Download hf_quant_config.json from burner22/numbat: direct link, hf CLI and curl.
- Browser
- Download file 915 Bytes
-
https://huggingface.co/burner22/numbat/resolve/main/hf_quant_config.json
- Command line
-
hf download hf://burner22/numbat/hf_quant_config.json
-
curl -L -o hf_quant_config.json https://huggingface.co/burner22/numbat/resolve/main/hf_quant_config.json
915 Bytes
| { | |
| "producer": { | |
| "name": "modelopt", | |
| "version": "0.47.0" | |
| }, | |
| "quantization": { | |
| "quant_algo": "NVFP4", | |
| "kv_cache_quant_algo": null, | |
| "exclude_modules": [ | |
| "lm_head", | |
| "model.embed_tokens", | |
| "model.norm", | |
| "model.layers.0.*", | |
| "model.layers.1.*", | |
| "model.layers.109.*", | |
| "model.layers.110.*", | |
| "model.layers.111.*", | |
| "model.layers.112.*", | |
| "model.layers.113.*", | |
| "model.layers.114.*", | |
| "model.layers.*.mlp.gate", | |
| "model.layers.*.self_attn.a_proj", | |
| "model.layers.*.self_attn.b_proj", | |
| "model.layers.*.self_attn.*conv1d", | |
| "model.layers.*.*layernorm", | |
| "model.layers.*.self_attn.*layernorm", | |
| "model.layers.*.self_attn.o_norm" | |
| ], | |
| "group_size": 16 | |
| } | |
| } |