Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
4-bit precision
gptq
Instructions to use wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1") model = AutoModelForCausalLM.from_pretrained("wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1
- SGLang
How to use wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1 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 "wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1" \ --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": "wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1" \ --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": "wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1 with Docker Model Runner:
docker model run hf.co/wolfofbackstreet/Qwen2.5-14B-Instruct-abliterated-SFT-int4-qptq-v1
| layer,module,loss,samples,damp,time | |
| 0,self_attn.k_proj,0.0000003350,0.01000,5.202 | |
| 0,self_attn.v_proj,0.0000000692,0.01000,1.844 | |
| 0,self_attn.q_proj,0.0000009049,0.01000,1.880 | |
| 0,self_attn.o_proj,0.0000004881,0.01000,1.923 | |
| 0,mlp.up_proj,0.0000004013,0.01000,1.959 | |
| 0,mlp.gate_proj,0.0000004576,0.01000,1.880 | |
| 0,mlp.down_proj,0.0000007120,0.01000,5.411 | |
| 1,self_attn.k_proj,0.0000000157,0.01000,1.819 | |
| 1,self_attn.v_proj,0.0000000055,0.01000,1.832 | |
| 1,self_attn.q_proj,0.0000000621,0.01000,1.861 | |
| 1,self_attn.o_proj,0.0000000086,0.01000,1.840 | |
| 1,mlp.up_proj,0.0000019768,0.01000,1.867 | |
| 1,mlp.gate_proj,0.0000052508,0.01000,1.905 | |
| 1,mlp.down_proj,0.0000000906,0.01000,5.419 | |
| 2,self_attn.k_proj,0.0000000728,0.01000,1.801 | |
| 2,self_attn.v_proj,0.0000000179,0.01000,1.823 | |
| 2,self_attn.q_proj,0.0000002062,0.01000,1.857 | |
| 2,self_attn.o_proj,0.0000000600,0.01000,1.846 | |
| 2,mlp.up_proj,0.0000047215,0.01000,1.878 | |
| 2,mlp.gate_proj,0.0000087961,0.01000,1.884 | |
| 2,mlp.down_proj,0.0000003970,0.01000,5.470 | |
| 3,self_attn.k_proj,0.0000004315,0.01000,1.840 | |
| 3,self_attn.v_proj,0.0000000883,0.01000,1.846 | |
| 3,self_attn.q_proj,0.0000011442,0.01000,1.875 | |
| 3,self_attn.o_proj,0.0000001831,0.01000,1.874 | |
| 3,mlp.up_proj,0.0000056673,0.01000,1.891 | |
| 3,mlp.gate_proj,0.0000120343,0.01000,1.938 | |
| 3,mlp.down_proj,0.0000008319,0.01000,5.519 | |
| 4,self_attn.k_proj,0.0000004847,0.01000,1.817 | |
| 4,self_attn.v_proj,0.0000001414,0.01000,1.864 | |
| 4,self_attn.q_proj,0.0000013076,0.01000,1.889 | |
| 4,self_attn.o_proj,0.0000003564,0.01000,1.885 | |
| 4,mlp.up_proj,0.0000116558,0.01000,1.903 | |
| 4,mlp.gate_proj,0.0000216054,0.01000,1.914 | |
| 4,mlp.down_proj,0.0000376080,0.01000,5.485 | |
| 5,self_attn.k_proj,0.0000016138,0.01000,1.873 | |
| 5,self_attn.v_proj,0.0000006714,0.01000,1.828 | |
| 5,self_attn.q_proj,0.0000051503,0.01000,1.871 | |
| 5,self_attn.o_proj,0.0000004706,0.01000,1.873 | |
| 5,mlp.up_proj,0.0000194342,0.01000,1.907 | |
| 5,mlp.gate_proj,0.0000375556,0.01000,1.905 | |
| 5,mlp.down_proj,0.0000029815,0.01000,5.497 | |
| 6,self_attn.k_proj,0.0000017430,0.01000,1.835 | |
| 6,self_attn.v_proj,0.0000009271,0.01000,1.868 | |
| 6,self_attn.q_proj,0.0000059942,0.01000,1.927 | |
| 6,self_attn.o_proj,0.0000004706,0.01000,1.844 | |
| 6,mlp.up_proj,0.0000311088,0.01000,1.907 | |
| 6,mlp.gate_proj,0.0000573928,0.01000,1.919 | |
| 6,mlp.down_proj,0.0000024663,0.01000,5.438 | |
| 7,self_attn.k_proj,0.0000024727,0.01000,1.856 | |
| 7,self_attn.v_proj,0.0000014215,0.01000,1.894 | |
| 7,self_attn.q_proj,0.0000086396,0.01000,1.921 | |
| 7,self_attn.o_proj,0.0000004921,0.01000,1.848 | |
| 7,mlp.up_proj,0.0000396673,0.01000,1.899 | |
| 7,mlp.gate_proj,0.0000740013,0.01000,1.923 | |
| 7,mlp.down_proj,0.0000024540,0.01000,5.510 | |
| 8,self_attn.k_proj,0.0000026104,0.01000,1.836 | |
| 8,self_attn.v_proj,0.0000011290,0.01000,1.841 | |
| 8,self_attn.q_proj,0.0000086844,0.01000,1.921 | |
| 8,self_attn.o_proj,0.0000004635,0.01000,1.882 | |
| 8,mlp.up_proj,0.0000273321,0.01000,1.904 | |
| 8,mlp.gate_proj,0.0000487217,0.01000,1.885 | |
| 8,mlp.down_proj,0.0000032780,0.01000,5.488 | |
| 9,self_attn.k_proj,0.0000024555,0.01000,1.810 | |
| 9,self_attn.v_proj,0.0000013944,0.01000,1.808 | |
| 9,self_attn.q_proj,0.0000083456,0.01000,1.866 | |
| 9,self_attn.o_proj,0.0000008478,0.01000,1.901 | |
| 9,mlp.up_proj,0.0000198372,0.01000,1.903 | |
| 9,mlp.gate_proj,0.0000217467,0.01000,1.924 | |
| 9,mlp.down_proj,0.0000050624,0.01000,5.444 | |
| 10,self_attn.k_proj,0.0000036627,0.01000,1.845 | |
| 10,self_attn.v_proj,0.0000020550,0.01000,1.859 | |
| 10,self_attn.q_proj,0.0000129593,0.01000,1.900 | |
| 10,self_attn.o_proj,0.0000009408,0.01000,1.870 | |
| 10,mlp.up_proj,0.0000235137,0.01000,1.913 | |
| 10,mlp.gate_proj,0.0000257956,0.01000,1.920 | |
| 10,mlp.down_proj,0.0000065154,0.01000,5.454 | |
| 11,self_attn.k_proj,0.0000027024,0.01000,1.842 | |
| 11,self_attn.v_proj,0.0000013275,0.01000,1.844 | |
| 11,self_attn.q_proj,0.0000094814,0.01000,1.908 | |
| 11,self_attn.o_proj,0.0000012815,0.01000,1.872 | |
| 11,mlp.up_proj,0.0000271779,0.01000,1.901 | |
| 11,mlp.gate_proj,0.0000338901,0.01000,1.927 | |
| 11,mlp.down_proj,0.0000055404,0.01000,5.426 | |
| 12,self_attn.k_proj,0.0000033274,0.01000,1.831 | |
| 12,self_attn.v_proj,0.0000015312,0.01000,1.874 | |
| 12,self_attn.q_proj,0.0000118420,0.01000,1.907 | |
| 12,self_attn.o_proj,0.0000015095,0.01000,1.891 | |
| 12,mlp.up_proj,0.0000296626,0.01000,1.883 | |
| 12,mlp.gate_proj,0.0000315980,0.01000,1.937 | |
| 12,mlp.down_proj,0.0000069176,0.01000,5.536 | |
| 13,self_attn.k_proj,0.0000036609,0.01000,1.830 | |
| 13,self_attn.v_proj,0.0000019053,0.01000,1.845 | |
| 13,self_attn.q_proj,0.0000127553,0.01000,1.902 | |
| 13,self_attn.o_proj,0.0000017589,0.01000,1.860 | |
| 13,mlp.up_proj,0.0000342408,0.01000,1.899 | |
| 13,mlp.gate_proj,0.0000364835,0.01000,1.897 | |
| 13,mlp.down_proj,0.0000081275,0.01000,5.459 | |
| 14,self_attn.k_proj,0.0000046018,0.01000,1.815 | |
| 14,self_attn.v_proj,0.0000021502,0.01000,1.844 | |
| 14,self_attn.q_proj,0.0000157138,0.01000,1.904 | |
| 14,self_attn.o_proj,0.0000017424,0.01000,1.912 | |
| 14,mlp.up_proj,0.0000358295,0.01000,1.884 | |
| 14,mlp.gate_proj,0.0000379976,0.01000,1.943 | |
| 14,mlp.down_proj,0.0000087410,0.01000,5.456 | |
| 15,self_attn.k_proj,0.0000040231,0.01000,1.865 | |
| 15,self_attn.v_proj,0.0000025008,0.01000,1.870 | |
| 15,self_attn.q_proj,0.0000143978,0.01000,1.934 | |
| 15,self_attn.o_proj,0.0000023147,0.01000,1.850 | |
| 15,mlp.up_proj,0.0000377908,0.01000,1.898 | |
| 15,mlp.gate_proj,0.0000417327,0.01000,1.920 | |
| 15,mlp.down_proj,0.0000092967,0.01000,5.418 | |
| 16,self_attn.k_proj,0.0000041533,0.01000,1.806 | |
| 16,self_attn.v_proj,0.0000017251,0.01000,1.818 | |
| 16,self_attn.q_proj,0.0000130656,0.01000,1.870 | |
| 16,self_attn.o_proj,0.0000018848,0.01000,1.865 | |
| 16,mlp.up_proj,0.0000358902,0.01000,1.949 | |
| 16,mlp.gate_proj,0.0000365655,0.01000,1.919 | |
| 16,mlp.down_proj,0.0000091063,0.01000,5.451 | |
| 17,self_attn.k_proj,0.0000046163,0.01000,1.824 | |
| 17,self_attn.v_proj,0.0000020594,0.01000,1.879 | |
| 17,self_attn.q_proj,0.0000156211,0.01000,1.908 | |
| 17,self_attn.o_proj,0.0000020003,0.01000,1.883 | |
| 17,mlp.up_proj,0.0000353395,0.01000,1.901 | |
| 17,mlp.gate_proj,0.0000348718,0.01000,1.915 | |
| 17,mlp.down_proj,0.0000084139,0.01000,5.425 | |
| 18,self_attn.k_proj,0.0000045449,0.01000,1.816 | |
| 18,self_attn.v_proj,0.0000022801,0.01000,1.862 | |
| 18,self_attn.q_proj,0.0000156325,0.01000,1.879 | |
| 18,self_attn.o_proj,0.0000023047,0.01000,1.850 | |
| 18,mlp.up_proj,0.0000352713,0.01000,1.930 | |
| 18,mlp.gate_proj,0.0000337707,0.01000,1.913 | |
| 18,mlp.down_proj,0.0000082508,0.01000,5.463 | |
| 19,self_attn.k_proj,0.0000049839,0.01000,1.802 | |
| 19,self_attn.v_proj,0.0000023918,0.01000,1.822 | |
| 19,self_attn.q_proj,0.0000187696,0.01000,1.887 | |
| 19,self_attn.o_proj,0.0000017641,0.01000,1.856 | |
| 19,mlp.up_proj,0.0000367612,0.01000,1.884 | |
| 19,mlp.gate_proj,0.0000351620,0.01000,1.979 | |
| 19,mlp.down_proj,0.0000086590,0.01000,5.455 | |
| 20,self_attn.k_proj,0.0000052856,0.01000,1.818 | |
| 20,self_attn.v_proj,0.0000022273,0.01000,1.855 | |
| 20,self_attn.q_proj,0.0000181894,0.01000,1.910 | |
| 20,self_attn.o_proj,0.0000023892,0.01000,1.842 | |
| 20,mlp.up_proj,0.0000353381,0.01000,1.925 | |
| 20,mlp.gate_proj,0.0000321341,0.01000,1.901 | |
| 20,mlp.down_proj,0.0000088698,0.01000,5.486 | |
| 21,self_attn.k_proj,0.0000049114,0.01000,1.818 | |
| 21,self_attn.v_proj,0.0000022491,0.01000,1.867 | |
| 21,self_attn.q_proj,0.0000168365,0.01000,1.889 | |
| 21,self_attn.o_proj,0.0000023714,0.01000,1.891 | |
| 21,mlp.up_proj,0.0000358492,0.01000,1.910 | |
| 21,mlp.gate_proj,0.0000322838,0.01000,1.922 | |
| 21,mlp.down_proj,0.0000086986,0.01000,5.502 | |
| 22,self_attn.k_proj,0.0000055599,0.01000,1.813 | |
| 22,self_attn.v_proj,0.0000033529,0.01000,1.850 | |
| 22,self_attn.q_proj,0.0000191039,0.01000,1.906 | |
| 22,self_attn.o_proj,0.0000033293,0.01000,1.900 | |
| 22,mlp.up_proj,0.0000364756,0.01000,1.895 | |
| 22,mlp.gate_proj,0.0000326488,0.01000,1.947 | |
| 22,mlp.down_proj,0.0000102696,0.01000,5.434 | |
| 23,self_attn.k_proj,0.0000052745,0.01000,1.829 | |
| 23,self_attn.v_proj,0.0000034399,0.01000,1.849 | |
| 23,self_attn.q_proj,0.0000195092,0.01000,1.917 | |
| 23,self_attn.o_proj,0.0000034217,0.01000,1.874 | |
| 23,mlp.up_proj,0.0000372584,0.01000,1.904 | |
| 23,mlp.gate_proj,0.0000351880,0.01000,1.913 | |
| 23,mlp.down_proj,0.0000095941,0.01000,5.462 | |
| 24,self_attn.k_proj,0.0000070816,0.01000,1.826 | |
| 24,self_attn.v_proj,0.0000029287,0.01000,1.850 | |
| 24,self_attn.q_proj,0.0000222552,0.01000,1.906 | |
| 24,self_attn.o_proj,0.0000030957,0.01000,1.881 | |
| 24,mlp.up_proj,0.0000366670,0.01000,1.907 | |
| 24,mlp.gate_proj,0.0000342159,0.01000,1.918 | |
| 24,mlp.down_proj,0.0000087833,0.01000,5.487 | |
| 25,self_attn.k_proj,0.0000071748,0.01000,1.793 | |
| 25,self_attn.v_proj,0.0000040279,0.01000,1.866 | |
| 25,self_attn.q_proj,0.0000254012,0.01000,1.877 | |
| 25,self_attn.o_proj,0.0000029004,0.01000,1.855 | |
| 25,mlp.up_proj,0.0000371724,0.01000,1.902 | |
| 25,mlp.gate_proj,0.0000334913,0.01000,1.928 | |
| 25,mlp.down_proj,0.0000093829,0.01000,5.419 | |
| 26,self_attn.k_proj,0.0000061567,0.01000,1.864 | |
| 26,self_attn.v_proj,0.0000025934,0.01000,1.879 | |
| 26,self_attn.q_proj,0.0000216056,0.01000,1.870 | |
| 26,self_attn.o_proj,0.0000025900,0.01000,1.852 | |
| 26,mlp.up_proj,0.0000396599,0.01000,1.870 | |
| 26,mlp.gate_proj,0.0000344749,0.01000,1.920 | |
| 26,mlp.down_proj,0.0000104758,0.01000,5.500 | |
| 27,self_attn.k_proj,0.0000063704,0.01000,1.840 | |
| 27,self_attn.v_proj,0.0000031997,0.01000,1.873 | |
| 27,self_attn.q_proj,0.0000213023,0.01000,1.885 | |
| 27,self_attn.o_proj,0.0000035989,0.01000,1.872 | |
| 27,mlp.up_proj,0.0000421102,0.01000,1.870 | |
| 27,mlp.gate_proj,0.0000365721,0.01000,1.933 | |
| 27,mlp.down_proj,0.0000127756,0.01000,5.493 | |
| 28,self_attn.k_proj,0.0000054439,0.01000,1.822 | |
| 28,self_attn.v_proj,0.0000046776,0.01000,1.870 | |
| 28,self_attn.q_proj,0.0000218742,0.01000,1.896 | |
| 28,self_attn.o_proj,0.0000047852,0.01000,1.878 | |
| 28,mlp.up_proj,0.0000448014,0.01000,1.884 | |
| 28,mlp.gate_proj,0.0000385664,0.01000,1.935 | |
| 28,mlp.down_proj,0.0000152208,0.01000,5.477 | |
| 29,self_attn.k_proj,0.0000075766,0.01000,1.844 | |
| 29,self_attn.v_proj,0.0000049398,0.01000,1.850 | |
| 29,self_attn.q_proj,0.0000267214,0.01000,1.860 | |
| 29,self_attn.o_proj,0.0000047729,0.01000,1.869 | |
| 29,mlp.up_proj,0.0000480947,0.01000,1.876 | |
| 29,mlp.gate_proj,0.0000412646,0.01000,1.904 | |
| 29,mlp.down_proj,0.0000174578,0.01000,5.489 | |
| 30,self_attn.k_proj,0.0000066515,0.01000,1.876 | |
| 30,self_attn.v_proj,0.0000055583,0.01000,1.862 | |
| 30,self_attn.q_proj,0.0000255336,0.01000,1.916 | |
| 30,self_attn.o_proj,0.0000063217,0.01000,1.873 | |
| 30,mlp.up_proj,0.0000510543,0.01000,1.942 | |
| 30,mlp.gate_proj,0.0000439742,0.01000,1.899 | |
| 30,mlp.down_proj,0.0000198458,0.01000,5.516 | |
| 31,self_attn.k_proj,0.0000067489,0.01000,1.805 | |
| 31,self_attn.v_proj,0.0000053660,0.01000,1.846 | |
| 31,self_attn.q_proj,0.0000256080,0.01000,1.898 | |
| 31,self_attn.o_proj,0.0000057112,0.01000,1.847 | |
| 31,mlp.up_proj,0.0000573254,0.01000,1.918 | |
| 31,mlp.gate_proj,0.0000506116,0.01000,1.923 | |
| 31,mlp.down_proj,0.0000237780,0.01000,5.419 | |
| 32,self_attn.k_proj,0.0000075074,0.01000,1.877 | |
| 32,self_attn.v_proj,0.0000073561,0.01000,1.828 | |
| 32,self_attn.q_proj,0.0000286492,0.01000,1.903 | |
| 32,self_attn.o_proj,0.0000055623,0.01000,1.840 | |
| 32,mlp.up_proj,0.0000628114,0.01000,1.929 | |
| 32,mlp.gate_proj,0.0000567609,0.01000,1.925 | |
| 32,mlp.down_proj,0.0000284905,0.01000,5.494 | |
| 33,self_attn.k_proj,0.0000079448,0.01000,1.831 | |
| 33,self_attn.v_proj,0.0000073397,0.01000,1.908 | |
| 33,self_attn.q_proj,0.0000313780,0.01000,1.873 | |
| 33,self_attn.o_proj,0.0000070431,0.01000,1.858 | |
| 33,mlp.up_proj,0.0000754818,0.01000,1.896 | |
| 33,mlp.gate_proj,0.0000693134,0.01000,1.931 | |
| 33,mlp.down_proj,0.0000400507,0.01000,5.435 | |
| 34,self_attn.k_proj,0.0000082468,0.01000,1.829 | |
| 34,self_attn.v_proj,0.0000089507,0.01000,1.840 | |
| 34,self_attn.q_proj,0.0000341429,0.01000,1.885 | |
| 34,self_attn.o_proj,0.0000067946,0.01000,1.856 | |
| 34,mlp.up_proj,0.0000866891,0.01000,1.940 | |
| 34,mlp.gate_proj,0.0000821586,0.01000,1.923 | |
| 34,mlp.down_proj,0.0000472456,0.01000,5.538 | |
| 35,self_attn.k_proj,0.0000078382,0.01000,1.832 | |
| 35,self_attn.v_proj,0.0000078588,0.01000,1.848 | |
| 35,self_attn.q_proj,0.0000307812,0.01000,1.875 | |
| 35,self_attn.o_proj,0.0000096358,0.01000,1.873 | |
| 35,mlp.up_proj,0.0000986368,0.01000,1.889 | |
| 35,mlp.gate_proj,0.0000958261,0.01000,1.897 | |
| 35,mlp.down_proj,0.0000586797,0.01000,5.461 | |
| 36,self_attn.k_proj,0.0000090568,0.01000,1.851 | |
| 36,self_attn.v_proj,0.0000142979,0.01000,1.868 | |
| 36,self_attn.q_proj,0.0000390433,0.01000,1.896 | |
| 36,self_attn.o_proj,0.0000102853,0.01000,1.869 | |
| 36,mlp.up_proj,0.0001096456,0.01000,1.909 | |
| 36,mlp.gate_proj,0.0001053176,0.01000,1.931 | |
| 36,mlp.down_proj,0.0000745272,0.01000,5.534 | |
| 37,self_attn.k_proj,0.0000102921,0.01000,1.848 | |
| 37,self_attn.v_proj,0.0000139348,0.01000,1.863 | |
| 37,self_attn.q_proj,0.0000407019,0.01000,1.867 | |
| 37,self_attn.o_proj,0.0000112271,0.01000,1.845 | |
| 37,mlp.up_proj,0.0001245920,0.01000,1.890 | |
| 37,mlp.gate_proj,0.0001196814,0.01000,1.926 | |
| 37,mlp.down_proj,0.0000844956,0.01000,5.465 | |
| 38,self_attn.k_proj,0.0000101334,0.01000,1.887 | |
| 38,self_attn.v_proj,0.0000142629,0.01000,1.838 | |
| 38,self_attn.q_proj,0.0000413608,0.01000,1.892 | |
| 38,self_attn.o_proj,0.0000118424,0.01000,1.871 | |
| 38,mlp.up_proj,0.0001422509,0.01000,1.891 | |
| 38,mlp.gate_proj,0.0001351870,0.01000,1.920 | |
| 38,mlp.down_proj,0.0001002093,0.01000,5.430 | |
| 39,self_attn.k_proj,0.0000097654,0.01000,1.844 | |
| 39,self_attn.v_proj,0.0000155185,0.01000,1.888 | |
| 39,self_attn.q_proj,0.0000430024,0.01000,1.902 | |
| 39,self_attn.o_proj,0.0000163587,0.01000,1.880 | |
| 39,mlp.up_proj,0.0001594624,0.01000,1.870 | |
| 39,mlp.gate_proj,0.0001501404,0.01000,1.908 | |
| 39,mlp.down_proj,0.0001202485,0.01000,5.403 | |
| 40,self_attn.k_proj,0.0000111764,0.01000,1.822 | |
| 40,self_attn.v_proj,0.0000212190,0.01000,1.853 | |
| 40,self_attn.q_proj,0.0000477737,0.01000,1.863 | |
| 40,self_attn.o_proj,0.0000136626,0.01000,1.917 | |
| 40,mlp.up_proj,0.0001759011,0.01000,1.878 | |
| 40,mlp.gate_proj,0.0001646361,0.01000,1.906 | |
| 40,mlp.down_proj,0.0001423487,0.01000,5.481 | |
| 41,self_attn.k_proj,0.0000109057,0.01000,1.806 | |
| 41,self_attn.v_proj,0.0000228068,0.01000,1.848 | |
| 41,self_attn.q_proj,0.0000501279,0.01000,1.862 | |
| 41,self_attn.o_proj,0.0000127372,0.01000,1.870 | |
| 41,mlp.up_proj,0.0001938302,0.01000,1.888 | |
| 41,mlp.gate_proj,0.0001788286,0.01000,1.896 | |
| 41,mlp.down_proj,0.0001654244,0.01000,5.465 | |
| 42,self_attn.k_proj,0.0000115910,0.01000,1.799 | |
| 42,self_attn.v_proj,0.0000252338,0.01000,1.854 | |
| 42,self_attn.q_proj,0.0000493074,0.01000,1.908 | |
| 42,self_attn.o_proj,0.0000177375,0.01000,1.901 | |
| 42,mlp.up_proj,0.0002140352,0.01000,1.900 | |
| 42,mlp.gate_proj,0.0001944924,0.01000,1.989 | |
| 42,mlp.down_proj,0.0002010431,0.01000,5.499 | |
| 43,self_attn.k_proj,0.0000116256,0.01000,1.842 | |
| 43,self_attn.v_proj,0.0000351566,0.01000,1.835 | |
| 43,self_attn.q_proj,0.0000555932,0.01000,1.879 | |
| 43,self_attn.o_proj,0.0000282134,0.01000,1.866 | |
| 43,mlp.up_proj,0.0002366024,0.01000,1.882 | |
| 43,mlp.gate_proj,0.0002109463,0.01000,1.936 | |
| 43,mlp.down_proj,0.0002490418,0.01000,5.505 | |
| 44,self_attn.k_proj,0.0000108512,0.01000,1.829 | |
| 44,self_attn.v_proj,0.0000399018,0.01000,1.854 | |
| 44,self_attn.q_proj,0.0000559182,0.01000,1.900 | |
| 44,self_attn.o_proj,0.0000437074,0.01000,1.848 | |
| 44,mlp.up_proj,0.0002603794,0.01000,1.894 | |
| 44,mlp.gate_proj,0.0002283661,0.01000,1.903 | |
| 44,mlp.down_proj,0.0003450318,0.01000,5.481 | |
| 45,self_attn.k_proj,0.0000117965,0.01000,1.829 | |
| 45,self_attn.v_proj,0.0000507443,0.01000,1.858 | |
| 45,self_attn.q_proj,0.0000629527,0.01000,1.856 | |
| 45,self_attn.o_proj,0.0000391735,0.01000,1.854 | |
| 45,mlp.up_proj,0.0002976336,0.01000,1.929 | |
| 45,mlp.gate_proj,0.0002640414,0.01000,1.947 | |
| 45,mlp.down_proj,0.0004670114,0.01000,5.500 | |
| 46,self_attn.k_proj,0.0000111906,0.01000,1.809 | |
| 46,self_attn.v_proj,0.0000567153,0.01000,1.836 | |
| 46,self_attn.q_proj,0.0000597288,0.01000,1.873 | |
| 46,self_attn.o_proj,0.0000797118,0.01000,1.855 | |
| 46,mlp.up_proj,0.0003228503,0.01000,1.910 | |
| 46,mlp.gate_proj,0.0002994808,0.01000,1.913 | |
| 46,mlp.down_proj,0.0006974383,0.01000,5.564 | |
| 47,self_attn.k_proj,0.0000108451,0.01000,1.835 | |
| 47,self_attn.v_proj,0.0000401424,0.01000,1.841 | |
| 47,self_attn.q_proj,0.0000495196,0.01000,1.875 | |
| 47,self_attn.o_proj,0.0000524342,0.01000,1.869 | |
| 47,mlp.up_proj,0.0003880085,0.01000,1.914 | |
| 47,mlp.gate_proj,0.0003715118,0.01000,1.928 | |
| 47,mlp.down_proj,0.0010730910,0.01000,5.509 | |