Instructions to use bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="bottlecapai/ThinkingCap-Qwen3.8-Flash-Next")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("bottlecapai/ThinkingCap-Qwen3.8-Flash-Next")
model = AutoModelForMultimodalLM.from_pretrained("bottlecapai/ThinkingCap-Qwen3.8-Flash-Next", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next

SGLang

How to use bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with Docker Model Runner:
```
docker model run hf.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next
```

Adamiros commited on 20 days ago

Commit

d90c9fe

0 Parent(s):

ThinkingCap: Qwen3.8-Flash-Next

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

.gitattributes +39 -0
LICENSE +16 -0
README.md +183 -0
cap_header.png +3 -0
chat_template.jinja +170 -0
config.json +154 -0
generation_config.json +12 -0
merges.txt +0 -0
model-00001-of-00131.safetensors +3 -0
model-00002-of-00131.safetensors +3 -0
model-00003-of-00131.safetensors +3 -0
model-00004-of-00131.safetensors +3 -0
model-00005-of-00131.safetensors +3 -0
model-00006-of-00131.safetensors +3 -0
model-00007-of-00131.safetensors +3 -0
model-00008-of-00131.safetensors +3 -0
model-00009-of-00131.safetensors +3 -0
model-00010-of-00131.safetensors +3 -0
model-00011-of-00131.safetensors +3 -0
model-00012-of-00131.safetensors +3 -0
model-00013-of-00131.safetensors +3 -0
model-00014-of-00131.safetensors +3 -0
model-00015-of-00131.safetensors +3 -0
model-00016-of-00131.safetensors +3 -0
model-00017-of-00131.safetensors +3 -0
model-00018-of-00131.safetensors +3 -0
model-00019-of-00131.safetensors +3 -0
model-00020-of-00131.safetensors +3 -0
model-00021-of-00131.safetensors +3 -0
model-00022-of-00131.safetensors +3 -0
model-00023-of-00131.safetensors +3 -0
model-00024-of-00131.safetensors +3 -0
model-00025-of-00131.safetensors +3 -0
model-00026-of-00131.safetensors +3 -0
model-00027-of-00131.safetensors +3 -0
model-00028-of-00131.safetensors +3 -0
model-00029-of-00131.safetensors +3 -0
model-00030-of-00131.safetensors +3 -0
model-00031-of-00131.safetensors +3 -0
model-00032-of-00131.safetensors +3 -0
model-00033-of-00131.safetensors +3 -0
model-00034-of-00131.safetensors +3 -0
model-00035-of-00131.safetensors +3 -0
model-00036-of-00131.safetensors +3 -0
model-00037-of-00131.safetensors +3 -0
model-00038-of-00131.safetensors +3 -0
model-00039-of-00131.safetensors +3 -0
model-00040-of-00131.safetensors +3 -0
model-00041-of-00131.safetensors +3 -0
model-00042-of-00131.safetensors +3 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,39 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+cap_header.png filter=lfs diff=lfs merge=lfs -text
+thinkingcap_demo.mp4 filter=lfs diff=lfs merge=lfs -text
+thinkingcap_demo_4k.mp4 filter=lfs diff=lfs merge=lfs -text

LICENSE ADDED Viewed

	@@ -0,0 +1,16 @@

+Qwen Community License 1.0
+Copyright (c) 2026 Qwen
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software, including the model weights, parameters, configuration files, inference code and associated documentation files (collectively, the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, sell, deploy, host, fine-tune, and create derivative works from (collectively, "Use" or "Using") copies of the Software; and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+1. The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. If the Software (or any derivative works thereof) is Used for any of the licensee's commercial products or services that have more than 100,000,000 monthly active users or US$ 20,000,000 (or equivalent in other currencies) monthly revenue, respective model name must be prominently displayed on the user interface of such product or service; and,
+2. If the licensee or any of its affiliates conducts a Model as a Service or AI Work Assistant business, the licensee shall obtain a separate license from Qwen before Using the Software or its derivative works for any commercial purpose. The foregoing requirement shall not apply to the licensee's internal Use of the Software, provided that such Use does not make the Software, its outputs, or its underlying model capabilities available to any third party.
+"Model as a Service" means giving a third party access to language model inference or fine-tuning (e.g., via API or a hosted endpoint) in a manner that allows such third parties to exercise meaningful control over the inputs, parameters, or training data. This does not include the mere relaying of requests to models hosted by other third parties.
+“AI Work Assistant” means an independent AI-powered product primarily designed for AI-assisted coding or office productivity (e.g., Qoder and QwenWork). It does not include: (a) a single-purpose AI tool (such as an AI translation tool); (b) an AI assistant primarily designed for a domain other than coding or office productivity (such as Taobao AI Shopping Assistant or AMap AI Chat); or (c) an AI assistant that is a feature of a product whose primary purpose is not AI-assisted coding or office productivity.
+THE SOFTWARE AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL QWEN, ITS AFFILIATES OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. THE USE OF THE SOFTWARE MUST COMPLY WITH APPLICABLE LAWS AND REGULATIONS, AND MUST NOT INFRINGE THE INTELLECTUAL PROPERTY RIGHTS OF ANY THIRD PARTY.
+For any questions regarding this license, please contact model-business@notice.qwencloud.com.

README.md ADDED Viewed

	@@ -0,0 +1,183 @@

+---
+base_model: "Qwen/Qwen3.8-Flash-Next"
+base_model_relation: finetune
+library_name: transformers
+tags:
+  - qwen3_8_flash_next
+  - token-efficient
+  - efficient-thinking
+license: other
+license_name: qwen-community-license-1.0
+license_link: LICENSE
+---
+<a href="https://www.bottlecapai.com/"><img src="cap_header.png" alt="ThinkingCap — BottleCap AI" width="100%"></a>
+# ThinkingCap: Qwen3.8-Flash-Next
+ThinkingCap brings our shorter-thinking post-training to
+[Qwen3.8-Flash-Next (Qwen Team, 2026)](https://huggingface.co/Qwen/Qwen3.8-Flash-Next), a mixture-of-experts model
+with image input. ThinkingCap Qwen3.8-Flash-Next cuts reasoning tokens by
+**38.5% on average (22% to 51% depending on the benchmark)**
+at an average accuracy of **88.8% against the base model's 89.8%**. Check our [blogpost](https://bottlecapai.com/post/thinkingcap-qwen3-8-flash-next/) for more details.
+<p align="center"><video src="https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next/resolve/main/thinkingcap_demo.mp4" width="720" controls autoplay loop muted playsinline style="display:block;margin:0 auto;max-width:100%"></video></p>
+*The base model and ThinkingCap answering the same prompts side by side, with each answer's token count and time; playback is sped up. Also in [4K](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next/resolve/main/thinkingcap_demo_4k.mp4).*
+## Token efficiency and benchmark performance
+<table width="100%" style="border-collapse:collapse;width:100%;display:table;table-layout:auto;font-size:14px;line-height:1.4;">
+<thead>
+<tr><th rowspan="2" style="text-align:left;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);vertical-align:bottom;color:#6b748a;font-weight:600;">Benchmark</th><th colspan="2" style="text-align:center;padding:6px 12px 3px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);color:#7a67e6;font-weight:700;font-size:11px;letter-spacing:0.06em;text-transform:uppercase;">Accuracy</th><th colspan="3" style="text-align:center;padding:6px 12px 3px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);color:#7a67e6;font-weight:700;font-size:11px;letter-spacing:0.06em;text-transform:uppercase;">Thinking tokens</th></tr>
+<tr><th style="text-align:center;padding:3px 12px 8px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);color:#6b748a;font-weight:600;font-size:12px;">Base</th><th style="text-align:center;padding:3px 12px 8px;border-bottom:1px solid rgba(128,128,128,0.22);color:#6b748a;font-weight:600;font-size:12px;">Ours</th><th style="text-align:center;padding:3px 12px 8px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);color:#6b748a;font-weight:600;font-size:12px;">Base<br><span style="font-weight:400;font-size:10px;">mean</span></th><th style="text-align:center;padding:3px 12px 8px;border-bottom:1px solid rgba(128,128,128,0.22);color:#6b748a;font-weight:600;font-size:12px;">Ours<br><span style="font-weight:400;font-size:10px;">mean</span></th><th style="text-align:center;padding:3px 12px 8px;border-bottom:1px solid rgba(128,128,128,0.22);color:#6b748a;font-weight:600;font-size:12px;">Reduction</th></tr>
+</thead>
+<tbody>
+<tr><td colspan="6" style="text-align:left;padding:7px 12px;background:rgba(199,185,255,0.16);color:#7a67e6;font-weight:700;font-size:11px;letter-spacing:0.06em;text-transform:uppercase;border-bottom:1px solid rgba(128,128,128,0.22);">Math &amp; code</td></tr>
+<tr><td style="text-align:left;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:13px;white-space:nowrap;">AIME 2026</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">97.92<span style="color:#6b748a;font-size:11px;"> &plusmn;0.85</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">97.19<span style="color:#6b748a;font-size:11px;"> &plusmn;1.15</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">16,694</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">9,281</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);color:#0a9d68;font-weight:700;font-variant-numeric:tabular-nums;white-space:nowrap;">&darr; 44.4%</td></tr>
+<tr><td style="text-align:left;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:13px;white-space:nowrap;">HMMT (Nov 2025)</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">99.17<span style="color:#6b748a;font-size:11px;"> &plusmn;1.03</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">97.71<span style="color:#6b748a;font-size:11px;"> &plusmn;1.55</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">15,975</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">8,874</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);color:#0a9d68;font-weight:700;font-variant-numeric:tabular-nums;white-space:nowrap;">&darr; 44.5%</td></tr>
+<tr><td style="text-align:left;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:13px;white-space:nowrap;">LiveCodeBench v6</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">91.86<span style="color:#6b748a;font-size:11px;"> &plusmn;2.72</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">90.86<span style="color:#6b748a;font-size:11px;"> &plusmn;1.05</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">28,653</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">16,945</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);color:#0a9d68;font-weight:700;font-variant-numeric:tabular-nums;white-space:nowrap;">&darr; 40.9%</td></tr>
+<tr><td colspan="6" style="text-align:left;padding:7px 12px;background:rgba(199,185,255,0.16);color:#7a67e6;font-weight:700;font-size:11px;letter-spacing:0.06em;text-transform:uppercase;border-bottom:1px solid rgba(128,128,128,0.22);">Long-context &amp; multimodal</td></tr>
+<tr><td style="text-align:left;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:13px;white-space:nowrap;">AA-LCR</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">80.62<span style="color:#6b748a;font-size:11px;"> &plusmn;1.54</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">78.75<span style="color:#6b748a;font-size:11px;"> &plusmn;2.60</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">1,510</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">1,088</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);color:#0a9d68;font-weight:700;font-variant-numeric:tabular-nums;white-space:nowrap;">&darr; 28.0%</td></tr>
+<tr><td style="text-align:left;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:13px;white-space:nowrap;">RealWorldQA</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">85.62<span style="color:#6b748a;font-size:11px;"> &plusmn;0.50</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">84.67<span style="color:#6b748a;font-size:11px;"> &plusmn;0.43</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">1,102</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">540</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);color:#0a9d68;font-weight:700;font-variant-numeric:tabular-nums;white-space:nowrap;">&darr; 51.0%</td></tr>
+<tr><td colspan="6" style="text-align:left;padding:7px 12px;background:rgba(199,185,255,0.16);color:#7a67e6;font-weight:700;font-size:11px;letter-spacing:0.06em;text-transform:uppercase;border-bottom:1px solid rgba(128,128,128,0.22);">Agentic</td></tr>
+<tr><td style="text-align:left;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:13px;white-space:nowrap;">&tau;&sup2;-bench</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">83.57<span style="color:#6b748a;font-size:11px;"> &plusmn;1.33</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">83.39<span style="color:#6b748a;font-size:11px;"> &plusmn;1.86</span></td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">2,111</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">1,637</td><td style="text-align:center;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);color:#0a9d68;font-weight:700;font-variant-numeric:tabular-nums;white-space:nowrap;">&darr; 22.5%</td></tr>
+<tr><td style="text-align:left;padding:9px 12px;border-top:2px solid rgba(128,128,128,0.22);background:rgba(199,185,255,0.10);font-weight:750;">Macro average</td><td style="text-align:center;padding:9px 12px;border-top:2px solid rgba(128,128,128,0.22);background:rgba(199,185,255,0.10);font-weight:750;border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">89.8</td><td style="text-align:center;padding:9px 12px;border-top:2px solid rgba(128,128,128,0.22);background:rgba(199,185,255,0.10);font-weight:750;font-variant-numeric:tabular-nums;white-space:nowrap;">88.8</td><td style="text-align:center;padding:9px 12px;border-top:2px solid rgba(128,128,128,0.22);background:rgba(199,185,255,0.10);font-weight:750;border-left:1px solid rgba(128,128,128,0.22);font-variant-numeric:tabular-nums;white-space:nowrap;">11,007</td><td style="text-align:center;padding:9px 12px;border-top:2px solid rgba(128,128,128,0.22);background:rgba(199,185,255,0.10);font-weight:750;font-variant-numeric:tabular-nums;white-space:nowrap;">6,394</td><td style="text-align:center;padding:9px 12px;border-top:2px solid rgba(128,128,128,0.22);background:rgba(199,185,255,0.10);font-weight:750;color:#0a9d68;font-variant-numeric:tabular-nums;white-space:nowrap;">&darr; 38.5%</td></tr>
+</tbody>
+</table>
+<details style="background:rgba(128,128,128,0.06);border:1px solid rgba(128,128,128,0.22);border-radius:8px;padding:6px 16px;margin:8px 0 24px;">
+<summary style="cursor:pointer;padding:6px 0;"><strong>Evaluation details</strong></summary>
+#### Models
+Base `Qwen/Qwen3.8-Flash-Next` against `bottlecapai/ThinkingCap-Qwen3.8-Flash-Next`, shown as `Ours`.
+#### Metrics
+- **Accuracy** (Base / Ours) — fraction of correct answers. The &tau;&sup2;-bench score is an unweighted mean over its three domains (airline, retail, telecom), not pooled over tasks.
+- **Thinking tokens** (Base / Ours) — mean length of the `<think>` trace, answer excluded. &tau;&sup2;-bench is a multi-turn agentic episode, so for that row the count is the reasoning summed over every turn of the episode (about 15 turns on average), not a single trace.
+- **(Thinking token) Reduction** — the relative change between the two mean columns beside it, `(Ours − Base) / Base`, where each mean is taken over every question and seed of the benchmark. A saving is shown as a green &darr; percentage.
+- **Macro average** (bottom row) — equal-weight mean across benchmarks of each column, including the reduction: it is the mean of the per-benchmark reductions, not the ratio of the two token figures beside it.
+We separately track **truncation**: on the single-turn benchmarks, the `<think>` trace never closes because the model hits the generation cap or stops while still reasoning, so no answer is produced; &tau;&sup2;-bench marks an episode if any of its turns hits the per-turn cap. Equal-weight across benchmarks it is **0.05% &rarr; 0.00%**.
+#### Serving
+Hardware: 4× NVIDIA H200, tensor parallel 4. vLLM 0.31.0, without speculative decoding.
+Thinking is on at `reasoning_effort=xhigh`, the chat template's own default, with the base model's
+recommended sampling &mdash; `temperature=1.0, top_p=0.95, top_k=20, min_p=0.0` &mdash; used
+unchanged for `Ours`.
+The generation cap is 253,952 tokens for most benchmarks. AA-LCR uses 131,072 and
+&tau;&sup2;-bench 65,536 per turn, because their documents and multi-turn transcripts occupy the
+rest of the window.
+#### Benchmarks
+Six benchmarks, each on its **complete** set: AIME 2026 (30 problems), HMMT Nov 2025 (30),
+LiveCodeBench v6 (175), AA-LCR (100), RealWorldQA (765) and &tau;&sup2;-bench (278 tasks across
+airline, retail and telecom).
+#### Seeds and intervals
+Independent runs per benchmark: 32 seeds on AIME 2026; 16 seeds on HMMT (Nov 2025); 8 seeds on AA-LCR, RealWorldQA and &tau;&sup2;-bench; 4 seeds on LiveCodeBench v6. Accuracy cells show the **95% t-interval across seeds** — how much the answer moves when only the sampling seed changes, at Qwen's recommended temperature of 1.0.
+</details>
+## Usage
+The bf16 weights take about 360 GB; we serve them on four H200s (141 GB each).
+### HuggingFace Transformers
+Requires transformers 5.16 or newer, the first release with this architecture.
+```python
+from transformers import AutoModelForImageTextToText, AutoProcessor
+model = AutoModelForImageTextToText.from_pretrained("bottlecapai/ThinkingCap-Qwen3.8-Flash-Next", dtype="bfloat16", device_map="auto")
+proc = AutoProcessor.from_pretrained("bottlecapai/ThinkingCap-Qwen3.8-Flash-Next")
+```
+Check https://huggingface.co/Qwen/Qwen3.8-Flash-Next for recommended usage, sampling params etc.
+### vLLM
+Requires vLLM 0.31.0 or newer. The reasoning parser returns the thinking in a separate `reasoning` field instead of inline in `content` before `</think>`, and the tool-call parser turns the model's XML tool calls into structured `tool_calls` — the same flags the base model's serving recipes use.
+```bash
+vllm serve bottlecapai/ThinkingCap-Qwen3.8-Flash-Next --tensor-parallel-size 4 --max-model-len 262144 \
+  --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_xml
+```
+On H200 nodes without NVSwitch, our tensor-parallel servers crashed with `illegal memory access` when split across NVLink islands with vLLM's default FlashInfer all-reduce. We serve on one island with `VLLM_ALLREDUCE_USE_FLASHINFER=0`.
+#### Speculative decoding
+The checkpoint keeps the base model's MTP head. With 3 draft tokens and probabilistic drafting, vLLM 0.31.0 on four H200s accepted on average **2.77 tokens per decoding step** with this model (the base model: 2.72), over AIME 2026 and RealWorldQA. vLLM issue [#55357](https://github.com/vllm-project/vllm/issues/55357), MTP draft acceptance dropping to zero with repetition inside the thinking on this architecture, is still open; it did not reproduce in our test.
+```bash
+vllm serve bottlecapai/ThinkingCap-Qwen3.8-Flash-Next --tensor-parallel-size 4 --max-model-len 262144 \
+  --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_xml \
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3,"draft_sample_method":"probabilistic"}'
+```
+#### Querying the server
+The server speaks the OpenAI Chat Completions API. One request covers text, images and the thinking-effort knob:
+```python
+from openai import OpenAI
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="-")
+r = client.chat.completions.create(
+    model="bottlecapai/ThinkingCap-Qwen3.8-Flash-Next",
+    messages=[{"role": "user", "content": [
+        {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
+        {"type": "text", "text": "What is happening in this picture?"},
+    ]}],
+    temperature=1.0, top_p=0.95,
+    extra_body={"top_k": 20,
+                "chat_template_kwargs": {"reasoning_effort": "xhigh"}},   # xhigh (default) | medium | low
+)
+print(r.choices[0].message.reasoning)               # the thinking
+print(r.choices[0].message.content)                 # the answer
+```
+A text-only request is the same call with a plain string as `content`.
+### Quantized versions
+Same checkpoint, chat template and license, quantized for smaller footprints:
+- **FP8** &mdash; [bottlecapai/ThinkingCap-Qwen3.8-Flash-Next-FP8](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next-FP8) &mdash; vLLM; Qwen's own FP8 layout (FP8 routed experts and n-gram table), ≈186 GB
+- **NVFP4 (W4A16)** &mdash; [bottlecapai/ThinkingCap-Qwen3.8-Flash-Next-NVFP4](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next-NVFP4) &mdash; vLLM; 4-bit weight-only routed experts, ≈132 GB
+- **GGUF** &mdash; [bottlecapai/ThinkingCap-Qwen3.8-Flash-Next-GGUF](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next-GGUF) &mdash; llama.cpp; BF16, Q8_0, Q6_K, Q4_K_M and IQ4_XS, with the vision projector
+## Where to find us
+<table style="border-collapse:collapse;border:0;margin:0"><tbody><tr>
+<td style="border:0;padding:0 18px 0 0"><a href="https://www.bottlecapai.com/"><img src="social-web.png" alt="Website" width="34" height="34"></a></td>
+<td style="border:0;padding:0 18px 0 0"><a href="https://www.linkedin.com/company/bottlecap-ai/"><img src="social-linkedin.png" alt="LinkedIn" width="34" height="34"></a></td>
+<td style="border:0;padding:0 18px 0 0"><a href="https://www.instagram.com/bottlecapai/"><img src="social-instagram.png" alt="Instagram" width="34" height="34"></a></td>
+<td style="border:0;padding:0"><a href="https://x.com/BottleCapAI"><img src="social-x.png" alt="X" width="34" height="34"></a></td>
+</tr></tbody></table>
+Need even more efficiency? Our enterprise versions go further — fewer thinking tokens still, tuned to your workload, at matched accuracy on your own tasks. Built for AI labs, inference providers and enterprises running models at scale. Deployed on your infrastructure, or in the cloud and region you choose.
+[Talk to our team](mailto:enterprise@bottlecapai.com)
+## License
+Released under the base model's own license, the Qwen Community License 1.0 (full text in [LICENSE](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next/blob/main/LICENSE)). Its conditions carry over to this model, including the separate license from Qwen that Model-as-a-Service and AI work-assistant businesses need for commercial use.
+## Citation
+If you use this model, please cite:
+```bibtex
+@misc{ThinkingCap-Qwen3.8-Flash-Next,
+  title     = {bottlecapai/ThinkingCap-Qwen3.8-Flash-Next},
+  author    = {Osusky, Adam and Lindauer, Jan and Jirkovsky, Adam and Mihal, Filip and Platek, Ondrej and Herel, David and Ihnatchenko, Luka and Bartek, Vojtech and Jirak, Jiri and Kubista, Daniel and Krus, Frantisek and Mikolov, Tomas},
+  year      = {2026},
+}
+```

cap_header.png ADDED Viewed

Git LFS Details

SHA256: 5d97257111543b14dc9fd1c82da9266015fe1b383a8b990695d2d01fb2bd8c35
Pointer size: 132 Bytes
Size of remote file: 2.01 MB

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,170 @@

+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + content + '<|im_end|>\n' }}
+        {%- elif reasoning_instructions %}
+            {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+        {%- endif %}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json ADDED Viewed

	@@ -0,0 +1,154 @@

+{
+    "architectures": [
+        "Qwen4ExpForConditionalGeneration"
+    ],
+    "image_token_id": 248056,
+    "language_model_only": false,
+    "model_type": "qwen4_exp",
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "bos_token_id": 248044,
+        "dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "hc_count": 4,
+        "hc_lowrank": 320,
+        "head_dim": 256,
+        "heads_per_ngram": 8,
+        "hidden_act": "silu",
+        "hidden_size": 2560,
+        "indexer_budget": 2048,
+        "indexer_compress_ratio": 4,
+        "indexer_head_dim": 128,
+        "indexer_kv_heads": 1,
+        "indexer_n_heads": 4,
+        "initializer_range": 0.02,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 48,
+        "linear_value_head_dim": 128,
+        "make_ngram_vocab_size_divisible_by": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "model_type": "qwen4_exp_text",
+        "moe_intermediate_size": 640,
+        "mtp": {
+            "hybrid": true,
+            "layer_types": [
+                "full_attention"
+            ],
+            "mtp_use_hidden_state_from_layer": null,
+            "num_hidden_layers": 1,
+            "rope_theta": 10000000
+        },
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "ngram_size": 3,
+        "ngram_vocab_size_base": 20000000,
+        "num_attention_heads": 24,
+        "num_experts": 512,
+        "num_experts_per_tok": 10,
+        "num_hidden_layers": 48,
+        "num_key_value_heads": 2,
+        "output_gate_type": "sigmoid",
+        "output_router_logits": false,
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "ple_conv_kernel_size": 4,
+        "ple_embed_dim": 2560,
+        "ple_layer_ids": [
+            2
+        ],
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "rope_type": "default"
+        },
+        "router_aux_loss_coef": 0.001,
+        "shared_expert_intermediate_size": 640,
+        "split_ngram_parts": 128,
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "5.8.0.dev0",
+    "video_token_id": 248057,
+    "vision_config": {
+        "deepstack_visual_indexes": [],
+        "depth": 27,
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4304,
+        "model_type": "qwen4_exp",
+        "num_heads": 16,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 2560,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model-00001-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a771b0f926f5f92a7abc9357bbc9cd7e441c15104f0781da45ddb6caeb9b135e
+size 1040155944

model-00002-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1da92de7cf72dcca86faf05007925389ceb24427609e8d3b478d53d97fd97a63
+size 3355443368

model-00003-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91581e6a127b2cebe17ff51e77e4ed72069ee3b7c14795672809f9f4703f289d
+size 1832518264

model-00004-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:18b75622772985f1d4e3d12427511043eb61a491c9c89c1c97ea340b735c3c86
+size 3355443368

model-00005-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d51493c944d0e6dc7087f54f67b13179d445b9891b7345ba3e28b9410c2c3cf9
+size 3355888504

model-00006-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8277a48e1fd7ab7ff7f0282befcc6eb4e09ab2e0780c00af6685e198faba233e
+size 3200016032

model-00007-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0fba369354e45b43efbe2773d63b7cb20caedb56ff9ed80e076bbcdaf560666a
+size 3200016032

model-00008-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:024f59b6f2cb27ab79a4267cff9603c398ef1a7ef9ba76009fd34a0a84a9455e
+size 3200016032

model-00009-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:23fbef154f7f68e5b6f555492832c78822a827554757797daf91de48df06b496
+size 3200016032

model-00010-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a303529a190c6661870d5abebf0ac18d36922a1da8db737d19f55bd1031fe8
+size 3200016032

model-00011-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1215943b48481febb33a1129c96613dec5f364613a2cc3ba1e27c23be0ca78a
+size 3200016032

model-00012-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f63d649ea84867ec75884dace5ea4d8c723a6560463674a6ee0ce621b4b9dbc1
+size 3200016032

model-00013-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0f0fb335f4c19a0158f60294e5b5c30bdfc344b003633c9c42e5e638a6808e
+size 3200016032

model-00014-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee73bd21c73b2610d2a30924f7acd24e63b1ca29e0a1f1c87f0f6a9648e347a
+size 3200016032

model-00015-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b35421bf21724db705a38ee9f779de07f9f1711be964049942960c5e3dddb1c2
+size 3200016032

model-00016-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:73c4b1bd1f3752d70f0161ec8c8a7701f0538e1ae722daf16a905e04a666e69f
+size 3200016032

model-00017-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ee60c1269974cc797bad8bfc9a0fac72437b323ceafcb225cef6980ecffce1b3
+size 3200016032

model-00018-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:72cf3696aa1af4611b2da2b013868f3724082362899d9dce3e9fec908d441fc2
+size 3200016032

model-00019-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bdad649be407bd8033a4abd6a24bf434ed6a173807892d18cc1c9771031bfd0c
+size 3200016032

model-00020-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2258dad55787922f1d4429aea528495511f58447baa9b4f1b7f92f58ba7110b0
+size 3200016032

model-00021-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:775952ac572fa4ff7e5e316ecb60483d4dd96f4369d6a7a403fa31d7f9d1a6d0
+size 3200016032

model-00022-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d205070bb898c59d23bc379652607911f39e219627028a29d82e8e8fecab7c0
+size 3200016032

model-00023-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:598d4f772853233b88911fdb1a49f8865e3c732e93b17aea44b65f455e69e9dc
+size 3200016032

model-00024-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:09e534942e7d4eb31803b347e14dd70090f16f85c89b0ad766bdace135806f12
+size 3200016032

model-00025-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:482d18f0e515c23c6933593d0cce289770600c6fa539168bd304e2169cc8a2be
+size 3200016032

model-00026-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ac479fe29ed3e03b7c3523974371d68dace22b7744ff9236f9429cdbb9241da0
+size 3200016032

model-00027-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4981d4e636723dbb063f04854e4362c1fe341d9ba80b5bb4231bb0d5ee8ab266
+size 3200016032

model-00028-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b45a957b1f3572d325b0795f549fb772c160bd5c5167f94a347b96e3c7b978d
+size 3200016032

model-00029-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:40d2f2291ff4800373087cd00f1f95c3bd69331c32f39cfdd5d43516764b03ec
+size 3200016032

model-00030-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:893a9b59e412a3242252274770efe0794ce8b216b2b3907b6854b7eaa6ddd334
+size 3200016032

model-00031-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6bf01d60f21bed295b9b1d43501593b4ce7ece28aaf75618b4fb58039c0d04
+size 3200016040

model-00032-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7453fcb5872160888730439ac71a5279d348686d68c6ba2d62ff12461443dc69
+size 3200016040

model-00033-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2f577ce40932031c4749f9177dab2119ff118f9f9b9df3d0d5e57c8e41d128
+size 3200016040

model-00034-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:35b5522668652e8cc7d8eacb0d45c59eb9ed9786e9102a9b71503f746f50da64
+size 3200016040

model-00035-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe611218d36ff7c06e4c24f7252215fdddc879ac3de2b1d569727ed31f82db1
+size 3200016040

model-00036-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:237789c0cef556ef22c9f1ca99b7baf71b33a56b70c5828380e1008e02510649
+size 3200016040

model-00037-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:40f57c4f8406c078248ee14dd5251dafb92f0aefcd91a5b2eca4a6d4c8ea48a0
+size 1742347160

model-00038-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:063965d1d57b1d87e3d45e65f0b0aa5a7100ca3daa157d02cb6d93cacfe106fe
+size 3355443376

model-00039-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2627aeca6620065ba1e4b137af7e030dbdfdcacd105c93b536c2e67aad23cfa7
+size 1716599840

model-00040-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed06bdece1c74ba1a87208ecc19dad59efafddc6d673a3d1ef6d25d3caf02453
+size 3355443376

model-00041-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e28ba5d9152051dc33e65ddf5c801692edc3f4447a879a1dd43669e572c2c65
+size 1941966288

model-00042-of-00131.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:071bb12fa66a5f393d9aaacba701ce8672567e17ee0249e4c256d881c6d7ee1d
+size 3355443376