Image-Text-to-Text
Transformers
Safetensors
qwen3_5_moe
qwen
qwen3
qwen3.5
Mixture of Experts
abliterated
uncensored
sft
opus
qwopus
multimodal
vision
mtp
conversational
4-bit precision
Instructions to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit") 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)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit") model = AutoModelForMultimodalLM.from_pretrained("OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit") 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=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit", "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/OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit
- SGLang
How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit 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 "OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit" \ --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": "OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit", "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 "OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit" \ --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": "OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit", "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 OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit with Docker Model Runner:
docker model run hf.co/OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-MLX-4bit
| { | |
| "architectures": [ | |
| "Qwen3_5MoeForConditionalGeneration" | |
| ], | |
| "eos_token_id": [ | |
| 248046, | |
| 248044 | |
| ], | |
| "image_token_id": 248056, | |
| "model_type": "qwen3_5_moe", | |
| "quantization": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine", | |
| "language_model.model.layers.0.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.0.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.1.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.1.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.2.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.2.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.3.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.3.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.4.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.4.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.5.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.5.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.6.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.6.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.7.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.7.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.8.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.8.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.9.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.9.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.10.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.10.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.11.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.11.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.12.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.12.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.13.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.13.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.14.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.14.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.15.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.15.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.16.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.16.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.17.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.17.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.18.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.18.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.19.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.19.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.20.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.20.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.21.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.21.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.22.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.22.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.23.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.23.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.24.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.24.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.25.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.25.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.26.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.26.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.27.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.27.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.28.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.28.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.29.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.29.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.30.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.30.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.31.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.31.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.32.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.32.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.33.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.33.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.34.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.34.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.35.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.35.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.36.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.36.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.37.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.37.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.38.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.38.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.39.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.39.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.40.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.40.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.41.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.41.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.42.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.42.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.43.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.43.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.44.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.44.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.45.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.45.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.46.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.46.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.47.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.47.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine", | |
| "language_model.model.layers.0.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.0.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.1.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.1.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.2.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.2.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.3.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.3.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.4.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.4.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.5.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.5.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.6.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.6.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.7.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.7.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.8.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.8.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.9.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.9.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.10.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.10.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.11.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.11.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.12.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.12.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.13.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.13.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.14.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.14.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.15.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.15.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.16.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.16.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.17.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.17.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.18.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.18.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.19.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.19.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.20.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.20.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.21.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.21.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.22.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.22.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.23.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.23.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.24.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.24.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.25.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.25.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.26.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.26.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.27.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.27.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.28.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.28.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.29.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.29.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.30.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.30.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.31.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.31.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.32.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.32.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.33.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.33.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.34.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.34.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.35.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.35.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.36.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.36.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.37.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.37.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.38.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.38.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.39.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.39.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.40.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.40.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.41.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.41.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.42.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.42.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.43.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.43.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.44.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.44.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.45.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.45.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.46.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.46.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.47.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.47.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "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": 64, | |
| "linear_value_head_dim": 128, | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_moe_text", | |
| "moe_intermediate_size": 1024, | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 32, | |
| "num_experts": 256, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "router_aux_loss_coef": 0.001, | |
| "shared_expert_intermediate_size": 1024, | |
| "use_cache": true, | |
| "vocab_size": 248320, | |
| "mamba_ssm_dtype": "float32", | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "rope_theta": 10000000, | |
| "partial_rotary_factor": 0.25, | |
| "type": "default" | |
| } | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.0.dev0", | |
| "video_token_id": 248057, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053 | |
| } |