Image-Text-to-Text
Transformers
Safetensors
inkling_mm_model
conversational
audio-text-to-text
Mixture of Experts
Eval Results
8-bit precision
compressed-tensors
Instructions to use INCModel2/Inkling-Small-MXFP4-CT-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use INCModel2/Inkling-Small-MXFP4-CT-AutoRound with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="INCModel2/Inkling-Small-MXFP4-CT-AutoRound") 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("INCModel2/Inkling-Small-MXFP4-CT-AutoRound") model = AutoModelForMultimodalLM.from_pretrained("INCModel2/Inkling-Small-MXFP4-CT-AutoRound", 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=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use INCModel2/Inkling-Small-MXFP4-CT-AutoRound with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "INCModel2/Inkling-Small-MXFP4-CT-AutoRound" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "INCModel2/Inkling-Small-MXFP4-CT-AutoRound", "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/INCModel2/Inkling-Small-MXFP4-CT-AutoRound
- SGLang
How to use INCModel2/Inkling-Small-MXFP4-CT-AutoRound 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 "INCModel2/Inkling-Small-MXFP4-CT-AutoRound" \ --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": "INCModel2/Inkling-Small-MXFP4-CT-AutoRound", "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 "INCModel2/Inkling-Small-MXFP4-CT-AutoRound" \ --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": "INCModel2/Inkling-Small-MXFP4-CT-AutoRound", "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 INCModel2/Inkling-Small-MXFP4-CT-AutoRound with Docker Model Runner:
docker model run hf.co/INCModel2/Inkling-Small-MXFP4-CT-AutoRound
| { | |
| "config_groups": { | |
| "group_0": { | |
| "targets": [ | |
| "model.llm.layers.2.mlp.experts.w2_weight", | |
| "model.llm.layers.11.mlp.experts.w2_weight", | |
| "model.llm.layers.19.mlp.experts.w13_weight", | |
| "model.llm.layers.21.mlp.experts.w2_weight", | |
| "model.llm.layers.23.mlp.experts.w2_weight", | |
| "model.llm.layers.29.mlp.experts.w13_weight", | |
| "model.llm.layers.3.mlp.experts.w2_weight", | |
| "model.llm.layers.31.mlp.experts.w2_weight", | |
| "model.llm.layers.32.mlp.experts.w2_weight", | |
| "model.llm.layers.36.mlp.experts.w13_weight", | |
| "model.llm.layers.11.mlp.experts.w13_weight", | |
| "model.llm.layers.16.mlp.experts.w2_weight", | |
| "model.llm.layers.17.mlp.experts.w2_weight", | |
| "model.llm.layers.20.mlp.experts.w13_weight", | |
| "model.llm.layers.22.mlp.experts.w2_weight", | |
| "model.llm.layers.27.mlp.experts.w2_weight", | |
| "model.llm.layers.28.mlp.experts.w2_weight", | |
| "model.llm.layers.40.mlp.experts.w13_weight", | |
| "model.llm.layers.7.mlp.experts.w13_weight", | |
| "model.llm.layers.8.mlp.experts.w13_weight", | |
| "model.llm.layers.13.mlp.experts.w13_weight", | |
| "model.llm.layers.14.mlp.experts.w2_weight", | |
| "model.llm.layers.28.mlp.experts.w13_weight", | |
| "model.llm.layers.31.mlp.experts.w13_weight", | |
| "model.llm.layers.41.mlp.experts.w2_weight", | |
| "model.llm.layers.9.mlp.experts.w2_weight", | |
| "model.llm.layers.15.mlp.experts.w2_weight", | |
| "model.llm.layers.17.mlp.experts.w13_weight", | |
| "model.llm.layers.19.mlp.experts.w2_weight", | |
| "model.llm.layers.20.mlp.experts.w2_weight", | |
| "model.llm.layers.27.mlp.experts.w13_weight", | |
| "model.llm.layers.30.mlp.experts.w13_weight", | |
| "model.llm.layers.35.mlp.experts.w13_weight", | |
| "model.llm.layers.39.mlp.experts.w13_weight", | |
| "model.llm.layers.9.mlp.experts.w13_weight", | |
| "model.llm.layers.16.mlp.experts.w13_weight", | |
| "model.llm.layers.29.mlp.experts.w2_weight", | |
| "model.llm.layers.32.mlp.experts.w13_weight", | |
| "model.llm.layers.33.mlp.experts.w13_weight", | |
| "model.llm.layers.36.mlp.experts.w2_weight", | |
| "model.llm.layers.37.mlp.experts.w13_weight", | |
| "model.llm.layers.6.mlp.experts.w13_weight", | |
| "model.llm.layers.6.mlp.experts.w2_weight", | |
| "model.llm.layers.2.mlp.experts.w13_weight", | |
| "model.llm.layers.12.mlp.experts.w2_weight", | |
| "model.llm.layers.13.mlp.experts.w2_weight", | |
| "model.llm.layers.18.mlp.experts.w2_weight", | |
| "model.llm.layers.22.mlp.experts.w13_weight", | |
| "model.llm.layers.25.mlp.experts.w13_weight", | |
| "model.llm.layers.26.mlp.experts.w2_weight", | |
| "model.llm.layers.10.mlp.experts.w13_weight", | |
| "model.llm.layers.10.mlp.experts.w2_weight", | |
| "model.llm.layers.14.mlp.experts.w13_weight", | |
| "model.llm.layers.15.mlp.experts.w13_weight", | |
| "model.llm.layers.3.mlp.experts.w13_weight", | |
| "model.llm.layers.30.mlp.experts.w2_weight", | |
| "model.llm.layers.38.mlp.experts.w13_weight", | |
| "model.llm.layers.39.mlp.experts.w2_weight", | |
| "model.llm.layers.5.mlp.experts.w2_weight", | |
| "model.llm.layers.7.mlp.experts.w2_weight", | |
| "model.llm.layers.23.mlp.experts.w13_weight", | |
| "model.llm.layers.24.mlp.experts.w13_weight", | |
| "model.llm.layers.24.mlp.experts.w2_weight", | |
| "model.llm.layers.26.mlp.experts.w13_weight", | |
| "model.llm.layers.34.mlp.experts.w2_weight", | |
| "model.llm.layers.38.mlp.experts.w2_weight", | |
| "model.llm.layers.4.mlp.experts.w13_weight", | |
| "model.llm.layers.4.mlp.experts.w2_weight", | |
| "model.llm.layers.41.mlp.experts.w13_weight", | |
| "model.llm.layers.5.mlp.experts.w13_weight", | |
| "model.llm.layers.12.mlp.experts.w13_weight", | |
| "model.llm.layers.18.mlp.experts.w13_weight", | |
| "model.llm.layers.21.mlp.experts.w13_weight", | |
| "model.llm.layers.25.mlp.experts.w2_weight", | |
| "model.llm.layers.33.mlp.experts.w2_weight", | |
| "model.llm.layers.34.mlp.experts.w13_weight", | |
| "model.llm.layers.35.mlp.experts.w2_weight", | |
| "model.llm.layers.37.mlp.experts.w2_weight", | |
| "model.llm.layers.40.mlp.experts.w2_weight", | |
| "model.llm.layers.8.mlp.experts.w2_weight", | |
| "RoutedExperts" | |
| ], | |
| "weights": { | |
| "num_bits": 4, | |
| "type": "float", | |
| "symmetric": true, | |
| "group_size": 32, | |
| "strategy": "group", | |
| "block_structure": null, | |
| "dynamic": false, | |
| "actorder": null, | |
| "scale_dtype": "torch.uint8", | |
| "zp_dtype": null, | |
| "observer": "memoryless_minmax", | |
| "observer_kwargs": {} | |
| }, | |
| "input_activations": { | |
| "num_bits": 4, | |
| "type": "float", | |
| "symmetric": true, | |
| "group_size": 32, | |
| "strategy": "group", | |
| "block_structure": null, | |
| "dynamic": true, | |
| "actorder": null, | |
| "scale_dtype": "torch.uint8", | |
| "zp_dtype": null, | |
| "observer": null, | |
| "observer_kwargs": {} | |
| }, | |
| "output_activations": null, | |
| "format": null | |
| } | |
| }, | |
| "quant_method": "compressed-tensors", | |
| "kv_cache_scheme": null, | |
| "format": "mxfp4-pack-quantized", | |
| "quantization_status": "compressed", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "model.mtp.layers.0.input_proj", | |
| "model.mtp.layers.0.transformer_block.attn.k_sconv", | |
| "model.mtp.layers.0.transformer_block.attn.v_sconv", | |
| "model.mtp.layers.0.transformer_block.attn.wk_dv", | |
| "model.mtp.layers.0.transformer_block.attn.wo_ud", | |
| "model.mtp.layers.0.transformer_block.attn.wq_du", | |
| "model.mtp.layers.0.transformer_block.attn.wr_du", | |
| "model.mtp.layers.0.transformer_block.attn.wv_dv", | |
| "model.mtp.layers.0.transformer_block.attn_sconv", | |
| "model.mtp.layers.0.transformer_block.mlp.w13_dn", | |
| "model.mtp.layers.0.transformer_block.mlp.w2_md", | |
| "model.mtp.layers.0.transformer_block.mlp_sconv", | |
| "model.mtp.layers.1.input_proj", | |
| "model.mtp.layers.1.transformer_block.attn.k_sconv", | |
| "model.mtp.layers.1.transformer_block.attn.v_sconv", | |
| "model.mtp.layers.1.transformer_block.attn.wk_dv", | |
| "model.mtp.layers.1.transformer_block.attn.wo_ud", | |
| "model.mtp.layers.1.transformer_block.attn.wq_du", | |
| "model.mtp.layers.1.transformer_block.attn.wr_du", | |
| "model.mtp.layers.1.transformer_block.attn.wv_dv", | |
| "model.mtp.layers.1.transformer_block.attn_sconv", | |
| "model.mtp.layers.1.transformer_block.mlp.w13_dn", | |
| "model.mtp.layers.1.transformer_block.mlp.w2_md", | |
| "model.mtp.layers.1.transformer_block.mlp_sconv", | |
| "model.mtp.layers.2.input_proj", | |
| "model.mtp.layers.2.transformer_block.attn.k_sconv", | |
| "model.mtp.layers.2.transformer_block.attn.v_sconv", | |
| "model.mtp.layers.2.transformer_block.attn.wk_dv", | |
| "model.mtp.layers.2.transformer_block.attn.wo_ud", | |
| "model.mtp.layers.2.transformer_block.attn.wq_du", | |
| "model.mtp.layers.2.transformer_block.attn.wr_du", | |
| "model.mtp.layers.2.transformer_block.attn.wv_dv", | |
| "model.mtp.layers.2.transformer_block.attn_sconv", | |
| "model.mtp.layers.2.transformer_block.mlp.w13_dn", | |
| "model.mtp.layers.2.transformer_block.mlp.w2_md", | |
| "model.mtp.layers.2.transformer_block.mlp_sconv", | |
| "model.mtp.layers.3.input_proj", | |
| "model.mtp.layers.3.transformer_block.attn.k_sconv", | |
| "model.mtp.layers.3.transformer_block.attn.v_sconv", | |
| "model.mtp.layers.3.transformer_block.attn.wk_dv", | |
| "model.mtp.layers.3.transformer_block.attn.wo_ud", | |
| "model.mtp.layers.3.transformer_block.attn.wq_du", | |
| "model.mtp.layers.3.transformer_block.attn.wr_du", | |
| "model.mtp.layers.3.transformer_block.attn.wv_dv", | |
| "model.mtp.layers.3.transformer_block.attn_sconv", | |
| "model.mtp.layers.3.transformer_block.mlp.w13_dn", | |
| "model.mtp.layers.3.transformer_block.mlp.w2_md", | |
| "model.mtp.layers.3.transformer_block.mlp_sconv", | |
| "model.mtp.layers.4.input_proj", | |
| "model.mtp.layers.4.transformer_block.attn.k_sconv", | |
| "model.mtp.layers.4.transformer_block.attn.v_sconv", | |
| "model.mtp.layers.4.transformer_block.attn.wk_dv", | |
| "model.mtp.layers.4.transformer_block.attn.wo_ud", | |
| "model.mtp.layers.4.transformer_block.attn.wq_du", | |
| "model.mtp.layers.4.transformer_block.attn.wr_du", | |
| "model.mtp.layers.4.transformer_block.attn.wv_dv", | |
| "model.mtp.layers.4.transformer_block.attn_sconv", | |
| "model.mtp.layers.4.transformer_block.mlp.w13_dn", | |
| "model.mtp.layers.4.transformer_block.mlp.w2_md", | |
| "model.mtp.layers.4.transformer_block.mlp_sconv", | |
| "model.mtp.layers.5.input_proj", | |
| "model.mtp.layers.5.transformer_block.attn.k_sconv", | |
| "model.mtp.layers.5.transformer_block.attn.v_sconv", | |
| "model.mtp.layers.5.transformer_block.attn.wk_dv", | |
| "model.mtp.layers.5.transformer_block.attn.wo_ud", | |
| "model.mtp.layers.5.transformer_block.attn.wq_du", | |
| "model.mtp.layers.5.transformer_block.attn.wr_du", | |
| "model.mtp.layers.5.transformer_block.attn.wv_dv", | |
| "model.mtp.layers.5.transformer_block.attn_sconv", | |
| "model.mtp.layers.5.transformer_block.mlp.w13_dn", | |
| "model.mtp.layers.5.transformer_block.mlp.w2_md", | |
| "model.mtp.layers.5.transformer_block.mlp_sconv", | |
| "model.mtp.layers.6.input_proj", | |
| "model.mtp.layers.6.transformer_block.attn.k_sconv", | |
| "model.mtp.layers.6.transformer_block.attn.v_sconv", | |
| "model.mtp.layers.6.transformer_block.attn.wk_dv", | |
| "model.mtp.layers.6.transformer_block.attn.wo_ud", | |
| "model.mtp.layers.6.transformer_block.attn.wq_du", | |
| "model.mtp.layers.6.transformer_block.attn.wr_du", | |
| "model.mtp.layers.6.transformer_block.attn.wv_dv", | |
| "model.mtp.layers.6.transformer_block.attn_sconv", | |
| "model.mtp.layers.6.transformer_block.mlp.w13_dn", | |
| "model.mtp.layers.6.transformer_block.mlp.w2_md", | |
| "model.mtp.layers.6.transformer_block.mlp_sconv", | |
| "model.mtp.layers.7.input_proj", | |
| "model.mtp.layers.7.transformer_block.attn.k_sconv", | |
| "model.mtp.layers.7.transformer_block.attn.v_sconv", | |
| "model.mtp.layers.7.transformer_block.attn.wk_dv", | |
| "model.mtp.layers.7.transformer_block.attn.wo_ud", | |
| "model.mtp.layers.7.transformer_block.attn.wq_du", | |
| "model.mtp.layers.7.transformer_block.attn.wr_du", | |
| "model.mtp.layers.7.transformer_block.attn.wv_dv", | |
| "model.mtp.layers.7.transformer_block.attn_sconv", | |
| "model.mtp.layers.7.transformer_block.mlp.w13_dn", | |
| "model.mtp.layers.7.transformer_block.mlp.w2_md", | |
| "model.mtp.layers.7.transformer_block.mlp_sconv", | |
| "model.llm.layers.0.attn.k_sconv", | |
| "model.llm.layers.0.attn.v_sconv", | |
| "model.llm.layers.0.attn.wv_dv", | |
| "model.llm.layers.0.mlp_sconv", | |
| "model.llm.layers.10.attn.k_sconv", | |
| "model.llm.layers.10.attn.wk_dv", | |
| "model.llm.layers.12.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.13.attn.wo_ud", | |
| "model.llm.layers.13.mlp.gate", | |
| "model.llm.layers.15.attn.wv_dv", | |
| "model.llm.layers.15.mlp.gate", | |
| "model.llm.layers.17.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.18.attn.k_sconv", | |
| "model.llm.layers.18.attn.wo_ud", | |
| "model.llm.layers.18.attn.wv_dv", | |
| "model.llm.layers.18.attn_sconv", | |
| "model.llm.layers.19.mlp.gate", | |
| "model.llm.layers.2.attn.k_sconv", | |
| "model.llm.layers.2.attn.v_sconv", | |
| "model.llm.layers.2.attn.wk_dv", | |
| "model.llm.layers.20.attn_sconv", | |
| "model.llm.layers.22.attn.wo_ud", | |
| "model.llm.layers.22.mlp.gate", | |
| "model.llm.layers.23.attn.wo_ud", | |
| "model.llm.layers.24.attn.wv_dv", | |
| "model.llm.layers.24.attn_sconv", | |
| "model.llm.layers.24.mlp_sconv", | |
| "model.llm.layers.25.attn.wk_dv", | |
| "model.llm.layers.26.attn.wk_dv", | |
| "model.llm.layers.27.attn.wr_du", | |
| "model.llm.layers.27.mlp_sconv", | |
| "model.llm.layers.29.mlp_sconv", | |
| "model.llm.layers.3.attn.k_sconv", | |
| "model.llm.layers.3.attn.v_sconv", | |
| "model.llm.layers.30.attn.k_sconv", | |
| "model.llm.layers.30.mlp.gate", | |
| "model.llm.layers.30.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.31.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.33.attn.wk_dv", | |
| "model.llm.layers.33.attn.wr_du", | |
| "model.llm.layers.33.attn_sconv", | |
| "model.llm.layers.37.attn.v_sconv", | |
| "model.llm.layers.37.attn.wk_dv", | |
| "model.llm.layers.38.attn_sconv", | |
| "model.llm.layers.39.attn.wk_dv", | |
| "model.llm.layers.39.attn.wq_du", | |
| "model.llm.layers.40.attn.wo_ud", | |
| "model.llm.layers.41.attn.wo_ud", | |
| "model.llm.layers.41.attn_sconv", | |
| "model.llm.layers.41.mlp_sconv", | |
| "model.llm.layers.5.attn.wk_dv", | |
| "model.audio.encoder", | |
| "model.llm.layers.1.mlp.w13_dn", | |
| "model.llm.layers.10.attn_sconv", | |
| "model.llm.layers.12.attn.wo_ud", | |
| "model.llm.layers.12.mlp_sconv", | |
| "model.llm.layers.13.attn.v_sconv", | |
| "model.llm.layers.15.attn.v_sconv", | |
| "model.llm.layers.15.attn.wr_du", | |
| "model.llm.layers.16.attn.wo_ud", | |
| "model.llm.layers.16.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.16.mlp_sconv", | |
| "model.llm.layers.17.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.18.attn.wq_du", | |
| "model.llm.layers.18.mlp.gate", | |
| "model.llm.layers.19.attn.wo_ud", | |
| "model.llm.layers.2.mlp_sconv", | |
| "model.llm.layers.20.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.21.attn.k_sconv", | |
| "model.llm.layers.21.mlp.gate", | |
| "model.llm.layers.22.attn.wr_du", | |
| "model.llm.layers.22.attn.wv_dv", | |
| "model.llm.layers.23.attn.k_sconv", | |
| "model.llm.layers.23.attn.v_sconv", | |
| "model.llm.layers.23.attn.wq_du", | |
| "model.llm.layers.23.attn_sconv", | |
| "model.llm.layers.23.mlp.gate", | |
| "model.llm.layers.24.attn.wr_du", | |
| "model.llm.layers.25.attn.wo_ud", | |
| "model.llm.layers.25.attn.wq_du", | |
| "model.llm.layers.25.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.26.attn.wq_du", | |
| "model.llm.layers.26.mlp_sconv", | |
| "model.llm.layers.27.attn.v_sconv", | |
| "model.llm.layers.27.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.28.attn.wq_du", | |
| "model.llm.layers.28.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.28.mlp_sconv", | |
| "model.llm.layers.3.attn.wr_du", | |
| "model.llm.layers.3.attn.wv_dv", | |
| "model.llm.layers.3.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.31.attn.k_sconv", | |
| "model.llm.layers.32.attn.wk_dv", | |
| "model.llm.layers.32.attn_sconv", | |
| "model.llm.layers.33.attn.wv_dv", | |
| "model.llm.layers.34.attn.wk_dv", | |
| "model.llm.layers.34.attn.wq_du", | |
| "model.llm.layers.34.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.35.attn_sconv", | |
| "model.llm.layers.35.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.35.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.36.attn_sconv", | |
| "model.llm.layers.36.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.37.attn.wo_ud", | |
| "model.llm.layers.37.attn_sconv", | |
| "model.llm.layers.37.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.37.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.38.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.4.attn.wq_du", | |
| "model.llm.layers.4.attn.wv_dv", | |
| "model.llm.layers.40.mlp.gate", | |
| "model.llm.layers.40.mlp_sconv", | |
| "model.llm.layers.41.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.5.attn.wv_dv", | |
| "model.llm.layers.5.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.6.attn.v_sconv", | |
| "model.llm.layers.6.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.7.mlp.gate", | |
| "model.llm.layers.8.attn.wo_ud", | |
| "model.llm.layers.8.attn_sconv", | |
| "model.llm.layers.8.mlp_sconv", | |
| "model.llm.layers.9.attn.wk_dv", | |
| "model.llm.layers.9.mlp_sconv", | |
| "model.llm.embed", | |
| "model.llm.layers.0.attn.wq_du", | |
| "model.llm.layers.1.attn.wo_ud", | |
| "model.llm.layers.1.attn.wq_du", | |
| "model.llm.layers.10.attn.wo_ud", | |
| "model.llm.layers.10.mlp_sconv", | |
| "model.llm.layers.11.attn.k_sconv", | |
| "model.llm.layers.11.attn.wq_du", | |
| "model.llm.layers.12.mlp.gate", | |
| "model.llm.layers.13.attn.wk_dv", | |
| "model.llm.layers.14.attn.wq_du", | |
| "model.llm.layers.14.attn_sconv", | |
| "model.llm.layers.14.mlp.gate", | |
| "model.llm.layers.15.attn.wk_dv", | |
| "model.llm.layers.16.attn.k_sconv", | |
| "model.llm.layers.16.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.17.attn.k_sconv", | |
| "model.llm.layers.17.attn.wq_du", | |
| "model.llm.layers.17.mlp_sconv", | |
| "model.llm.layers.19.attn_sconv", | |
| "model.llm.layers.19.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.2.attn.wq_du", | |
| "model.llm.layers.2.attn.wv_dv", | |
| "model.llm.layers.2.mlp.gate", | |
| "model.llm.layers.20.attn.v_sconv", | |
| "model.llm.layers.20.attn.wo_ud", | |
| "model.llm.layers.20.attn.wv_dv", | |
| "model.llm.layers.20.mlp.gate", | |
| "model.llm.layers.20.mlp_sconv", | |
| "model.llm.layers.21.attn_sconv", | |
| "model.llm.layers.22.attn_sconv", | |
| "model.llm.layers.23.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.24.attn.k_sconv", | |
| "model.llm.layers.25.attn.wv_dv", | |
| "model.llm.layers.25.mlp_sconv", | |
| "model.llm.layers.28.attn.wk_dv", | |
| "model.llm.layers.28.attn.wo_ud", | |
| "model.llm.layers.29.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.31.attn.wq_du", | |
| "model.llm.layers.31.attn.wr_du", | |
| "model.llm.layers.31.attn.wv_dv", | |
| "model.llm.layers.32.attn.k_sconv", | |
| "model.llm.layers.33.attn.v_sconv", | |
| "model.llm.layers.33.attn.wo_ud", | |
| "model.llm.layers.34.attn.wv_dv", | |
| "model.llm.layers.34.attn_sconv", | |
| "model.llm.layers.34.mlp_sconv", | |
| "model.llm.layers.36.attn.v_sconv", | |
| "model.llm.layers.36.attn.wk_dv", | |
| "model.llm.layers.37.attn.wr_du", | |
| "model.llm.layers.37.attn.wv_dv", | |
| "model.llm.layers.38.attn.wq_du", | |
| "model.llm.layers.38.attn.wv_dv", | |
| "model.llm.layers.38.mlp_sconv", | |
| "model.llm.layers.39.attn_sconv", | |
| "model.llm.layers.4.attn.k_sconv", | |
| "model.llm.layers.41.attn.wv_dv", | |
| "model.llm.layers.5.attn.wr_du", | |
| "model.llm.layers.6.attn.wr_du", | |
| "model.llm.layers.7.mlp_sconv", | |
| "model.llm.layers.8.attn.wr_du", | |
| "model.llm.layers.8.attn.wv_dv", | |
| "model.llm.layers.9.attn.v_sconv", | |
| "model.llm.layers.1.attn.wr_du", | |
| "model.llm.layers.10.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.11.attn.wr_du", | |
| "model.llm.layers.11.mlp_sconv", | |
| "model.llm.layers.12.attn.k_sconv", | |
| "model.llm.layers.12.attn.v_sconv", | |
| "model.llm.layers.13.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.14.attn.wv_dv", | |
| "model.llm.layers.15.attn.wq_du", | |
| "model.llm.layers.15.attn_sconv", | |
| "model.llm.layers.16.attn.wr_du", | |
| "model.llm.layers.17.attn.wk_dv", | |
| "model.llm.layers.19.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.19.mlp_sconv", | |
| "model.llm.layers.2.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.20.attn.wk_dv", | |
| "model.llm.layers.22.attn.k_sconv", | |
| "model.llm.layers.23.mlp_sconv", | |
| "model.llm.layers.24.attn.wk_dv", | |
| "model.llm.layers.24.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.25.attn.wr_du", | |
| "model.llm.layers.26.attn.k_sconv", | |
| "model.llm.layers.29.attn.wr_du", | |
| "model.llm.layers.29.attn.wv_dv", | |
| "model.llm.layers.29.mlp.gate", | |
| "model.llm.layers.3.attn.wk_dv", | |
| "model.llm.layers.30.attn.wo_ud", | |
| "model.llm.layers.30.mlp_sconv", | |
| "model.llm.layers.31.attn.v_sconv", | |
| "model.llm.layers.31.attn_sconv", | |
| "model.llm.layers.32.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.32.mlp_sconv", | |
| "model.llm.layers.33.mlp_sconv", | |
| "model.llm.layers.35.attn.wk_dv", | |
| "model.llm.layers.35.attn.wv_dv", | |
| "model.llm.layers.36.attn.wv_dv", | |
| "model.llm.layers.36.mlp.gate", | |
| "model.llm.layers.39.attn.k_sconv", | |
| "model.llm.layers.39.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.40.attn.v_sconv", | |
| "model.llm.layers.6.attn.wk_dv", | |
| "model.llm.layers.6.attn.wo_ud", | |
| "model.llm.layers.7.attn.k_sconv", | |
| "model.llm.layers.7.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.9.attn_sconv", | |
| "model.llm.layers.0.attn.wk_dv", | |
| "model.llm.layers.0.mlp.w13_dn", | |
| "model.llm.layers.1.attn.wk_dv", | |
| "model.llm.layers.10.attn.wr_du", | |
| "model.llm.layers.11.attn.wk_dv", | |
| "model.llm.layers.12.attn.wq_du", | |
| "model.llm.layers.12.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.14.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.14.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.16.attn.wk_dv", | |
| "model.llm.layers.17.attn.wv_dv", | |
| "model.llm.layers.17.attn_sconv", | |
| "model.llm.layers.19.attn.k_sconv", | |
| "model.llm.layers.20.attn.wr_du", | |
| "model.llm.layers.21.mlp_sconv", | |
| "model.llm.layers.24.attn.v_sconv", | |
| "model.llm.layers.27.attn.k_sconv", | |
| "model.llm.layers.27.attn.wq_du", | |
| "model.llm.layers.31.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.33.attn.wq_du", | |
| "model.llm.layers.33.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.34.attn.wo_ud", | |
| "model.llm.layers.35.attn.wq_du", | |
| "model.llm.layers.37.mlp.gate", | |
| "model.llm.layers.39.attn.v_sconv", | |
| "model.llm.layers.39.attn.wr_du", | |
| "model.llm.layers.39.mlp.gate", | |
| "model.llm.layers.41.attn.wk_dv", | |
| "model.llm.layers.6.attn.wv_dv", | |
| "model.llm.layers.6.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.7.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.8.attn.wk_dv", | |
| "model.llm.layers.8.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.9.attn.wo_ud", | |
| "model.llm.layers.0.attn.wo_ud", | |
| "model.llm.layers.0.attn.wr_du", | |
| "model.llm.layers.1.attn_sconv", | |
| "model.llm.layers.10.mlp.gate", | |
| "model.llm.layers.10.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.11.attn_sconv", | |
| "model.llm.layers.11.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.11.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.12.attn.wv_dv", | |
| "model.llm.layers.13.attn.wv_dv", | |
| "model.llm.layers.13.attn_sconv", | |
| "model.llm.layers.14.attn.v_sconv", | |
| "model.llm.layers.14.attn.wk_dv", | |
| "model.llm.layers.15.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.15.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.18.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.18.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.2.attn_sconv", | |
| "model.llm.layers.21.attn.wo_ud", | |
| "model.llm.layers.21.attn.wq_du", | |
| "model.llm.layers.22.attn.v_sconv", | |
| "model.llm.layers.22.attn.wq_du", | |
| "model.llm.layers.22.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.22.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.22.mlp_sconv", | |
| "model.llm.layers.23.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.26.attn.wo_ud", | |
| "model.llm.layers.26.attn_sconv", | |
| "model.llm.layers.26.mlp.gate", | |
| "model.llm.layers.26.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.27.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.29.attn.k_sconv", | |
| "model.llm.layers.29.attn.wo_ud", | |
| "model.llm.layers.30.attn_sconv", | |
| "model.llm.layers.31.mlp.gate", | |
| "model.llm.layers.32.attn.v_sconv", | |
| "model.llm.layers.33.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.34.attn.k_sconv", | |
| "model.llm.layers.34.attn.wr_du", | |
| "model.llm.layers.34.mlp.gate", | |
| "model.llm.layers.35.attn.k_sconv", | |
| "model.llm.layers.36.attn.k_sconv", | |
| "model.llm.layers.36.attn.wq_du", | |
| "model.llm.layers.37.attn.wq_du", | |
| "model.llm.layers.38.attn.wo_ud", | |
| "model.llm.layers.38.attn.wr_du", | |
| "model.llm.layers.39.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.4.attn.wo_ud", | |
| "model.llm.layers.4.attn_sconv", | |
| "model.llm.layers.40.attn.wv_dv", | |
| "model.llm.layers.40.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.41.attn.v_sconv", | |
| "model.llm.layers.41.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.5.attn.wq_du", | |
| "model.llm.layers.6.mlp_sconv", | |
| "model.llm.layers.7.attn.wo_ud", | |
| "model.llm.layers.9.attn.k_sconv", | |
| "model.llm.layers.9.attn.wr_du", | |
| "model.llm.layers.9.mlp.gate", | |
| "model.llm.layers.0.mlp.w2_md", | |
| "model.llm.layers.1.attn.k_sconv", | |
| "model.llm.layers.1.mlp_sconv", | |
| "model.llm.layers.10.attn.wq_du", | |
| "model.llm.layers.11.attn.v_sconv", | |
| "model.llm.layers.13.attn.k_sconv", | |
| "model.llm.layers.14.mlp_sconv", | |
| "model.llm.layers.15.attn.wo_ud", | |
| "model.llm.layers.16.attn.wq_du", | |
| "model.llm.layers.16.attn.wv_dv", | |
| "model.llm.layers.17.attn.v_sconv", | |
| "model.llm.layers.17.mlp.gate", | |
| "model.llm.layers.18.attn.wk_dv", | |
| "model.llm.layers.18.attn.wr_du", | |
| "model.llm.layers.19.attn.wk_dv", | |
| "model.llm.layers.19.attn.wq_du", | |
| "model.llm.layers.2.attn.wr_du", | |
| "model.llm.layers.2.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.21.attn.v_sconv", | |
| "model.llm.layers.24.attn.wo_ud", | |
| "model.llm.layers.25.attn.v_sconv", | |
| "model.llm.layers.25.attn_sconv", | |
| "model.llm.layers.26.attn.v_sconv", | |
| "model.llm.layers.26.attn.wv_dv", | |
| "model.llm.layers.26.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.27.attn.wv_dv", | |
| "model.llm.layers.27.attn_sconv", | |
| "model.llm.layers.27.mlp.gate", | |
| "model.llm.layers.28.attn.v_sconv", | |
| "model.llm.layers.28.attn.wr_du", | |
| "model.llm.layers.28.attn.wv_dv", | |
| "model.llm.layers.28.attn_sconv", | |
| "model.llm.layers.28.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.29.attn.wq_du", | |
| "model.llm.layers.3.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.30.attn.v_sconv", | |
| "model.llm.layers.30.attn.wk_dv", | |
| "model.llm.layers.30.attn.wv_dv", | |
| "model.llm.layers.31.mlp_sconv", | |
| "model.llm.layers.32.attn.wv_dv", | |
| "model.llm.layers.33.attn.k_sconv", | |
| "model.llm.layers.35.attn.wr_du", | |
| "model.llm.layers.35.mlp.gate", | |
| "model.llm.layers.37.attn.k_sconv", | |
| "model.llm.layers.38.attn.k_sconv", | |
| "model.llm.layers.38.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.39.mlp_sconv", | |
| "model.llm.layers.4.attn.wr_du", | |
| "model.llm.layers.4.mlp_sconv", | |
| "model.llm.layers.40.attn.wk_dv", | |
| "model.llm.layers.41.attn.wq_du", | |
| "model.llm.layers.41.mlp.gate", | |
| "model.llm.layers.5.attn.k_sconv", | |
| "model.llm.layers.5.attn.v_sconv", | |
| "model.llm.layers.5.attn_sconv", | |
| "model.llm.layers.6.attn.k_sconv", | |
| "model.llm.layers.6.attn_sconv", | |
| "model.llm.layers.7.attn.wk_dv", | |
| "model.llm.layers.7.attn_sconv", | |
| "model.llm.layers.8.attn.wq_du", | |
| "model.llm.layers.9.attn.wq_du", | |
| "model.llm.layers.9.mlp.shared_experts.shared_w2_weight", | |
| "model.visual.layers.linear_1", | |
| "model.llm.layers.0.attn_sconv", | |
| "model.llm.layers.1.attn.wv_dv", | |
| "model.llm.layers.1.mlp.w2_md", | |
| "model.llm.layers.10.attn.v_sconv", | |
| "model.llm.layers.10.attn.wv_dv", | |
| "model.llm.layers.11.attn.wo_ud", | |
| "model.llm.layers.11.attn.wv_dv", | |
| "model.llm.layers.11.mlp.gate", | |
| "model.llm.layers.12.attn.wk_dv", | |
| "model.llm.layers.12.attn_sconv", | |
| "model.llm.layers.13.attn.wr_du", | |
| "model.llm.layers.13.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.14.attn.k_sconv", | |
| "model.llm.layers.14.attn.wo_ud", | |
| "model.llm.layers.15.attn.k_sconv", | |
| "model.llm.layers.16.attn.v_sconv", | |
| "model.llm.layers.16.attn_sconv", | |
| "model.llm.layers.17.attn.wr_du", | |
| "model.llm.layers.18.attn.v_sconv", | |
| "model.llm.layers.19.attn.wr_du", | |
| "model.llm.layers.20.attn.k_sconv", | |
| "model.llm.layers.20.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.21.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.22.attn.wk_dv", | |
| "model.llm.layers.23.attn.wk_dv", | |
| "model.llm.layers.24.mlp.gate", | |
| "model.llm.layers.24.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.25.attn.k_sconv", | |
| "model.llm.layers.27.attn.wk_dv", | |
| "model.llm.layers.28.attn.k_sconv", | |
| "model.llm.layers.29.attn_sconv", | |
| "model.llm.layers.29.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.3.attn.wq_du", | |
| "model.llm.layers.3.attn_sconv", | |
| "model.llm.layers.3.mlp.gate", | |
| "model.llm.layers.30.attn.wr_du", | |
| "model.llm.layers.30.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.31.attn.wo_ud", | |
| "model.llm.layers.32.attn.wq_du", | |
| "model.llm.layers.34.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.35.attn.wo_ud", | |
| "model.llm.layers.36.mlp_sconv", | |
| "model.llm.layers.37.mlp_sconv", | |
| "model.llm.layers.38.mlp.gate", | |
| "model.llm.layers.39.attn.wo_ud", | |
| "model.llm.layers.4.mlp.gate", | |
| "model.llm.layers.4.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.40.attn.k_sconv", | |
| "model.llm.layers.40.attn.wq_du", | |
| "model.llm.layers.40.attn.wr_du", | |
| "model.llm.layers.41.attn.k_sconv", | |
| "model.llm.layers.5.mlp.gate", | |
| "model.llm.layers.6.mlp.gate", | |
| "model.llm.layers.7.attn.wr_du", | |
| "model.llm.layers.8.attn.k_sconv", | |
| "model.llm.layers.8.attn.v_sconv", | |
| "model.llm.layers.8.mlp.gate", | |
| "model.llm.layers.8.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.1.attn.v_sconv", | |
| "model.llm.layers.12.attn.wr_du", | |
| "model.llm.layers.13.attn.wq_du", | |
| "model.llm.layers.13.mlp_sconv", | |
| "model.llm.layers.14.attn.wr_du", | |
| "model.llm.layers.15.mlp_sconv", | |
| "model.llm.layers.16.mlp.gate", | |
| "model.llm.layers.17.attn.wo_ud", | |
| "model.llm.layers.18.mlp_sconv", | |
| "model.llm.layers.19.attn.v_sconv", | |
| "model.llm.layers.19.attn.wv_dv", | |
| "model.llm.layers.2.attn.wo_ud", | |
| "model.llm.layers.20.attn.wq_du", | |
| "model.llm.layers.21.attn.wk_dv", | |
| "model.llm.layers.21.attn.wr_du", | |
| "model.llm.layers.21.attn.wv_dv", | |
| "model.llm.layers.21.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.23.attn.wr_du", | |
| "model.llm.layers.23.attn.wv_dv", | |
| "model.llm.layers.24.attn.wq_du", | |
| "model.llm.layers.25.mlp.gate", | |
| "model.llm.layers.25.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.26.attn.wr_du", | |
| "model.llm.layers.27.attn.wo_ud", | |
| "model.llm.layers.28.mlp.gate", | |
| "model.llm.layers.29.attn.v_sconv", | |
| "model.llm.layers.29.attn.wk_dv", | |
| "model.llm.layers.3.attn.wo_ud", | |
| "model.llm.layers.3.mlp_sconv", | |
| "model.llm.layers.30.attn.wq_du", | |
| "model.llm.layers.31.attn.wk_dv", | |
| "model.llm.layers.32.attn.wo_ud", | |
| "model.llm.layers.32.attn.wr_du", | |
| "model.llm.layers.32.mlp.gate", | |
| "model.llm.layers.32.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.33.mlp.gate", | |
| "model.llm.layers.34.attn.v_sconv", | |
| "model.llm.layers.35.attn.v_sconv", | |
| "model.llm.layers.35.mlp_sconv", | |
| "model.llm.layers.36.attn.wo_ud", | |
| "model.llm.layers.36.attn.wr_du", | |
| "model.llm.layers.36.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.38.attn.v_sconv", | |
| "model.llm.layers.38.attn.wk_dv", | |
| "model.llm.layers.39.attn.wv_dv", | |
| "model.llm.layers.4.attn.v_sconv", | |
| "model.llm.layers.4.attn.wk_dv", | |
| "model.llm.layers.4.mlp.shared_experts.shared_w2_weight", | |
| "model.llm.layers.40.attn_sconv", | |
| "model.llm.layers.40.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.41.attn.wr_du", | |
| "model.llm.layers.5.attn.wo_ud", | |
| "model.llm.layers.5.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.layers.5.mlp_sconv", | |
| "model.llm.layers.6.attn.wq_du", | |
| "model.llm.layers.7.attn.v_sconv", | |
| "model.llm.layers.7.attn.wq_du", | |
| "model.llm.layers.7.attn.wv_dv", | |
| "model.llm.layers.9.attn.wv_dv", | |
| "model.llm.layers.9.mlp.shared_experts.shared_w13_weight", | |
| "model.llm.unembed", | |
| "model.visual.layers.linear_0", | |
| "model.visual.layers.linear_2", | |
| "model.visual.layers.linear_3" | |
| ], | |
| "provider": "auto-round" | |
| } |