Download quantization_config.json from LeaderboardModel1/DeepSeek-R1-Distill-Qwen-1.5B-AutoRound-NVFP4-Tuning: direct link, hf CLI and curl.
- Browser
- Download file 17.1 kB
-
https://huggingface.co/LeaderboardModel1/DeepSeek-R1-Distill-Qwen-1.5B-AutoRound-NVFP4-Tuning/resolve/main/quantization_config.json
- Command line
-
hf download hf://LeaderboardModel1/DeepSeek-R1-Distill-Qwen-1.5B-AutoRound-NVFP4-Tuning/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/LeaderboardModel1/DeepSeek-R1-Distill-Qwen-1.5B-AutoRound-NVFP4-Tuning/resolve/main/quantization_config.json
17.1 kB
| { | |
| "bits": 4, | |
| "act_bits": 4, | |
| "data_type": "nv_fp", | |
| "act_data_type": "nv_fp4_with_static_gs", | |
| "group_size": 16, | |
| "act_group_size": 16, | |
| "sym": true, | |
| "act_sym": true, | |
| "act_dynamic": true, | |
| "low_gpu_mem_usage": true, | |
| "autoround_version": "0.13.1", | |
| "block_name_to_quantize": "model.layers", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:llm_compressor", | |
| "extra_config": { | |
| "model.layers.0.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.0.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.0.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.1.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.1.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.1.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.2.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.2.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.2.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.2.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.3.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.3.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.3.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.3.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.4.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.4.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.4.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.4.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.5.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.5.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.5.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.5.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.6.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.6.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.6.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.6.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.7.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.7.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.7.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.7.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.8.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.8.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.8.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.8.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.9.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.9.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.9.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.9.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.10.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.10.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.10.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.10.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.11.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.11.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.11.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.11.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.12.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.12.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.12.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.12.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.13.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.13.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.13.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.13.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.14.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.14.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.14.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.14.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.15.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.15.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.15.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.15.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.16.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.16.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.16.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.16.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.17.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.17.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.17.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.17.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.18.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.18.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.18.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.18.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.19.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.19.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.19.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.19.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.20.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.20.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.20.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.20.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.21.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.21.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.21.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.21.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.22.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.22.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.22.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.22.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.23.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.23.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.23.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.23.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.24.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.24.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.24.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.24.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.25.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.25.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.25.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.25.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.26.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.26.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.26.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.26.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.27.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.27.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.27.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| "model.layers.27.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| }, | |
| ".*self_attn.*": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| } | |
| } | |
| } |