  "_name_or_path": "/home/qinbowen/models/judgelm33b/1",
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -20,10 +18,9 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.32.0",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 0,
-  "transformers_version": "4.40.0"
-}

model-00001-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:92b9aacdcb8d0defda17854f98c582c1b640b839472a6c2cdceb0b5840c439e4
-size 9818301384

model-00002-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0ade9f2402613f1d9e11ded549b93856aa8fd15c09387985fd38bd14f65f5cb3
-size 9958078152

model-00003-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c7afae70e9c79427af0e29f5f167152b307ca4cda9491dddfeebe80eaf0363b7
-size 9896709728

model-00004-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:083cb0fa678bb94b5af6fd8d13fba6cc38057669ea99d8484761205d1633606a
-size 9869446512

model-00005-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:abd55c7b341ec74443dfb41b5f25c4b7b289a1016a9230f3d5a008e2e96b243d
-size 9869446512

model-00006-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3fcab592ff5c3c49794e0a029e5eed73bb92832324af5e3d9f68950f619ec1a2
-size 9958078160

model-00007-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a1cbb965d018a4e4d671a8a023887a4abe1452f459afc8d454194e730d0f7c42
-size 5687890152

model.safetensors.index.json

@@ -1,550 +0,0 @@
-{
-  "metadata": {
-    "total_size": 65057887232
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00007-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-00002-of-00007.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-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-00003-of-00007.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-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-00003-of-00007.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-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-00004-of-00007.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-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-00004-of-00007.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00004-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-00001-of-00007.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-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-00005-of-00007.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00005-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-00005-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-00001-of-00007.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-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-00006-of-00007.safetensors",
-    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.45.self_attn.v_proj.weight": "model-00005-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-00001-of-00007.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-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-00006-of-00007.safetensors",
-    "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.54.self_attn.v_proj.weight": "model-00006-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-00006-of-00007.safetensors",
-    "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.norm.weight": "model-00007-of-00007.safetensors"
-  }
-}

special_tokens_map.json

@@ -1,24 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<unk>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

tokenizer_config.json

@@ -1,37 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "legacy": null,
-  "model_max_length": 2048,
-  "pad_token": null,
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "use_default_system_prompt": true
-}