Image-Text-to-Text
Transformers
Safetensors
qwen3_5
qwen3.8
qwen
huihui
awq
w4a16
multimodal
v100
sm70
tensor-parallel
abliterated
uncensored
conversational
4-bit precision
Instructions to use leoncca/Qwen3.8-27B-Huihui-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use leoncca/Qwen3.8-27B-Huihui-AWQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="leoncca/Qwen3.8-27B-Huihui-AWQ") 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("leoncca/Qwen3.8-27B-Huihui-AWQ") model = AutoModelForMultimodalLM.from_pretrained("leoncca/Qwen3.8-27B-Huihui-AWQ", 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 leoncca/Qwen3.8-27B-Huihui-AWQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "leoncca/Qwen3.8-27B-Huihui-AWQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "leoncca/Qwen3.8-27B-Huihui-AWQ", "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/leoncca/Qwen3.8-27B-Huihui-AWQ
- SGLang
How to use leoncca/Qwen3.8-27B-Huihui-AWQ 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 "leoncca/Qwen3.8-27B-Huihui-AWQ" \ --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": "leoncca/Qwen3.8-27B-Huihui-AWQ", "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 "leoncca/Qwen3.8-27B-Huihui-AWQ" \ --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": "leoncca/Qwen3.8-27B-Huihui-AWQ", "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 leoncca/Qwen3.8-27B-Huihui-AWQ with Docker Model Runner:
docker model run hf.co/leoncca/Qwen3.8-27B-Huihui-AWQ
Download quant_log.csv from leoncca/Qwen3.8-27B-Huihui-AWQ: direct link, hf CLI and curl.
- Browser
- Download file 16.6 kB
-
https://huggingface.co/leoncca/Qwen3.8-27B-Huihui-AWQ/resolve/main/quant_log.csv
- Command line
-
hf download hf://leoncca/Qwen3.8-27B-Huihui-AWQ/quant_log.csv
-
curl -L -o quant_log.csv https://huggingface.co/leoncca/Qwen3.8-27B-Huihui-AWQ/resolve/main/quant_log.csv
16.6 kB
| layer,module,loss,samples,damp,time | |
| 0,linear_attn.in_proj_qkv,0.0000016380,,0.021 | |
| 0,linear_attn.in_proj_z,0.0000016380,,0.031 | |
| 0,linear_attn.out_proj,not applicable,,0.036 | |
| 0,mlp.gate_proj,0.0000003862,,0.048 | |
| 0,mlp.up_proj,0.0000003862,,0.059 | |
| 0,mlp.down_proj,0.0000010086,,0.072 | |
| 1,linear_attn.in_proj_qkv,0.0000012900,,0.008 | |
| 1,linear_attn.in_proj_z,0.0000012900,,0.014 | |
| 1,linear_attn.out_proj,not applicable,,0.019 | |
| 1,mlp.gate_proj,0.0000011203,,0.028 | |
| 1,mlp.up_proj,0.0000011203,,0.037 | |
| 1,mlp.down_proj,0.0000016897,,0.046 | |
| 2,linear_attn.in_proj_qkv,0.0000022176,,0.007 | |
| 2,linear_attn.in_proj_z,0.0000022176,,0.012 | |
| 2,linear_attn.out_proj,not applicable,,0.017 | |
| 2,mlp.gate_proj,0.0000040707,,0.026 | |
| 2,mlp.up_proj,0.0000040707,,0.035 | |
| 2,mlp.down_proj,0.0000039030,,0.044 | |
| 3,self_attn.q_proj,0.0000034477,,0.010 | |
| 3,self_attn.k_proj,0.0000034477,,0.017 | |
| 3,self_attn.v_proj,0.0000034477,,0.019 | |
| 3,self_attn.o_proj,not applicable,,0.023 | |
| 3,mlp.gate_proj,0.0000037049,,0.033 | |
| 3,mlp.up_proj,0.0000037049,,0.042 | |
| 3,mlp.down_proj,0.0000038534,,0.051 | |
| 4,linear_attn.in_proj_qkv,0.0000038554,,0.007 | |
| 4,linear_attn.in_proj_z,0.0000038554,,0.013 | |
| 4,linear_attn.out_proj,not applicable,,0.017 | |
| 4,mlp.gate_proj,0.0000080375,,0.027 | |
| 4,mlp.up_proj,0.0000080375,,0.036 | |
| 4,mlp.down_proj,0.0000061858,,0.045 | |
| 5,linear_attn.in_proj_qkv,0.0000045622,,0.007 | |
| 5,linear_attn.in_proj_z,0.0000045622,,0.013 | |
| 5,linear_attn.out_proj,not applicable,,0.018 | |
| 5,mlp.gate_proj,0.0000099294,,0.027 | |
| 5,mlp.up_proj,0.0000099294,,0.037 | |
| 5,mlp.down_proj,0.0000087976,,0.046 | |
| 6,linear_attn.in_proj_qkv,0.0000073547,,0.008 | |
| 6,linear_attn.in_proj_z,0.0000073547,,0.014 | |
| 6,linear_attn.out_proj,not applicable,,0.018 | |
| 6,mlp.gate_proj,0.0000167014,,0.028 | |
| 6,mlp.up_proj,0.0000167014,,0.037 | |
| 6,mlp.down_proj,0.0000156754,,0.047 | |
| 7,self_attn.q_proj,0.0000117582,,0.010 | |
| 7,self_attn.k_proj,0.0000117582,,0.016 | |
| 7,self_attn.v_proj,0.0000117582,,0.018 | |
| 7,self_attn.o_proj,not applicable,,0.022 | |
| 7,mlp.gate_proj,0.0000187049,,0.032 | |
| 7,mlp.up_proj,0.0000187049,,0.041 | |
| 7,mlp.down_proj,0.0000153803,,0.051 | |
| 8,linear_attn.in_proj_qkv,0.0000101067,,0.007 | |
| 8,linear_attn.in_proj_z,0.0000101067,,0.015 | |
| 8,linear_attn.out_proj,not applicable,,0.019 | |
| 8,mlp.gate_proj,0.0000248312,,0.030 | |
| 8,mlp.up_proj,0.0000248312,,0.040 | |
| 8,mlp.down_proj,0.0000195886,,0.049 | |
| 9,linear_attn.in_proj_qkv,0.0000095339,,0.007 | |
| 9,linear_attn.in_proj_z,0.0000095339,,0.014 | |
| 9,linear_attn.out_proj,not applicable,,0.019 | |
| 9,mlp.gate_proj,0.0000238178,,0.030 | |
| 9,mlp.up_proj,0.0000238178,,0.039 | |
| 9,mlp.down_proj,0.0000189169,,0.049 | |
| 10,linear_attn.in_proj_qkv,0.0000121491,,0.006 | |
| 10,linear_attn.in_proj_z,0.0000121491,,0.013 | |
| 10,linear_attn.out_proj,not applicable,,0.017 | |
| 10,mlp.gate_proj,0.0000241134,,0.028 | |
| 10,mlp.up_proj,0.0000241134,,0.037 | |
| 10,mlp.down_proj,0.0000199430,,0.047 | |
| 11,self_attn.q_proj,0.0000221919,,0.009 | |
| 11,self_attn.k_proj,0.0000221919,,0.015 | |
| 11,self_attn.v_proj,0.0000221919,,0.017 | |
| 11,self_attn.o_proj,not applicable,,0.021 | |
| 11,mlp.gate_proj,0.0000247778,,0.031 | |
| 11,mlp.up_proj,0.0000247778,,0.040 | |
| 11,mlp.down_proj,0.0000206496,,0.049 | |
| 12,linear_attn.in_proj_qkv,0.0000174694,,0.009 | |
| 12,linear_attn.in_proj_z,0.0000174694,,0.017 | |
| 12,linear_attn.out_proj,not applicable,,0.021 | |
| 12,mlp.gate_proj,0.0000251065,,0.031 | |
| 12,mlp.up_proj,0.0000251065,,0.040 | |
| 12,mlp.down_proj,0.0000208054,,0.049 | |
| 13,linear_attn.in_proj_qkv,0.0000190737,,0.006 | |
| 13,linear_attn.in_proj_z,0.0000190737,,0.014 | |
| 13,linear_attn.out_proj,not applicable,,0.018 | |
| 13,mlp.gate_proj,0.0000274123,,0.028 | |
| 13,mlp.up_proj,0.0000274123,,0.037 | |
| 13,mlp.down_proj,0.0000234874,,0.046 | |
| 14,linear_attn.in_proj_qkv,0.0000267416,,0.008 | |
| 14,linear_attn.in_proj_z,0.0000267416,,0.014 | |
| 14,linear_attn.out_proj,not applicable,,0.018 | |
| 14,mlp.gate_proj,0.0000290493,,0.027 | |
| 14,mlp.up_proj,0.0000290493,,0.036 | |
| 14,mlp.down_proj,0.0000248887,,0.045 | |
| 15,self_attn.q_proj,0.0000299744,,0.009 | |
| 15,self_attn.k_proj,0.0000299744,,0.016 | |
| 15,self_attn.v_proj,0.0000299744,,0.019 | |
| 15,self_attn.o_proj,not applicable,,0.024 | |
| 15,mlp.gate_proj,0.0000348603,,0.033 | |
| 15,mlp.up_proj,0.0000348603,,0.044 | |
| 15,mlp.down_proj,0.0000292151,,0.053 | |
| 16,linear_attn.in_proj_qkv,0.0000269105,,0.009 | |
| 16,linear_attn.in_proj_z,0.0000269105,,0.017 | |
| 16,linear_attn.out_proj,not applicable,,0.021 | |
| 16,mlp.gate_proj,0.0000426992,,0.031 | |
| 16,mlp.up_proj,0.0000426992,,0.040 | |
| 16,mlp.down_proj,0.0000366058,,0.049 | |
| 17,linear_attn.in_proj_qkv,0.0000358655,,0.007 | |
| 17,linear_attn.in_proj_z,0.0000358655,,0.015 | |
| 17,linear_attn.out_proj,not applicable,,0.020 | |
| 17,mlp.gate_proj,0.0000543341,,0.029 | |
| 17,mlp.up_proj,0.0000543341,,0.039 | |
| 17,mlp.down_proj,0.0000475483,,0.048 | |
| 18,linear_attn.in_proj_qkv,0.0000441931,,0.007 | |
| 18,linear_attn.in_proj_z,0.0000441931,,0.015 | |
| 18,linear_attn.out_proj,not applicable,,0.019 | |
| 18,mlp.gate_proj,0.0000884037,,0.028 | |
| 18,mlp.up_proj,0.0000884037,,0.038 | |
| 18,mlp.down_proj,0.0000819403,,0.047 | |
| 19,self_attn.q_proj,0.0001163868,,0.013 | |
| 19,self_attn.k_proj,0.0001163868,,0.019 | |
| 19,self_attn.v_proj,0.0001163868,,0.021 | |
| 19,self_attn.o_proj,not applicable,,0.026 | |
| 19,mlp.gate_proj,0.0001117514,,0.035 | |
| 19,mlp.up_proj,0.0001117514,,0.045 | |
| 19,mlp.down_proj,0.0001028360,,0.054 | |
| 20,linear_attn.in_proj_qkv,0.0000673925,,0.008 | |
| 20,linear_attn.in_proj_z,0.0000673925,,0.017 | |
| 20,linear_attn.out_proj,not applicable,,0.022 | |
| 20,mlp.gate_proj,0.0001333659,,0.032 | |
| 20,mlp.up_proj,0.0001333659,,0.042 | |
| 20,mlp.down_proj,0.0001111933,,0.052 | |
| 21,linear_attn.in_proj_qkv,0.0000724064,,0.006 | |
| 21,linear_attn.in_proj_z,0.0000724064,,0.013 | |
| 21,linear_attn.out_proj,not applicable,,0.017 | |
| 21,mlp.gate_proj,0.0001530533,,0.026 | |
| 21,mlp.up_proj,0.0001530533,,0.036 | |
| 21,mlp.down_proj,0.0001211819,,0.045 | |
| 22,linear_attn.in_proj_qkv,0.0000684318,,0.007 | |
| 22,linear_attn.in_proj_z,0.0000684318,,0.017 | |
| 22,linear_attn.out_proj,not applicable,,0.021 | |
| 22,mlp.gate_proj,0.0001648623,,0.031 | |
| 22,mlp.up_proj,0.0001648623,,0.041 | |
| 22,mlp.down_proj,0.0001336086,,0.050 | |
| 23,self_attn.q_proj,0.0001666454,,0.010 | |
| 23,self_attn.k_proj,0.0001666454,,0.016 | |
| 23,self_attn.v_proj,0.0001666454,,0.019 | |
| 23,self_attn.o_proj,not applicable,,0.023 | |
| 23,mlp.gate_proj,0.0001898821,,0.033 | |
| 23,mlp.up_proj,0.0001898821,,0.042 | |
| 23,mlp.down_proj,0.0001388790,,0.052 | |
| 24,linear_attn.in_proj_qkv,0.0001078959,,0.008 | |
| 24,linear_attn.in_proj_z,0.0001078959,,0.015 | |
| 24,linear_attn.out_proj,not applicable,,0.019 | |
| 24,mlp.gate_proj,0.0002328693,,0.030 | |
| 24,mlp.up_proj,0.0002328693,,0.039 | |
| 24,mlp.down_proj,0.0001753442,,0.048 | |
| 25,linear_attn.in_proj_qkv,0.0001290192,,0.007 | |
| 25,linear_attn.in_proj_z,0.0001290192,,0.013 | |
| 25,linear_attn.out_proj,not applicable,,0.017 | |
| 25,mlp.gate_proj,0.0002542316,,0.027 | |
| 25,mlp.up_proj,0.0002542316,,0.036 | |
| 25,mlp.down_proj,0.0001938546,,0.045 | |
| 26,linear_attn.in_proj_qkv,0.0001712637,,0.007 | |
| 26,linear_attn.in_proj_z,0.0001712637,,0.015 | |
| 26,linear_attn.out_proj,not applicable,,0.019 | |
| 26,mlp.gate_proj,0.0002860233,,0.028 | |
| 26,mlp.up_proj,0.0002860233,,0.037 | |
| 26,mlp.down_proj,0.0002183416,,0.047 | |
| 27,self_attn.q_proj,0.0006835859,,0.011 | |
| 27,self_attn.k_proj,0.0006835859,,0.017 | |
| 27,self_attn.v_proj,0.0006835859,,0.020 | |
| 27,self_attn.o_proj,not applicable,,0.024 | |
| 27,mlp.gate_proj,0.0003562241,,0.034 | |
| 27,mlp.up_proj,0.0003562241,,0.044 | |
| 27,mlp.down_proj,0.0002953839,,0.053 | |
| 28,linear_attn.in_proj_qkv,0.0002207250,,0.008 | |
| 28,linear_attn.in_proj_z,0.0002207250,,0.016 | |
| 28,linear_attn.out_proj,not applicable,,0.021 | |
| 28,mlp.gate_proj,0.0003317673,,0.030 | |
| 28,mlp.up_proj,0.0003317673,,0.040 | |
| 28,mlp.down_proj,0.0002664407,,0.049 | |
| 29,linear_attn.in_proj_qkv,0.0001950549,,0.009 | |
| 29,linear_attn.in_proj_z,0.0001950549,,0.018 | |
| 29,linear_attn.out_proj,not applicable,,0.023 | |
| 29,mlp.gate_proj,0.0003462141,,0.032 | |
| 29,mlp.up_proj,0.0003462141,,0.042 | |
| 29,mlp.down_proj,0.0002838155,,0.051 | |
| 30,linear_attn.in_proj_qkv,0.0002944490,,0.006 | |
| 30,linear_attn.in_proj_z,0.0002944490,,0.013 | |
| 30,linear_attn.out_proj,not applicable,,0.017 | |
| 30,mlp.gate_proj,0.0003567455,,0.026 | |
| 30,mlp.up_proj,0.0003567455,,0.036 | |
| 30,mlp.down_proj,0.0002943160,,0.045 | |
| 31,self_attn.q_proj,0.0005755530,,0.015 | |
| 31,self_attn.k_proj,0.0005755530,,0.024 | |
| 31,self_attn.v_proj,0.0005755530,,0.026 | |
| 31,self_attn.o_proj,not applicable,,0.030 | |
| 31,mlp.gate_proj,0.0004014420,,0.039 | |
| 31,mlp.up_proj,0.0004014420,,0.048 | |
| 31,mlp.down_proj,0.0003186199,,0.058 | |
| 32,linear_attn.in_proj_qkv,0.0003106689,,0.009 | |
| 32,linear_attn.in_proj_z,0.0003106689,,0.018 | |
| 32,linear_attn.out_proj,not applicable,,0.022 | |
| 32,mlp.gate_proj,0.0004421567,,0.032 | |
| 32,mlp.up_proj,0.0004421567,,0.042 | |
| 32,mlp.down_proj,0.0003454416,,0.051 | |
| 33,linear_attn.in_proj_qkv,0.0003900356,,0.006 | |
| 33,linear_attn.in_proj_z,0.0003900356,,0.015 | |
| 33,linear_attn.out_proj,not applicable,,0.020 | |
| 33,mlp.gate_proj,0.0004678640,,0.029 | |
| 33,mlp.up_proj,0.0004678640,,0.038 | |
| 33,mlp.down_proj,0.0003478689,,0.048 | |
| 34,linear_attn.in_proj_qkv,0.0003785149,,0.008 | |
| 34,linear_attn.in_proj_z,0.0003785149,,0.016 | |
| 34,linear_attn.out_proj,not applicable,,0.021 | |
| 34,mlp.gate_proj,0.0006320122,,0.030 | |
| 34,mlp.up_proj,0.0006320122,,0.040 | |
| 34,mlp.down_proj,0.0004934073,,0.049 | |
| 35,self_attn.q_proj,0.0011108149,,0.011 | |
| 35,self_attn.k_proj,0.0011108149,,0.017 | |
| 35,self_attn.v_proj,0.0011108149,,0.019 | |
| 35,self_attn.o_proj,not applicable,,0.024 | |
| 35,mlp.gate_proj,0.0006238400,,0.034 | |
| 35,mlp.up_proj,0.0006238400,,0.043 | |
| 35,mlp.down_proj,0.0004824514,,0.052 | |
| 36,linear_attn.in_proj_qkv,0.0002366832,,0.009 | |
| 36,linear_attn.in_proj_z,0.0002366832,,0.017 | |
| 36,linear_attn.out_proj,not applicable,,0.022 | |
| 36,mlp.gate_proj,0.0005296277,,0.031 | |
| 36,mlp.up_proj,0.0005296277,,0.040 | |
| 36,mlp.down_proj,0.0003962678,,0.050 | |
| 37,linear_attn.in_proj_qkv,0.0002503380,,0.006 | |
| 37,linear_attn.in_proj_z,0.0002503380,,0.013 | |
| 37,linear_attn.out_proj,not applicable,,0.017 | |
| 37,mlp.gate_proj,0.0005041908,,0.027 | |
| 37,mlp.up_proj,0.0005041908,,0.036 | |
| 37,mlp.down_proj,0.0003558242,,0.045 | |
| 38,linear_attn.in_proj_qkv,0.0001721865,,0.006 | |
| 38,linear_attn.in_proj_z,0.0001721865,,0.012 | |
| 38,linear_attn.out_proj,not applicable,,0.016 | |
| 38,mlp.gate_proj,0.0005179235,,0.025 | |
| 38,mlp.up_proj,0.0005179235,,0.035 | |
| 38,mlp.down_proj,0.0003848562,,0.044 | |
| 39,self_attn.q_proj,0.0006607451,,0.010 | |
| 39,self_attn.k_proj,0.0006607451,,0.014 | |
| 39,self_attn.v_proj,0.0006607451,,0.017 | |
| 39,self_attn.o_proj,not applicable,,0.021 | |
| 39,mlp.gate_proj,0.0005020925,,0.031 | |
| 39,mlp.up_proj,0.0005020925,,0.040 | |
| 39,mlp.down_proj,0.0003556356,,0.049 | |
| 40,linear_attn.in_proj_qkv,0.0002660381,,0.007 | |
| 40,linear_attn.in_proj_z,0.0002660381,,0.015 | |
| 40,linear_attn.out_proj,not applicable,,0.020 | |
| 40,mlp.gate_proj,0.0005828155,,0.029 | |
| 40,mlp.up_proj,0.0005828155,,0.038 | |
| 40,mlp.down_proj,0.0004103785,,0.048 | |
| 41,linear_attn.in_proj_qkv,0.0002335446,,0.009 | |
| 41,linear_attn.in_proj_z,0.0002335446,,0.017 | |
| 41,linear_attn.out_proj,not applicable,,0.021 | |
| 41,mlp.gate_proj,0.0006417350,,0.031 | |
| 41,mlp.up_proj,0.0006417350,,0.041 | |
| 41,mlp.down_proj,0.0004168435,,0.050 | |
| 42,linear_attn.in_proj_qkv,0.0003170260,,0.007 | |
| 42,linear_attn.in_proj_z,0.0003170260,,0.014 | |
| 42,linear_attn.out_proj,not applicable,,0.018 | |
| 42,mlp.gate_proj,0.0007591126,,0.027 | |
| 42,mlp.up_proj,0.0007591126,,0.037 | |
| 42,mlp.down_proj,0.0004959149,,0.046 | |
| 43,self_attn.q_proj,0.0011036232,,0.006 | |
| 43,self_attn.k_proj,0.0011036232,,0.012 | |
| 43,self_attn.v_proj,0.0011036232,,0.015 | |
| 43,self_attn.o_proj,not applicable,,0.019 | |
| 43,mlp.gate_proj,0.0007401613,,0.029 | |
| 43,mlp.up_proj,0.0007401613,,0.038 | |
| 43,mlp.down_proj,0.0004964855,,0.048 | |
| 44,linear_attn.in_proj_qkv,0.0004131533,,0.008 | |
| 44,linear_attn.in_proj_z,0.0004131533,,0.018 | |
| 44,linear_attn.out_proj,not applicable,,0.023 | |
| 44,mlp.gate_proj,0.0007805692,,0.034 | |
| 44,mlp.up_proj,0.0007805692,,0.043 | |
| 44,mlp.down_proj,0.0005284736,,0.053 | |
| 45,linear_attn.in_proj_qkv,0.0003519070,,0.009 | |
| 45,linear_attn.in_proj_z,0.0003519070,,0.018 | |
| 45,linear_attn.out_proj,not applicable,,0.023 | |
| 45,mlp.gate_proj,0.0008203685,,0.033 | |
| 45,mlp.up_proj,0.0008203685,,0.042 | |
| 45,mlp.down_proj,0.0005516273,,0.051 | |
| 46,linear_attn.in_proj_qkv,0.0005885546,,0.006 | |
| 46,linear_attn.in_proj_z,0.0005885546,,0.012 | |
| 46,linear_attn.out_proj,not applicable,,0.016 | |
| 46,mlp.gate_proj,0.0009080387,,0.026 | |
| 46,mlp.up_proj,0.0009080387,,0.035 | |
| 46,mlp.down_proj,0.0006251069,,0.044 | |
| 47,self_attn.q_proj,0.0012794546,,0.010 | |
| 47,self_attn.k_proj,0.0012794546,,0.017 | |
| 47,self_attn.v_proj,0.0012794546,,0.019 | |
| 47,self_attn.o_proj,not applicable,,0.023 | |
| 47,mlp.gate_proj,0.0010251296,,0.033 | |
| 47,mlp.up_proj,0.0010251296,,0.043 | |
| 47,mlp.down_proj,0.0007053357,,0.052 | |
| 48,linear_attn.in_proj_qkv,0.0005421048,,0.013 | |
| 48,linear_attn.in_proj_z,0.0005421048,,0.021 | |
| 48,linear_attn.out_proj,not applicable,,0.026 | |
| 48,mlp.gate_proj,0.0012638368,,0.035 | |
| 48,mlp.up_proj,0.0012638368,,0.045 | |
| 48,mlp.down_proj,0.0008488864,,0.055 | |
| 49,linear_attn.in_proj_qkv,0.0004842966,,0.007 | |
| 49,linear_attn.in_proj_z,0.0004842966,,0.013 | |
| 49,linear_attn.out_proj,not applicable,,0.018 | |
| 49,mlp.gate_proj,0.0014845806,,0.028 | |
| 49,mlp.up_proj,0.0014845806,,0.037 | |
| 49,mlp.down_proj,0.0009813060,,0.047 | |
| 50,linear_attn.in_proj_qkv,0.0008999808,,0.005 | |
| 50,linear_attn.in_proj_z,0.0008999808,,0.011 | |
| 50,linear_attn.out_proj,not applicable,,0.015 | |
| 50,mlp.gate_proj,0.0024173252,,0.025 | |
| 50,mlp.up_proj,0.0024173252,,0.034 | |
| 50,mlp.down_proj,0.0018818722,,0.043 | |
| 51,self_attn.q_proj,0.0039922510,,0.008 | |
| 51,self_attn.k_proj,0.0039922510,,0.014 | |
| 51,self_attn.v_proj,0.0039922510,,0.016 | |
| 51,self_attn.o_proj,not applicable,,0.020 | |
| 51,mlp.gate_proj,0.0027920838,,0.029 | |
| 51,mlp.up_proj,0.0027920838,,0.039 | |
| 51,mlp.down_proj,0.0022079181,,0.048 | |
| 52,linear_attn.in_proj_qkv,0.0006440525,,0.007 | |
| 52,linear_attn.in_proj_z,0.0006440525,,0.018 | |
| 52,linear_attn.out_proj,not applicable,,0.022 | |
| 52,mlp.gate_proj,0.0023486493,,0.031 | |
| 52,mlp.up_proj,0.0023486493,,0.041 | |
| 52,mlp.down_proj,0.0018052340,,0.050 | |
| 53,linear_attn.in_proj_qkv,0.0005554363,,0.007 | |
| 53,linear_attn.in_proj_z,0.0005554363,,0.015 | |
| 53,linear_attn.out_proj,not applicable,,0.019 | |
| 53,mlp.gate_proj,0.0023646984,,0.029 | |
| 53,mlp.up_proj,0.0023646984,,0.038 | |
| 53,mlp.down_proj,0.0018894822,,0.047 | |
| 54,linear_attn.in_proj_qkv,0.0005636523,,0.007 | |
| 54,linear_attn.in_proj_z,0.0005636523,,0.014 | |
| 54,linear_attn.out_proj,not applicable,,0.020 | |
| 54,mlp.gate_proj,0.0029807497,,0.029 | |
| 54,mlp.up_proj,0.0029807497,,0.038 | |
| 54,mlp.down_proj,0.0026787185,,0.047 | |
| 55,self_attn.q_proj,0.0037838577,,0.010 | |
| 55,self_attn.k_proj,0.0037838577,,0.016 | |
| 55,self_attn.v_proj,0.0037838577,,0.018 | |
| 55,self_attn.o_proj,not applicable,,0.022 | |
| 55,mlp.gate_proj,0.0024683767,,0.034 | |
| 55,mlp.up_proj,0.0024683767,,0.043 | |
| 55,mlp.down_proj,0.0018751933,,0.053 | |
| 56,linear_attn.in_proj_qkv,0.0007844024,,0.006 | |
| 56,linear_attn.in_proj_z,0.0007844024,,0.014 | |
| 56,linear_attn.out_proj,not applicable,,0.018 | |
| 56,mlp.gate_proj,0.0023013421,,0.028 | |
| 56,mlp.up_proj,0.0023013421,,0.037 | |
| 56,mlp.down_proj,0.0016854609,,0.047 | |
| 57,linear_attn.in_proj_qkv,0.0005686481,,0.006 | |
| 57,linear_attn.in_proj_z,0.0005686481,,0.013 | |
| 57,linear_attn.out_proj,not applicable,,0.017 | |
| 57,mlp.gate_proj,0.0023689751,,0.026 | |
| 57,mlp.up_proj,0.0023689751,,0.036 | |
| 57,mlp.down_proj,0.0016684245,,0.046 | |
| 58,linear_attn.in_proj_qkv,0.0006748634,,0.006 | |
| 58,linear_attn.in_proj_z,0.0006748634,,0.015 | |
| 58,linear_attn.out_proj,not applicable,,0.020 | |
| 58,mlp.gate_proj,0.0032920326,,0.030 | |
| 58,mlp.up_proj,0.0032920326,,0.039 | |
| 58,mlp.down_proj,0.0021778252,,0.048 | |
| 59,self_attn.q_proj,0.0099577962,,0.009 | |
| 59,self_attn.k_proj,0.0099577962,,0.015 | |
| 59,self_attn.v_proj,0.0099577962,,0.016 | |
| 59,self_attn.o_proj,not applicable,,0.020 | |
| 59,mlp.gate_proj,0.0040843336,,0.030 | |
| 59,mlp.up_proj,0.0040843336,,0.039 | |
| 59,mlp.down_proj,0.0031100676,,0.049 | |
| 60,linear_attn.in_proj_qkv,0.0012042811,,0.009 | |
| 60,linear_attn.in_proj_z,0.0012042811,,0.017 | |
| 60,linear_attn.out_proj,not applicable,,0.021 | |
| 60,mlp.gate_proj,0.0043294880,,0.031 | |
| 60,mlp.up_proj,0.0043294880,,0.042 | |
| 60,mlp.down_proj,0.0036994821,,0.051 | |
| 61,linear_attn.in_proj_qkv,0.0013711013,,0.006 | |
| 61,linear_attn.in_proj_z,0.0013711013,,0.014 | |
| 61,linear_attn.out_proj,not applicable,,0.018 | |
| 61,mlp.gate_proj,0.0055645517,,0.028 | |
| 61,mlp.up_proj,0.0055645517,,0.037 | |
| 61,mlp.down_proj,0.0049028226,,0.046 | |
| 62,linear_attn.in_proj_qkv,0.0044048463,,0.007 | |
| 62,linear_attn.in_proj_z,0.0044048463,,0.012 | |
| 62,linear_attn.out_proj,not applicable,,0.016 | |
| 62,mlp.gate_proj,0.0093146329,,0.026 | |
| 62,mlp.up_proj,0.0093146329,,0.036 | |
| 62,mlp.down_proj,0.0091457848,,0.045 | |
| 63,self_attn.q_proj,0.0142782208,,0.012 | |
| 63,self_attn.k_proj,0.0142782208,,0.018 | |
| 63,self_attn.v_proj,0.0142782208,,0.020 | |
| 63,self_attn.o_proj,not applicable,,0.024 | |
| 63,mlp.gate_proj,0.0228790123,,0.034 | |
| 63,mlp.up_proj,0.0228790123,,0.043 | |
| 63,mlp.down_proj,0.0271780144,,0.052 | |