commit f07eaf47978398486da4dc2d8957ab460d1baff5 Author: ModelHub XC Date: Fri May 22 23:31:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: TLabFineTuning/TRIP-Qwen2.5-VL-3B-Bus-LoRA Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1deb14 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text + +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + + +adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text + + +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text + +部署.png filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..7f17fb0 --- /dev/null +++ b/README.md @@ -0,0 +1,111 @@ +--- +base_model: qwen/Qwen2.5-VL-3B-Instruct +library_name: peft +--- + +# 基于 Qwen2.5-VL-3B-Instruct 的 LoRA 头盔检测模型 + +本模型是基于 Qwen2.5-VL-3B-Instruct 微调得到的 LoRA 轻量化模型，专门针对骑行人员头盔佩戴检测任务优化。 + +## 模型详情 + +本模型为 Qwen2.5-VL-3B-Instruct 的轻量级 LoRA 适配器，经微调后可判断图片中的骑行者是否佩戴安全头盔。 + +模型支持图像+文本指令输入，仅输出以下两种结果： +- 佩戴头盔 +- 未佩戴头盔 + +- 研发团队：TLabFineTuning +- 模型类型：多模态大模型 LoRA 适配器 +- 语言：中文 +- 开源协议：Apache 2.0 +- 基础模型：Qwen2.5-VL-3B-Instruct + +## 使用场景 + +- 交通安全监测 +- 骑行人员行为分析 +- 智能安防监控 + +## 模型局限性 + +- 模型在清晰、无遮挡的骑行者图像上效果最佳 +- 光线不足、遮挡严重的图像会降低识别准确率 +- 模型基于少量样本训练，泛化能力有限 + +## 快速使用代码 +```python +import torch +from peft import PeftModel +from transformers import AutoProcessor, AutoTokenizer, Qwen2_5_VLForConditionalGeneration +from qwen_vl_utils import process_vision_info +from PIL import Image + +base_model_path = "qwen/Qwen2.5-VL-3B-Instruct" +lora_model_path = "./" +prompt = "识别图片中骑行者是否佩戴头盔，仅输出：佩戴头盔/未佩戴头盔" +device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") + +tokenizer = AutoTokenizer.from_pretrained(base_model_path, use_fast=False, trust_remote_code=True) +processor = AutoProcessor.from_pretrained(base_model_path, use_fast=False, trust_remote_code=True) +base_model = Qwen2_5_VLForConditionalGeneration.from_pretrained( + base_model_path, torch_dtype=torch.bfloat16, trust_remote_code=True +).to(device) +model = PeftModel.from_pretrained(base_model, lora_model_path).to(device) +model.eval() + +def infer_helmet(image_path): + img = Image.open(image_path).convert("RGB") + messages = [ + {"role": "user", "content": [{"type": "image", "image": img}, {"type": "text", "text": prompt}]} + ] + text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) + image_inputs, _ = process_vision_info(messages) + inputs = processor(text=[text], images=image_inputs, return_tensors="pt").to(device) + + with torch.no_grad(): + outputs = model.generate(**inputs, max_new_tokens=10, do_sample=False) + result = tokenizer.decode(outputs[0], skip_special_tokens=True).split("assistant")[-1].strip() + return result + ``` +## 训练信息 + +- 学习率：1e-5 +- LoRA 秩：2 +- 模型大小：1.8MB +- 训练设备：8GB 显存显卡 + +## 模型检测效果 + +### 图1：Qwen 微调结果 +Qwen微调结果 + +### 图2：Qwen 识别单人图片结果 +单人图片识别结果 + +### 图3：Qwen 识别多人图片结果 +多人图片识别结果 + +### 图4：微调模型部署后香橙派摄像头拍照识别结果 +部署后摄像头识别结果 + +### 图5：实地部署图片 +部署 + +## 项目团队与贡献 + +### 模型研发与维护 +TRIP 项目小组 + +### 核心贡献者 +谭妍、刘天赐、王思远、薛栋、张乐鑫、张媛 + +### 支持单位 +东南大学交通学院 +东南大学网络与信息中心 + +### 致谢 +感谢东南大学网络与信息中心提供的晟腾算力与香橙派硬件支持 + +### 免责声明 +本模型仅用于科研与技术验证目的。使用者需遵守相关法律法规，并对模型输出结果的使用自行承担责任。 \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.json b/chat_template.json new file mode 100644 index 0000000..13303be --- /dev/null +++ b/chat_template.json @@ -0,0 +1,3 @@ +{ + "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}" +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..13c01f9 --- /dev/null +++ b/config.json @@ -0,0 +1,66 @@ +{ + "architectures": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dropout": 0.0, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "image_token_id": 151655, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 128000, + "max_window_layers": 70, + "model_type": "qwen2_5_vl", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_section": [ + 16, + 24, + 24 + ], + "rope_type": "default", + "type": "default" + }, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "use_cache": false, + "use_sliding_window": false, + "video_token_id": 151656, + "vision_config": { + "depth": 32, + "fullatt_block_indexes": [ + 7, + 15, + 23, + 31 + ], + "hidden_act": "silu", + "hidden_size": 1280, + "in_channels": 3, + "in_chans": 3, + "intermediate_size": 3420, + "model_type": "qwen2_5_vl", + "num_heads": 16, + "out_hidden_size": 2048, + "patch_size": 14, + "spatial_merge_size": 2, + "spatial_patch_size": 14, + "temporal_patch_size": 2, + "tokens_per_second": 2, + "torch_dtype": "bfloat16", + "window_size": 112 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vision_token_id": 151654, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..3b2aaf5 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"image-captioning"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8596575 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 1e-06, + "transformers_version": "4.51.3" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..2ef564c --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e04af9c950e393054010dcef499c3f005e803e9b2da1a09b96a26c33266eb1 +size 1823241 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..8b59cd3 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b8dd3842613d99973336c4bfd2b7656696b067cd436a9daaacbefc0ec0ef409 +size 1978621000 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..511edb9 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:766a5eca00c8c7e01e0b64c790843c87accec28b167d15bf6737d95f8da1217e +size 1995630768 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..f3c2027 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1934d22f12aef78e16d4bfd920fc49c07e278773a4e978b2d3780e6ad608d165 +size 1993528056 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..b44996a --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34195b43bf737171d12d8ca84c4ba5ae548f846d188cf1b631076e7d187cc08a +size 1541557696 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..aaa4790 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,831 @@ +{ + "metadata": { + "total_size": 7509245952 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors", + "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors", + "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors", + "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors", + "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors", + "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors", + "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..ee08cdd --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,29 @@ +{ + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "max_pixels": 12845056, + "merge_size": 2, + "min_pixels": 3136, + "patch_size": 14, + "processor_class": "Qwen2_5_VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "temporal_patch_size": 2 +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "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 + } +} diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..374859f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,208 @@ +{ + "add_bos_token": false, + "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 + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_config.json b/train_config.json new file mode 100644 index 0000000..1d45cde --- /dev/null +++ b/train_config.json @@ -0,0 +1,12 @@ +{ + "base_model": "D:\\models\\qwen\\Qwen2___5-VL-3B-Instruct", + "lora_r": 2, + "lora_alpha": 4, + "learning_rate": 1e-05, + "max_vision_tokens": 64, + "batch_size": 10, + "total_samples": 135, + "trained_samples": 136, + "merged": true, + "note": "此目录包含完整独立模型，无需原基础模型即可加载" +} \ No newline at end of file diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..44dd190 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0592c64c8ca6276a97c9c7d8c62c3336ba87131e31bd702e68ea149af42b3ed +size 3535052 diff --git a/图片1.png b/图片1.png new file mode 100644 index 0000000..b9bb220 Binary files /dev/null and b/图片1.png differ diff --git a/图片2.png b/图片2.png new file mode 100644 index 0000000..9c56a2c Binary files /dev/null and b/图片2.png differ diff --git a/图片3.png b/图片3.png new file mode 100644 index 0000000..6c3ead2 Binary files /dev/null and b/图片3.png differ diff --git a/图片4.png b/图片4.png new file mode 100644 index 0000000..21d9a39 Binary files /dev/null and b/图片4.png differ diff --git a/部署.png b/部署.png new file mode 100644 index 0000000..80e7652 --- /dev/null +++ b/部署.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c2a391de644290082124c73dc833404da578bca2152e16c09ddde69d042a42 +size 2171271