commit 508affde84f63bb4daac26bde3f0a05cd12efbc3 Author: ModelHub XC Date: Sun Aug 23 03:33:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Salesforce/GTA1-7B-2507 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6781a9e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,55 @@ +*.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 +*.model 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 +*.pt 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 + +tokenizer.json 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 +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors 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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..cd6a4a5 --- /dev/null +++ b/README.md @@ -0,0 +1,225 @@ +--- +language: +- en +license: apache-2.0 +metrics: +- accuracy +pipeline_tag: image-text-to-text +tags: +- VLM +- Computer-Use-Agent +- OS-Agent +- GUI +- Grounding +library_name: transformers +--- + +# Introduction + +Reinforcement learning (RL) (e.g., GRPO) helps with grounding because of its inherent objective alignment—rewarding successful clicks—rather than encouraging long textual Chain-of-Thought (CoT) reasoning. Unlike approaches that rely heavily on verbose CoT reasoning, GRPO directly incentivizes actionable and grounded responses. Based on findings from our [blog](https://huggingface.co/blog/HelloKKMe/grounding-r1), we share state-of-the-art GUI grounding models trained using GRPO. + +# Grounding Performance + +We follow the standard evaluation protocol and benchmark our model on three challenging datasets. Our method consistently achieves the best results among all open-source model families. Below are the comparative results: + +| **Model** | **Size** | **Open Source** | **ScreenSpot-V2** | **ScreenSpotPro** | **OSWORLD-G** | **OSWORLD-G-Refined** | +|-------------------|:--------:|:---------------:|:-----------------:|:-----------------:|:-----------------:|:-----------------:| +| OpenAI CUA | — | ❌ | 87.9 | 23.4 | — | — | +| Claude 3.7 | — | ❌ | 87.6 | 27.7 | — | — | +| JEDI-7B | 7B | ✅ | 91.7 | 39.5 | 54.1 | — | +| SE-GUI | 7B | ✅ | 90.3 | 47.0 | — | — | +| UI-TARS | 7B | ✅ | 91.6 | 35.7 | 47.5 | — | +| UI-TARS-1.5* | 7B | ✅ | 89.7* | 42.0* | 52.8* | 64.2* | +| UGround-v1-7B | 7B | ✅ | — | 31.1 | — | 36.4 | +| Qwen2.5-VL-32B-Instruct | 32B | ✅ | 91.9* | 48.0 | 46.5 | 59.6* | +| UGround-v1-72B | 72B | ✅ | — | 34.5 | — | — | +| Qwen2.5-VL-72B-Instruct | 72B | ✅ | 94.00* | 53.3 | — | 62.2* | +| UI-TARS | 72B | ✅ | 90.3 | 38.1 | — | — | +| OpenCUA | 7B | ✅ | 92.3 | 50.0 | 55.3 | 68.3* | +| OpenCUA | 32B | ✅ | 93.4 | 55.3 | 59.6 | 70.2* | +| GTA1-2507 (Ours) | 7B | ✅ | 92.4 *(∆ +2.7)* | 50.1*(∆ +8.1)* | 55.1 *(∆ +2.3)* | 67.7 *(∆ +3.5)* | +| GTA1 (Ours) | 7B | ✅ | 93.4 *(∆ +0.1)* | 55.5*(∆ +5.5)* | 60.1*(∆ +4.8)* | 68.8*(∆ +0.5)* | +| GTA1 (Ours) | 32B | ✅ | 95.2 *(∆ +1.8)* | 63.6*(∆ +8.3)* | 65.2 *(∆ +5.6)* | 72.2*(∆ +2.0)* | + +> **Note:** +> - Model size is indicated in billions (B) of parameters. +> - A dash (—) denotes results that are currently unavailable. +> - A superscript asterisk (﹡) denotes our evaluated result. +> - UI-TARS-1.5 7B, OpenCUA-7B, and OpenCUA-32B are applied as our baseline models. +> - ∆ indicates the performance improvement (∆) of our model compared to its baseline. + + +# Agent Performance + +## OSWorld and OSWorld-Verified Benchmarks + +We evaluate our models on the OSWorld and OSWorld-Verified benchmarks following the standard evaluation protocol. The results demonstrate strong performance across both datasets. + +| **Agent Model** | **Step** | **OSWorld** | **OSWorld-Verified** | +|-----------------|:--------:|:-----------:|:-------------------:| +| **Proprietary Models** | +| Claude 3.7 Sonnet | 100 | 28.0 | — | +| OpenAI CUA 4o | 200 | 38.1 | — | +| UI-TARS-1.5 | 100 | 42.5 | 41.8 | +| OpenAI CUA o3 | 200 | 42.9 | — | +| **Open-Source Models** | +| Aria-UI w/ GPT-4o | 15 | 15.2 | — | +| Aguvis-72B w/ GPT-4o | 15 | 17.0 | — | +| UI-TARS-72B-SFT | 50 | 18.8 | — | +| Agent S w/ Claude-3.5-Sonnet | 15 | 20.5 | — | +| Agent S w/ GPT-4o | 15 | 20.6 | — | +| UI-TARS-72B-DPO | 15 | 22.7 | — | +| UI-TARS-72B-DPO | 50 | 24.6 | — | +| UI-TARS-1.5-7B | 100 | 26.9 | 27.4 | +| Jedi-7B w/ o3 | 100 | — | 51.0 | +| Jedi-7B w/ GPT-4o | 100 | 27.0 | — | +| Agent S2 w/ Claude-3.7-Sonnet | 50 | 34.5 | — | +| Agent S2 w/ Gemini-2.5-Pro | 50 | 41.4 | 45.8 | +| Agent S2.5 w/ o3 | 100 | — | 56.0 | +| Agent S2.5 w/ GPT-5 | 100 | — | 58.4 | +| CoAct-1 w/o3 & o4mini & OpenAI CUA 4o | 150 | — | 60.8 | +| GTA1-7B-2507 w/ o3 | 100 | 45.2 | 53.1 | +| GTA1-7B-2507 w/ GPT-5 | 100 | — | 61.0 | +| GTA1-32B w/ o3 | 100 | — | 55.4 | +| GTA1-32B w/ GPT-5 | 100 | — | 63.4 | + +> **Note:** A dash (—) indicates unavailable results. + +## WindowsAgentArena Benchmark + +We also evaluate our models on the WindowsAgentArena benchmark, demonstrating strong performance in Windows-specific GUI automation tasks. + +| **Agent Model** | **Step** | **Success Rate** | +|-----------------|:--------:|:---------------:| +| Kimi-VL | 15 | 10.4 | +| WAA | — | 19.5 | +| Jedi w/ GPT-4o | 100 | 33.7 | +| GTA1-7B-2507 w/ o3 | 100 | 47.9 | +| GTA1-7B-2507 w/ GPT-5 | 100 | 49.2 | +| GTA1-32B w/ o3 | 100 | 51.2 | +| GTA1-32B w/ GPT-5 | 100 | 50.6 | + +> **Note:** A dash (—) indicates unavailable results. + +# Inference +Below is a code snippet demonstrating how to run inference using a trained model. + +```python +from PIL import Image +from qwen_vl_utils import process_vision_info, smart_resize +from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor +import torch +import re + +SYSTEM_PROMPT = ''' +You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. The image resolution is height {height} and width {width}. For elements with area, return the center point. + +Output the coordinate pair exactly: +(x,y) +''' +SYSTEM_PROMPT=SYSTEM_PROMPT.strip() + +# Function to extract coordinates from model output +def extract_coordinates(raw_string): + try: + matches = re.findall(r"\((-?\d*\.?\d+),\s*(-?\d*\.?\d+)\)", raw_string) + return [tuple(map(int, match)) for match in matches][0] + except: + return 0,0 + +# Load model and processor +model_path = "HelloKKMe/GTA1-7B" +max_new_tokens = 32 + +model = Qwen2_5_VLForConditionalGeneration.from_pretrained( + model_path, + torch_dtype=torch.bfloat16, + attn_implementation="flash_attention_2", + device_map="auto" +) +processor = AutoProcessor.from_pretrained( + model_path, + min_pixels=3136, + max_pixels= 4096 * 2160 +) + +# Load and resize image +image = Image.open("file path") +instruction = "description" # Instruction for grounding +width, height = image.width, image.height + +resized_height, resized_width = smart_resize( + image.height, + image.width, + factor=processor.image_processor.patch_size * processor.image_processor.merge_size, + min_pixels=processor.image_processor.min_pixels, + max_pixels=processor.image_processor.max_pixels, +) +resized_image = image.resize((resized_width, resized_height)) +scale_x, scale_y = width / resized_width, height / resized_height + +# Prepare system and user messages +system_message = { + "role": "system", + "content": SYSTEM_PROMPT.format(height=resized_height,width=resized_width) +} + +user_message = { + "role": "user", + "content": [ + {"type": "image", "image": resized_image}, + {"type": "text", "text": instruction} + ] +} + +# Tokenize and prepare inputs +image_inputs, video_inputs = process_vision_info([system_message, user_message]) +text = processor.apply_chat_template([system_message, user_message], tokenize=False, add_generation_prompt=True) +inputs = processor(text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt") +inputs = inputs.to(model.device) + +# Generate prediction +output_ids = model.generate(**inputs, max_new_tokens=max_new_tokens, do_sample=False, temperature=1.0, use_cache=True) +generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)] +output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)[0] + +# Extract and rescale coordinates +pred_x, pred_y = extract_coordinates(output_text) +pred_x*=scale_x +pred_y*=scale_y +print(pred_x,pred_y) +``` + +## Ethical Considerations + +This model is released for research and educational purposes. While our model demonstrates strong performance on GUI benchmarks, users should carefully evaluate its suitability for their specific use cases. + +**Important Considerations:** +- **Accuracy Limitations:** Like all AI systems, this model may produce incorrect outputs or fail to accurately identify GUI elements in certain scenarios. +- **Safety and Security:** Exercise caution when deploying GUI automation agents, especially in production environments where incorrect actions could affect system integrity or data security. +- **Human Oversight:** We recommend maintaining appropriate human supervision when using this model for automated GUI interactions. +- **Compliance:** Users are responsible for ensuring their use of this model complies with applicable laws, regulations, and organizational policies. + +**Recommended Best Practices:** +- Thoroughly test the model in controlled environments before production deployment +- Implement safeguards and error handling mechanisms +- Consider the potential impact of automated actions on user systems and data +- Regularly monitor and validate model performance in your specific domain + +For further guidance on use cases, refer to our AUP and AI AUP. + +## Citation + +If you're using any GTA model or find it helpful in your research, please cite it as follows: + +```markdown +@article{yang2025gta1guitesttimescaling, + title={GTA1: GUI Test-time Scaling Agent}, + author={Yan Yang and Dongxu Li and Yutong Dai and Yuhao Yang and Ziyang Luo and Zirui Zhao and Zhiyuan Hu and Junzhe Huang and Amrita Saha and Zeyuan Chen and Ran Xu and Liyuan Pan and Silvio Savarese and Caiming Xiong and Junnan Li}, + year={2025}, + eprint={2507.05791}, + archivePrefix={arXiv}, + primaryClass={cs.AI}, + url={https://arxiv.org/abs/2507.05791}, +} +``` 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..b59417d --- /dev/null +++ b/config.json @@ -0,0 +1,65 @@ +{ + "architectures": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "image_token_id": 151655, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 128000, + "max_window_layers": 28, + "model_type": "qwen2_5_vl", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "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": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.0", + "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": 3584, + "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": 152064 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..4aef15d --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a03d41e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 151643, + "eos_token_id": 151645, + "transformers_version": "4.51.0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..69c22fd --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c7c4d87cd0f8a32dae22a57fd7abae3bf51f4561e3b7432428f7cc0420a5e0 +size 4968243304 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..538de6c --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0edcf66e153ae7e7620e46c06cb788334caf6e9febd224fc0920f90fc0559df5 +size 4991495816 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..eca2212 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c29dbfa4d4f9d84714c91cd20224c607784510fb78fe1589e7a736ea1cd40f +size 4932751040 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..7f0ae74 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ed3ae02bbb01313eea54e8e245a7d1057c013eff99ed995dbf86b56489c910 +size 1691924384 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6a84000 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,736 @@ +{ + "metadata": { + "total_size": 16584333312 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-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-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-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-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-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-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-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-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-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-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-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.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-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-00001-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-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-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..82a7c7c --- /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": 8847360, + "merge_size": 2, + "min_pixels": 3136, + "patch_size": 14, + "processor_class": "Qwen2_5_VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 8847360, + "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.json b/tokenizer.json new file mode 100644 index 0000000..6c06829 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214 +size 11422063 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..51072a4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,215 @@ +{ + "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": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "max_length": null, + "max_pixels": 8847360, + "min_pixels": 3136, + "model_max_length": 131072, + "pad_to_multiple_of": null, + "pad_token": "<|endoftext|>", + "pad_token_type_id": 0, + "padding_side": "right", + "processor_class": "Qwen2_5_VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833