Upload folder using huggingface_hub

.gitattributes

@@ -33,21 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-blobs/09782507221803a2287fcacb4ef166317fee2e62839ad43caa4c2f9ec461f77c filter=lfs diff=lfs merge=lfs -text
-blobs/2f452321174378d32090e7c94cffa3b43a4539e2f407f936b12a35639122005a filter=lfs diff=lfs merge=lfs -text
-blobs/3168a6cbc214a1e83a04235e676fad12952ef36010442e02e007701ea23037e4 filter=lfs diff=lfs merge=lfs -text
-blobs/39f8a745a63bdd2552d0aaa25728108ccd66718611bb8f1b1d1998a86e5054a1 filter=lfs diff=lfs merge=lfs -text
-blobs/46d25976bd3a6cb3055a1376a5a3ffec0f350d6a34a9749cbdd0495409e5e744 filter=lfs diff=lfs merge=lfs -text
-blobs/48dd3dd98f76920c997a634e4f390f4ab11e629c7d76d752ef94844477bea183 filter=lfs diff=lfs merge=lfs -text
-blobs/4a79addd10e3e66dcc4b53822ed86a7e31197ca3a54eaacc2a8140921d158f47 filter=lfs diff=lfs merge=lfs -text
-blobs/4f76e418f06f6b9b7f8a524f6405b1baee70ca7418a9a660f7537c490263ae35 filter=lfs diff=lfs merge=lfs -text
-blobs/66dcd62e9496e9b8c456f6c95df848034fe648f4414ff1088a35f7a6efa44156 filter=lfs diff=lfs merge=lfs -text
-blobs/83154d2dd5e7064947716c0930013e17943c378f80343c5f6067e8afdc291c1f filter=lfs diff=lfs merge=lfs -text
-blobs/87afe66c34acb2c5a7b118db74939afe8f47613f442eca4ed0f38a02e4e93fed filter=lfs diff=lfs merge=lfs -text
-blobs/98d1b9f92f0154fc8f7cbfe0c6d7d3955b088cf2c520e1a41c2f157c07c5b6bf filter=lfs diff=lfs merge=lfs -text
-blobs/9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa filter=lfs diff=lfs merge=lfs -text
-blobs/ab1e3dfb60f12733be7aae9274996f14814cc4680a707e1a201a0b627b4373ea filter=lfs diff=lfs merge=lfs -text
-blobs/c4fdcf55d00ffa11e55fcc79ab5cca51d50a1d267219820ac66c36be0177fb23 filter=lfs diff=lfs merge=lfs -text
-blobs/d17169ad645848ed1c32ef9d34529d80bbe052b3f5309d9f7973ed0fde30c09a filter=lfs diff=lfs merge=lfs -text
-blobs/f3611e6a6ce31c332c9fcbaa2d5975ad981a6aa05470b66df74dab8811f7cb0a filter=lfs diff=lfs merge=lfs -text
-snapshots/92affcfb5e90a59ad7b4e1fc45212ae5f37fbcc1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,450 @@
+---
+tags:
+- vllm
+- vision
+- fp8
+license: apache-2.0
+license_link: >-
+  https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md
+language:
+- en
+base_model: Qwen/Qwen2.5-VL-72B-Instruct
+library_name: transformers
+---
+
+# Qwen2.5-VL-72B-Instruct-quantized-FP8-Dynamic
+
+## Model Overview
+- **Model Architecture:** Qwen2.5-VL-72B-Instruct
+  - **Input:** Vision-Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** FP8
+  - **Activation quantization:** FP8
+- **Release Date:** 2/24/2025
+- **Version:** 1.0
+- **Model Developers:** Neural Magic
+
+Quantized version of [Qwen/Qwen2.5-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct).
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights of [Qwen/Qwen2.5-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct) to FP8 data type, ready for inference with vLLM >= 0.5.2.
+
+## Deployment
+
+### Use with vLLM
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+from vllm.assets.image import ImageAsset
+from vllm import LLM, SamplingParams
+
+# prepare model
+llm = LLM(
+    model="neuralmagic/Qwen2.5-VL-72B-Instruct-FP8-Dynamic",
+    trust_remote_code=True,
+    max_model_len=4096,
+    max_num_seqs=2,
+)
+
+# prepare inputs
+question = "What is the content of this image?"
+inputs = {
+    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
+    "multi_modal_data": {
+        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
+    },
+}
+
+# generate response
+print("========== SAMPLE GENERATION ==============")
+outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
+print(f"PROMPT  : {outputs[0].prompt}")
+print(f"RESPONSE: {outputs[0].outputs[0].text}")
+print("==========================================")
+```
+
+vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below as part a multimodal announcement blog.
+
+<details>
+  <summary>Model Creation Code</summary>
+  
+```python
+import requests
+import torch
+from PIL import Image
+from transformers import AutoProcessor
+from llmcompressor.transformers import oneshot
+from llmcompressor.transformers.tracing import (
+    TraceableQwen2_5_VLForConditionalGeneration,
+)
+from llmcompressor.modifiers.quantization import QuantizationModifier
+
+# Load model.
+model_id = Qwen/Qwen2.5-VL-72B-Instruct
+model = TraceableQwen2_5_VLForConditionalGeneration.from_pretrained(
+    model_id, device_map="auto", torch_dtype="auto"
+)
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
+
+# Recipe
+recipe = [
+    QuantizationModifier(
+        targets="Linear",
+        scheme="FP8_DYNAMIC",
+        sequential_targets=["MistralDecoderLayer"],
+        ignore=["re:.*lm_head", "re:vision_tower.*", "re:multi_modal_projector.*"],
+    ),
+]
+
+SAVE_DIR=f"{model_id.split('/')[1]}-FP8-Dynamic"
+
+# Perform oneshot
+oneshot(
+    model=model,
+    recipe=recipe,
+    trust_remote_code_model=True,
+    output_dir=SAVE_DIR
+)
+
+
+```
+</details>
+
+## Evaluation
+
+The model was evaluated using [mistral-evals](https://github.com/neuralmagic/mistral-evals) for vision-related tasks and using [lm_evaluation_harness](https://github.com/neuralmagic/lm-evaluation-harness) for select text-based benchmarks. The evaluations were conducted using the following commands:
+
+<details>
+<summary>Evaluation Commands</summary>
+  
+### Vision Tasks
+- vqav2
+- docvqa
+- mathvista
+- mmmu
+- chartqa
+
+```
+vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7
+
+python -m eval.run eval_vllm \
+        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
+        --url http://0.0.0.0:8000 \
+        --output_dir ~/tmp \
+        --eval_name <vision_task_name>
+```
+
+### Text-based Tasks
+#### MMLU
+  
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
+  --tasks mmlu \
+  --num_fewshot 5 \
+  --batch_size auto \
+  --output_path output_dir
+
+```
+
+#### MGSM
+
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="<model_name>",dtype=auto,max_model_len=4096,max_gen_toks=2048,max_num_seqs=128,tensor_parallel_size=<n>,gpu_memory_utilization=0.9 \
+  --tasks mgsm_cot_native \
+  --num_fewshot 0 \
+  --batch_size auto \
+  --output_path output_dir
+
+```
+</details>
+
+### Accuracy
+
+<table>
+  <thead>
+    <tr>
+      <th>Category</th>
+      <th>Metric</th>
+      <th>Qwen/Qwen2.5-VL-72B-Instruct</th>
+      <th>neuralmagic/Qwen2.5-VL-72B-Instruct-FP8-Dynamic</th>
+      <th>Recovery (%)</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="6"><b>Vision</b></td>
+      <td>MMMU (val, CoT)<br><i>explicit_prompt_relaxed_correctness</i></td>
+      <td>64.33</td>
+      <td>66.88</td>
+      <td>103.96%</td>
+    </tr>
+    <tr>
+      <td>VQAv2 (val)<br><i>vqa_match</i></td>
+      <td>81.94</td>
+      <td>81.94</td>
+      <td>100.00%</td>
+    </tr>
+    <tr>
+      <td>DocVQA (val)<br><i>anls</i></td>
+      <td>94.71</td>
+      <td>94.64</td>
+      <td>99.93%</td>
+    </tr>
+    <tr>
+      <td>ChartQA (test, CoT)<br><i>anywhere_in_answer_relaxed_correctness</i></td>
+      <td>88.96</td>
+      <td>89.04</td>
+      <td>100.09%</td>
+    </tr>
+    <tr>
+      <td>Mathvista (testmini, CoT)<br><i>explicit_prompt_relaxed_correctness</i></td>
+      <td>78.18</td>
+      <td>77.78</td>
+      <td>99.49%</td>
+    </tr>
+    <tr>
+      <td><b>Average Score</b></td>
+      <td><b>81.62</b></td>
+      <td><b>81.86</b></td>
+      <td><b>100.29%</b></td>
+    </tr>
+    <tr>
+      <td rowspan="2"><b>Text</b></td>
+      <td>MGSM (CoT)</td>
+      <td>75.45</td>
+      <td>49.65</td>
+      <td>65.81%</td>
+    </tr>
+    <tr>
+      <td>MMLU (5-shot)</td>
+      <td>86.16</td>
+      <td>86.12</td>
+      <td>99.95%</td>
+    </tr>
+  </tbody>
+</table>
+
+
+## Inference Performance
+
+
+This model achieves up to 1.79x speedup in single-stream deployment and up to 1.84x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario.
+The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
+
+<details>
+<summary>Benchmarking Command</summary>
+```
+  guidellm --model neuralmagic/Qwen2.5-VL-72B-Instruct-FP8-Dynamic --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server
+```
+
+</details>
+
+
+### Single-stream performance (measured with vLLM version 0.7.2)
+
+<table border="1" class="dataframe">
+  <thead>
+    <tr>
+      <th></th>
+      <th></th>
+      <th></th>
+      <th></th>
+      <th style="text-align: center;" colspan="2" >Document Visual Question Answering<br>1680W x 2240H<br>64/128</th>
+      <th style="text-align: center;" colspan="2" >Visual Reasoning <br>640W x 480H<br>128/128</th>
+      <th style="text-align: center;" colspan="2" >Image Captioning<br>480W x 360H<br>0/128</th>
+    </tr>
+    <tr>
+      <th>Hardware</th>
+      <th>Number of GPUs</th>
+      <th>Model</th>
+      <th>Average Cost Reduction</th>
+      <th>Latency (s)</th>
+      <th>Queries Per Dollar</th>
+      <th>Latency (s)th>
+      <th>Queries Per Dollar</th>
+      <th>Latency (s)</th>
+      <th>Queries Per Dollar</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th rowspan="3" valign="top">A100</td>
+      <td>4</td>
+      <td>Qwen/Qwen2.5-VL-72B-Instruct</td>
+      <td></td>
+      <td>6.4</td>
+      <td>78</td>
+      <td>4.5</td>
+      <td>111</td>
+      <td>4.4</td>
+      <td>113</td>
+    </tr>
+    <tr>
+      <td>2</td>
+      <td>neuralmagic/Qwen2.5-VL-72B-Instruct-quantized.w8a8</td>
+      <td>1.85</td>
+      <td>7.0</td>
+      <td>143</td>
+      <td>4.9</td>
+      <td>205</td>
+      <td>4.8</td>
+      <td>211</td>
+    </tr>
+    <tr>
+      <td>1</td>
+      <td>neuralmagic/Qwen2.5-VL-72B-Instruct-quantized.w4a16</td>
+      <td>3.33</td>
+      <td>9.4</td>
+      <td>213</td>
+      <td>5.1</td>
+      <td>396</td>
+      <td>4.8</td>
+      <td>420</td>
+    </tr>
+    <tr>
+      <th rowspan="3" valign="top">H100</td>
+      <td>4</td>
+      <td>Qwen/Qwen2.5-VL-72B-Instruct</td>
+      <td></td>
+      <td>4.3</td>
+      <td>68</td>
+      <td>3.0</td>
+      <td>97</td>
+      <td>2.9</td>
+      <td>100</td>
+    </tr>
+    <tr>
+      <td>2</td>
+      <td>neuralmagic/Qwen2.5-VL-72B-Instruct-FP8-Dynamic</td>
+      <td>1.79</td>
+      <td>4.6</td>
+      <td>122</td>
+      <td>3.3</td>
+      <td>173</td>
+      <td>3.2</td>
+      <td>177</td>
+    </tr>
+    <tr>
+      <td>1</td>
+      <td>neuralmagic/Qwen2.5-VL-72B-Instruct-quantized.w4a16</td>
+      <td>5.66</td>
+      <td>4.3</td>
+      <td>252</td>
+      <td>4.4</td>
+      <td>251</td>
+      <td>4.2</td>
+      <td>259</td>
+    </tr>
+  </tbody>
+</table>
+
+**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens
+
+**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).
+
+### Multi-stream asynchronous performance (measured with vLLM version 0.7.2)
+
+<table border="1" class="dataframe">
+  <thead>
+    <tr>
+      <th></th>
+      <th></th>
+      <th></th>
+      <th style="text-align: center;" colspan="2" >Document Visual Question Answering<br>1680W x 2240H<br>64/128</th>
+      <th style="text-align: center;" colspan="2" >Visual Reasoning <br>640W x 480H<br>128/128</th>
+      <th style="text-align: center;" colspan="2" >Image Captioning<br>480W x 360H<br>0/128</th>
+    </tr>
+    <tr>
+      <th>Hardware</th>
+      <th>Model</th>
+      <th>Average Cost Reduction</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>Queries Per Dollar</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>Queries Per Dollar</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>Queries Per Dollar</th>
+    </tr>
+  </thead>
+  <tbody style="text-align: center">
+    <tr>
+      <th rowspan="3" valign="top">A100x4</th>
+      <td>Qwen/Qwen2.5-VL-72B-Instruct</td>
+      <td></td>
+      <td>0.4</td>
+      <td>180</td>
+      <td>1.1</td>
+      <td>539</td>
+      <td>1.2</td>
+      <td>595</td>
+    </tr>
+    <tr>
+      <td>neuralmagic/Qwen2.5-VL-72B-Instruct-quantized.w8a8</td>
+      <td>1.80</td>
+      <td>0.6</td>
+      <td>289</td>
+      <td>2.0</td>
+      <td>1020</td>
+      <td>2.3</td>
+      <td>1133</td>
+    </tr>
+    <tr>
+      <td>neuralmagic/Qwen2.5-VL-72B-Instruct-quantized.w4a16</td>
+      <td>2.75</td>
+      <td>0.7</td>
+      <td>341</td>
+      <td>3.2</td>
+      <td>1588</td>
+      <td>4.1</td>
+      <td>2037</td>
+    </tr>
+    <tr>
+      <th rowspan="3" valign="top">H100x4</th>
+      <td>Qwen/Qwen2.5-VL-72B-Instruct</td>
+      <td></td>
+      <td>0.5</td>
+      <td>134</td>
+      <td>1.2</td>
+      <td>357</td>
+      <td>1.3</td>
+      <td>379</td>
+    </tr>
+    <tr>
+      <td>neuralmagic/Qwen2.5-VL-72B-Instruct-FP8-Dynamic</td>
+      <td>1.73</td>
+      <td>0.9</td>
+      <td>247</td>
+      <td>2.2</td>
+      <td>621</td>
+      <td>2.4</td>
+      <td>669</td>
+    </tr>
+    <tr>
+      <td>neuralmagic/Qwen2.5-VL-72B-Instruct-quantized.w4a16</td>
+      <td>8.27</td>
+      <td>3.3</td>
+      <td>913</td>
+      <td>3.3</td>
+      <td>898</td>
+      <td>3.6</td>
+      <td>991</td>
+    </tr>
+  </tbody>
+</table>
+
+**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens
+
+**QPS: Queries per second.
+
+**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 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
+}

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 %}"
+}

config.json

@@ -0,0 +1,255 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-VL-72B-Instruct",
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 80,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": 1.323305644571225,
+    "ignore": [
+      "visual.blocks.0.attn.qkv",
+      "visual.blocks.0.attn.proj",
+      "visual.blocks.0.mlp.gate_proj",
+      "visual.blocks.0.mlp.up_proj",
+      "visual.blocks.0.mlp.down_proj",
+      "visual.blocks.1.attn.qkv",
+      "visual.blocks.1.attn.proj",
+      "visual.blocks.1.mlp.gate_proj",
+      "visual.blocks.1.mlp.up_proj",
+      "visual.blocks.1.mlp.down_proj",
+      "visual.blocks.2.attn.qkv",
+      "visual.blocks.2.attn.proj",
+      "visual.blocks.2.mlp.gate_proj",
+      "visual.blocks.2.mlp.up_proj",
+      "visual.blocks.2.mlp.down_proj",
+      "visual.blocks.3.attn.qkv",
+      "visual.blocks.3.attn.proj",
+      "visual.blocks.3.mlp.gate_proj",
+      "visual.blocks.3.mlp.up_proj",
+      "visual.blocks.3.mlp.down_proj",
+      "visual.blocks.4.attn.qkv",
+      "visual.blocks.4.attn.proj",
+      "visual.blocks.4.mlp.gate_proj",
+      "visual.blocks.4.mlp.up_proj",
+      "visual.blocks.4.mlp.down_proj",
+      "visual.blocks.5.attn.qkv",
+      "visual.blocks.5.attn.proj",
+      "visual.blocks.5.mlp.gate_proj",
+      "visual.blocks.5.mlp.up_proj",
+      "visual.blocks.5.mlp.down_proj",
+      "visual.blocks.6.attn.qkv",
+      "visual.blocks.6.attn.proj",
+      "visual.blocks.6.mlp.gate_proj",
+      "visual.blocks.6.mlp.up_proj",
+      "visual.blocks.6.mlp.down_proj",
+      "visual.blocks.7.attn.qkv",
+      "visual.blocks.7.attn.proj",
+      "visual.blocks.7.mlp.gate_proj",
+      "visual.blocks.7.mlp.up_proj",
+      "visual.blocks.7.mlp.down_proj",
+      "visual.blocks.8.attn.qkv",
+      "visual.blocks.8.attn.proj",
+      "visual.blocks.8.mlp.gate_proj",
+      "visual.blocks.8.mlp.up_proj",
+      "visual.blocks.8.mlp.down_proj",
+      "visual.blocks.9.attn.qkv",
+      "visual.blocks.9.attn.proj",
+      "visual.blocks.9.mlp.gate_proj",
+      "visual.blocks.9.mlp.up_proj",
+      "visual.blocks.9.mlp.down_proj",
+      "visual.blocks.10.attn.qkv",
+      "visual.blocks.10.attn.proj",
+      "visual.blocks.10.mlp.gate_proj",
+      "visual.blocks.10.mlp.up_proj",
+      "visual.blocks.10.mlp.down_proj",
+      "visual.blocks.11.attn.qkv",
+      "visual.blocks.11.attn.proj",
+      "visual.blocks.11.mlp.gate_proj",
+      "visual.blocks.11.mlp.up_proj",
+      "visual.blocks.11.mlp.down_proj",
+      "visual.blocks.12.attn.qkv",
+      "visual.blocks.12.attn.proj",
+      "visual.blocks.12.mlp.gate_proj",
+      "visual.blocks.12.mlp.up_proj",
+      "visual.blocks.12.mlp.down_proj",
+      "visual.blocks.13.attn.qkv",
+      "visual.blocks.13.attn.proj",
+      "visual.blocks.13.mlp.gate_proj",
+      "visual.blocks.13.mlp.up_proj",
+      "visual.blocks.13.mlp.down_proj",
+      "visual.blocks.14.attn.qkv",
+      "visual.blocks.14.attn.proj",
+      "visual.blocks.14.mlp.gate_proj",
+      "visual.blocks.14.mlp.up_proj",
+      "visual.blocks.14.mlp.down_proj",
+      "visual.blocks.15.attn.qkv",
+      "visual.blocks.15.attn.proj",
+      "visual.blocks.15.mlp.gate_proj",
+      "visual.blocks.15.mlp.up_proj",
+      "visual.blocks.15.mlp.down_proj",
+      "visual.blocks.16.attn.qkv",
+      "visual.blocks.16.attn.proj",
+      "visual.blocks.16.mlp.gate_proj",
+      "visual.blocks.16.mlp.up_proj",
+      "visual.blocks.16.mlp.down_proj",
+      "visual.blocks.17.attn.qkv",
+      "visual.blocks.17.attn.proj",
+      "visual.blocks.17.mlp.gate_proj",
+      "visual.blocks.17.mlp.up_proj",
+      "visual.blocks.17.mlp.down_proj",
+      "visual.blocks.18.attn.qkv",
+      "visual.blocks.18.attn.proj",
+      "visual.blocks.18.mlp.gate_proj",
+      "visual.blocks.18.mlp.up_proj",
+      "visual.blocks.18.mlp.down_proj",
+      "visual.blocks.19.attn.qkv",
+      "visual.blocks.19.attn.proj",
+      "visual.blocks.19.mlp.gate_proj",
+      "visual.blocks.19.mlp.up_proj",
+      "visual.blocks.19.mlp.down_proj",
+      "visual.blocks.20.attn.qkv",
+      "visual.blocks.20.attn.proj",
+      "visual.blocks.20.mlp.gate_proj",
+      "visual.blocks.20.mlp.up_proj",
+      "visual.blocks.20.mlp.down_proj",
+      "visual.blocks.21.attn.qkv",
+      "visual.blocks.21.attn.proj",
+      "visual.blocks.21.mlp.gate_proj",
+      "visual.blocks.21.mlp.up_proj",
+      "visual.blocks.21.mlp.down_proj",
+      "visual.blocks.22.attn.qkv",
+      "visual.blocks.22.attn.proj",
+      "visual.blocks.22.mlp.gate_proj",
+      "visual.blocks.22.mlp.up_proj",
+      "visual.blocks.22.mlp.down_proj",
+      "visual.blocks.23.attn.qkv",
+      "visual.blocks.23.attn.proj",
+      "visual.blocks.23.mlp.gate_proj",
+      "visual.blocks.23.mlp.up_proj",
+      "visual.blocks.23.mlp.down_proj",
+      "visual.blocks.24.attn.qkv",
+      "visual.blocks.24.attn.proj",
+      "visual.blocks.24.mlp.gate_proj",
+      "visual.blocks.24.mlp.up_proj",
+      "visual.blocks.24.mlp.down_proj",
+      "visual.blocks.25.attn.qkv",
+      "visual.blocks.25.attn.proj",
+      "visual.blocks.25.mlp.gate_proj",
+      "visual.blocks.25.mlp.up_proj",
+      "visual.blocks.25.mlp.down_proj",
+      "visual.blocks.26.attn.qkv",
+      "visual.blocks.26.attn.proj",
+      "visual.blocks.26.mlp.gate_proj",
+      "visual.blocks.26.mlp.up_proj",
+      "visual.blocks.26.mlp.down_proj",
+      "visual.blocks.27.attn.qkv",
+      "visual.blocks.27.attn.proj",
+      "visual.blocks.27.mlp.gate_proj",
+      "visual.blocks.27.mlp.up_proj",
+      "visual.blocks.27.mlp.down_proj",
+      "visual.blocks.28.attn.qkv",
+      "visual.blocks.28.attn.proj",
+      "visual.blocks.28.mlp.gate_proj",
+      "visual.blocks.28.mlp.up_proj",
+      "visual.blocks.28.mlp.down_proj",
+      "visual.blocks.29.attn.qkv",
+      "visual.blocks.29.attn.proj",
+      "visual.blocks.29.mlp.gate_proj",
+      "visual.blocks.29.mlp.up_proj",
+      "visual.blocks.29.mlp.down_proj",
+      "visual.blocks.30.attn.qkv",
+      "visual.blocks.30.attn.proj",
+      "visual.blocks.30.mlp.gate_proj",
+      "visual.blocks.30.mlp.up_proj",
+      "visual.blocks.30.mlp.down_proj",
+      "visual.blocks.31.attn.qkv",
+      "visual.blocks.31.attn.proj",
+      "visual.blocks.31.mlp.gate_proj",
+      "visual.blocks.31.mlp.up_proj",
+      "visual.blocks.31.mlp.down_proj",
+      "visual.merger.mlp.0",
+      "visual.merger.mlp.2",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  },
+  "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": "4.49.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "intermediate_size": 3456,
+    "model_type": "qwen2_5_vl",
+    "out_hidden_size": 8192,
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fdcf55d00ffa11e55fcc79ab5cca51d50a1d267219820ac66c36be0177fb23
+size 4929545176

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66dcd62e9496e9b8c456f6c95df848034fe648f4414ff1088a35f7a6efa44156
+size 4873985928

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f76e418f06f6b9b7f8a524f6405b1baee70ca7418a9a660f7537c490263ae35
+size 4782749304

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09782507221803a2287fcacb4ef166317fee2e62839ad43caa4c2f9ec461f77c
+size 4873986032

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1e3dfb60f12733be7aae9274996f14814cc4680a707e1a201a0b627b4373ea
+size 4782749368

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f8a745a63bdd2552d0aaa25728108ccd66718611bb8f1b1d1998a86e5054a1
+size 4873986032

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f452321174378d32090e7c94cffa3b43a4539e2f407f936b12a35639122005a
+size 4782749368

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87afe66c34acb2c5a7b118db74939afe8f47613f442eca4ed0f38a02e4e93fed
+size 4873986032

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a79addd10e3e66dcc4b53822ed86a7e31197ca3a54eaacc2a8140921d158f47
+size 4782749368

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83154d2dd5e7064947716c0930013e17943c378f80343c5f6067e8afdc291c1f
+size 4873986032

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48dd3dd98f76920c997a634e4f390f4ab11e629c7d76d752ef94844477bea183
+size 4782749368

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3168a6cbc214a1e83a04235e676fad12952ef36010442e02e007701ea23037e4
+size 4873986032

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d1b9f92f0154fc8f7cbfe0c6d7d3955b088cf2c520e1a41c2f157c07c5b6bf
+size 4782749368

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d25976bd3a6cb3055a1376a5a3ffec0f350d6a34a9749cbdd0495409e5e744
+size 4873986032

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17169ad645848ed1c32ef9d34529d80bbe052b3f5309d9f7973ed0fde30c09a
+size 4782749368

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3611e6a6ce31c332c9fcbaa2d5975ad981a6aa05470b66df74dab8811f7cb0a
+size 4096149840

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5VLImageProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

recipe.yaml

@@ -0,0 +1,6 @@
+DEFAULT_stage:
+  DEFAULT_modifiers:
+    QuantizationModifier:
+      ignore: ['re:.*lm_head', 're:visual.*']
+      targets: [Linear]
+      scheme: FP8_DYNAMIC

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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 <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|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<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\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<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\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": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}