Download hf_quant_config.json from trl-internal-testing/tiny-Inkling2LoopForConditionalGeneration: direct link, hf CLI and curl.
- Browser
- Download file 13.5 kB
-
https://huggingface.co/trl-internal-testing/tiny-Inkling2LoopForConditionalGeneration/resolve/main/hf_quant_config.json
- Command line
-
hf download hf://trl-internal-testing/tiny-Inkling2LoopForConditionalGeneration/hf_quant_config.json
-
curl -L -o hf_quant_config.json https://huggingface.co/trl-internal-testing/tiny-Inkling2LoopForConditionalGeneration/resolve/main/hf_quant_config.json
13.5 kB
| { | |
| "model": { | |
| "parameter_groups": [ | |
| { | |
| "compute_dtype": "float32", | |
| "output_dtype": "float32", | |
| "required_activation_quantization": null, | |
| "tensors": [ | |
| "model.llm.attn_res.attn_queries.0", | |
| "model.llm.attn_res.attn_queries.1", | |
| "model.llm.attn_res.attn_queries.2", | |
| "model.llm.attn_res.attn_queries.3", | |
| "model.llm.attn_res.attn_queries.4", | |
| "model.llm.attn_res.attn_queries.5", | |
| "model.llm.attn_res.attn_queries.6", | |
| "model.llm.attn_res.mlp_queries.0", | |
| "model.llm.attn_res.mlp_queries.1", | |
| "model.llm.attn_res.mlp_queries.2", | |
| "model.llm.attn_res.mlp_queries.3", | |
| "model.llm.attn_res.mlp_queries.4", | |
| "model.llm.attn_res.mlp_queries.5", | |
| "model.llm.attn_res.mlp_queries.6", | |
| "model.llm.attn_res.mlp_queries.7", | |
| "model.llm.attn_res.output_query", | |
| "model.llm.layers.0.mlp.gate.bias", | |
| "model.llm.layers.1.mlp.gate.bias", | |
| "model.llm.layers.2.mlp.gate.bias", | |
| "model.llm.layers.3.mlp.gate.bias", | |
| "model.llm.layers.4.mlp.gate.bias", | |
| "model.llm.layers.5.mlp.gate.bias", | |
| "model.llm.layers.6.mlp.gate.bias", | |
| "model.llm.layers.7.mlp.gate.bias", | |
| "model.llm.middle_cycle_cross_pass_kv_queries", | |
| "model.llm.middle_cycle_cross_pass_queries" | |
| ], | |
| "weight_block_shape": [], | |
| "weight_transform": "cast" | |
| }, | |
| { | |
| "compute_dtype": "bfloat16", | |
| "output_dtype": "bfloat16", | |
| "required_activation_quantization": null, | |
| "tensors": [ | |
| "model.llm.embed.weight", | |
| "model.llm.embed_norm.weight", | |
| "model.llm.layers.0.attn.attn_sink_proj.weight", | |
| "model.llm.layers.0.attn.gate_attn.weight", | |
| "model.llm.layers.0.attn.k_sconv.weight", | |
| "model.llm.layers.0.attn.q_l2_clip.scale", | |
| "model.llm.layers.0.attn.rel_l2_clip.scale", | |
| "model.llm.layers.0.attn.rel_logits_proj.proj", | |
| "model.llm.layers.0.attn.v_sconv.weight", | |
| "model.llm.layers.0.attn.wk_dv.weight", | |
| "model.llm.layers.0.attn.wo_ud.weight", | |
| "model.llm.layers.0.attn.wq_du.weight", | |
| "model.llm.layers.0.attn.wr_du.weight", | |
| "model.llm.layers.0.attn.wv_dv.weight", | |
| "model.llm.layers.0.attn_norm.weight", | |
| "model.llm.layers.0.attn_sconv.weight", | |
| "model.llm.layers.0.mlp.gate.weight", | |
| "model.llm.layers.0.mlp_norm.weight", | |
| "model.llm.layers.0.mlp_sconv.weight", | |
| "model.llm.layers.1.attn.attn_sink_proj.weight", | |
| "model.llm.layers.1.attn.gate_attn.weight", | |
| "model.llm.layers.1.attn.q_l2_clip.scale", | |
| "model.llm.layers.1.attn.rel_l2_clip.scale", | |
| "model.llm.layers.1.attn.rel_logits_proj.proj", | |
| "model.llm.layers.1.attn.wk_dv.weight", | |
| "model.llm.layers.1.attn.wo_ud.weight", | |
| "model.llm.layers.1.attn.wq_du.weight", | |
| "model.llm.layers.1.attn.wr_du.weight", | |
| "model.llm.layers.1.attn.wv_dv.weight", | |
| "model.llm.layers.1.attn_sconv.weight", | |
| "model.llm.layers.1.mlp.gate.weight", | |
| "model.llm.layers.1.mlp_norm.weight", | |
| "model.llm.layers.1.mlp_sconv.weight", | |
| "model.llm.layers.2.attn.attn_sink_proj.weight", | |
| "model.llm.layers.2.attn.gate_attn.weight", | |
| "model.llm.layers.2.attn.k_sconv.weight", | |
| "model.llm.layers.2.attn.q_l2_clip.scale", | |
| "model.llm.layers.2.attn.rel_l2_clip.scale", | |
| "model.llm.layers.2.attn.rel_logits_proj.proj", | |
| "model.llm.layers.2.attn.v_sconv.weight", | |
| "model.llm.layers.2.attn.wk_dv.weight", | |
| "model.llm.layers.2.attn.wo_ud.weight", | |
| "model.llm.layers.2.attn.wq_du.weight", | |
| "model.llm.layers.2.attn.wr_du.weight", | |
| "model.llm.layers.2.attn.wv_dv.weight", | |
| "model.llm.layers.2.attn_norm.weight", | |
| "model.llm.layers.2.attn_sconv.weight", | |
| "model.llm.layers.2.mlp.gate.weight", | |
| "model.llm.layers.2.mlp_norm.weight", | |
| "model.llm.layers.2.mlp_sconv.weight", | |
| "model.llm.layers.3.attn.attn_sink_proj.weight", | |
| "model.llm.layers.3.attn.gate_attn.weight", | |
| "model.llm.layers.3.attn.q_l2_clip.scale", | |
| "model.llm.layers.3.attn.rel_l2_clip.scale", | |
| "model.llm.layers.3.attn.rel_logits_proj.proj", | |
| "model.llm.layers.3.attn.wk_dv.weight", | |
| "model.llm.layers.3.attn.wo_ud.weight", | |
| "model.llm.layers.3.attn.wq_du.weight", | |
| "model.llm.layers.3.attn.wr_du.weight", | |
| "model.llm.layers.3.attn.wv_dv.weight", | |
| "model.llm.layers.3.attn_sconv.weight", | |
| "model.llm.layers.3.mlp.gate.weight", | |
| "model.llm.layers.3.mlp_norm.weight", | |
| "model.llm.layers.3.mlp_sconv.weight", | |
| "model.llm.layers.4.attn.attn_sink_proj.weight", | |
| "model.llm.layers.4.attn.gate_attn.weight", | |
| "model.llm.layers.4.attn.k_sconv.weight", | |
| "model.llm.layers.4.attn.q_l2_clip.scale", | |
| "model.llm.layers.4.attn.rel_l2_clip.scale", | |
| "model.llm.layers.4.attn.rel_logits_proj.proj", | |
| "model.llm.layers.4.attn.v_sconv.weight", | |
| "model.llm.layers.4.attn.wk_dv.weight", | |
| "model.llm.layers.4.attn.wo_ud.weight", | |
| "model.llm.layers.4.attn.wq_du.weight", | |
| "model.llm.layers.4.attn.wr_du.weight", | |
| "model.llm.layers.4.attn.wv_dv.weight", | |
| "model.llm.layers.4.attn_norm.weight", | |
| "model.llm.layers.4.attn_sconv.weight", | |
| "model.llm.layers.4.mlp.gate.weight", | |
| "model.llm.layers.4.mlp_norm.weight", | |
| "model.llm.layers.4.mlp_sconv.weight", | |
| "model.llm.layers.5.attn.attn_sink_proj.weight", | |
| "model.llm.layers.5.attn.gate_attn.weight", | |
| "model.llm.layers.5.attn.k_sconv.static_w", | |
| "model.llm.layers.5.attn.k_sconv.weight_proj", | |
| "model.llm.layers.5.attn.q_l2_clip.scale", | |
| "model.llm.layers.5.attn.rel_l2_clip.scale", | |
| "model.llm.layers.5.attn.rel_logits_proj.proj", | |
| "model.llm.layers.5.attn.v_sconv.static_w", | |
| "model.llm.layers.5.attn.v_sconv.weight_proj", | |
| "model.llm.layers.5.attn.wk_dv.weight", | |
| "model.llm.layers.5.attn.wo_ud.weight", | |
| "model.llm.layers.5.attn.wq_du.weight", | |
| "model.llm.layers.5.attn.wr_du.weight", | |
| "model.llm.layers.5.attn.wv_dv.weight", | |
| "model.llm.layers.5.attn_sconv.weight", | |
| "model.llm.layers.5.k_input_norm.weight", | |
| "model.llm.layers.5.mlp.gate.weight", | |
| "model.llm.layers.5.mlp_norm.weight", | |
| "model.llm.layers.5.mlp_sconv.weight", | |
| "model.llm.layers.5.q_input_norm.weight", | |
| "model.llm.layers.5.v_input_norm.weight", | |
| "model.llm.layers.6.attn.attn_sink_proj.weight", | |
| "model.llm.layers.6.attn.gate_attn.weight", | |
| "model.llm.layers.6.attn.k_sconv.weight", | |
| "model.llm.layers.6.attn.q_l2_clip.scale", | |
| "model.llm.layers.6.attn.rel_l2_clip.scale", | |
| "model.llm.layers.6.attn.rel_logits_proj.proj", | |
| "model.llm.layers.6.attn.v_sconv.weight", | |
| "model.llm.layers.6.attn.wk_dv.weight", | |
| "model.llm.layers.6.attn.wo_ud.weight", | |
| "model.llm.layers.6.attn.wq_du.weight", | |
| "model.llm.layers.6.attn.wr_du.weight", | |
| "model.llm.layers.6.attn.wv_dv.weight", | |
| "model.llm.layers.6.attn_norm.weight", | |
| "model.llm.layers.6.attn_sconv.weight", | |
| "model.llm.layers.6.mlp.gate.weight", | |
| "model.llm.layers.6.mlp_norm.weight", | |
| "model.llm.layers.6.mlp_sconv.weight", | |
| "model.llm.layers.7.attn.attn_sink_proj.weight", | |
| "model.llm.layers.7.attn.gate_attn.weight", | |
| "model.llm.layers.7.attn.q_l2_clip.scale", | |
| "model.llm.layers.7.attn.rel_l2_clip.scale", | |
| "model.llm.layers.7.attn.rel_logits_proj.proj", | |
| "model.llm.layers.7.attn.wk_dv.weight", | |
| "model.llm.layers.7.attn.wo_ud.weight", | |
| "model.llm.layers.7.attn.wq_du.weight", | |
| "model.llm.layers.7.attn.wr_du.weight", | |
| "model.llm.layers.7.attn.wv_dv.weight", | |
| "model.llm.layers.7.attn_sconv.weight", | |
| "model.llm.layers.7.mlp.gate.weight", | |
| "model.llm.layers.7.mlp_norm.weight", | |
| "model.llm.layers.7.mlp_sconv.weight", | |
| "model.llm.norm.weight", | |
| "model.visual.backbone.embeddings.class_embedding", | |
| "model.visual.backbone.embeddings.cls_position_embedding", | |
| "model.visual.backbone.embeddings.patch_embedding.weight", | |
| "model.visual.backbone.embeddings.position_embedding", | |
| "model.visual.backbone.layers.0.ln_1.bias", | |
| "model.visual.backbone.layers.0.ln_1.weight", | |
| "model.visual.backbone.layers.0.ln_2.bias", | |
| "model.visual.backbone.layers.0.ln_2.weight", | |
| "model.visual.backbone.layers.0.ls_1.gamma", | |
| "model.visual.backbone.layers.0.ls_2.gamma", | |
| "model.visual.backbone.layers.0.mlp.c_fc.bias", | |
| "model.visual.backbone.layers.0.mlp.c_fc.weight", | |
| "model.visual.backbone.layers.0.mlp.c_proj.bias", | |
| "model.visual.backbone.layers.0.mlp.c_proj.weight", | |
| "model.visual.backbone.layers.0.self_attn.k_proj.bias", | |
| "model.visual.backbone.layers.0.self_attn.k_proj.weight", | |
| "model.visual.backbone.layers.0.self_attn.out_proj.bias", | |
| "model.visual.backbone.layers.0.self_attn.out_proj.weight", | |
| "model.visual.backbone.layers.0.self_attn.q_proj.bias", | |
| "model.visual.backbone.layers.0.self_attn.q_proj.weight", | |
| "model.visual.backbone.layers.0.self_attn.v_proj.bias", | |
| "model.visual.backbone.layers.0.self_attn.v_proj.weight", | |
| "model.visual.backbone.layers.1.ln_1.bias", | |
| "model.visual.backbone.layers.1.ln_1.weight", | |
| "model.visual.backbone.layers.1.ln_2.bias", | |
| "model.visual.backbone.layers.1.ln_2.weight", | |
| "model.visual.backbone.layers.1.ls_1.gamma", | |
| "model.visual.backbone.layers.1.ls_2.gamma", | |
| "model.visual.backbone.layers.1.mlp.c_fc.bias", | |
| "model.visual.backbone.layers.1.mlp.c_fc.weight", | |
| "model.visual.backbone.layers.1.mlp.c_proj.bias", | |
| "model.visual.backbone.layers.1.mlp.c_proj.weight", | |
| "model.visual.backbone.layers.1.self_attn.k_proj.bias", | |
| "model.visual.backbone.layers.1.self_attn.k_proj.weight", | |
| "model.visual.backbone.layers.1.self_attn.out_proj.bias", | |
| "model.visual.backbone.layers.1.self_attn.out_proj.weight", | |
| "model.visual.backbone.layers.1.self_attn.q_proj.bias", | |
| "model.visual.backbone.layers.1.self_attn.q_proj.weight", | |
| "model.visual.backbone.layers.1.self_attn.v_proj.bias", | |
| "model.visual.backbone.layers.1.self_attn.v_proj.weight", | |
| "model.visual.backbone.ln_pre.bias", | |
| "model.visual.backbone.ln_pre.weight", | |
| "model.visual.proj_in.weight", | |
| "model.visual.proj_out.weight" | |
| ], | |
| "weight_block_shape": [], | |
| "weight_transform": "cast" | |
| }, | |
| { | |
| "compute_dtype": "nvfp4", | |
| "output_dtype": "uint8", | |
| "required_activation_quantization": { | |
| "amax_type": "per_token", | |
| "block_size": 16, | |
| "format": "nvfp4_e2m1", | |
| "rounding": "nearest", | |
| "scale_dtype": "float8_e4m3fn", | |
| "scale_selection_rule": "fouroversix_mae" | |
| }, | |
| "tensors": [ | |
| "model.llm.layers.0.mlp.experts.w13_weight", | |
| "model.llm.layers.0.mlp.experts.w2_weight", | |
| "model.llm.layers.1.mlp.experts.w13_weight", | |
| "model.llm.layers.1.mlp.experts.w2_weight", | |
| "model.llm.layers.2.mlp.experts.w13_weight", | |
| "model.llm.layers.2.mlp.experts.w2_weight", | |
| "model.llm.layers.3.mlp.experts.w13_weight", | |
| "model.llm.layers.3.mlp.experts.w2_weight", | |
| "model.llm.layers.4.mlp.experts.w13_weight", | |
| "model.llm.layers.4.mlp.experts.w2_weight", | |
| "model.llm.layers.5.mlp.experts.w13_weight", | |
| "model.llm.layers.5.mlp.experts.w2_weight" | |
| ], | |
| "weight_block_shape": [ | |
| 1, | |
| 16 | |
| ], | |
| "weight_scale_format": "amax_denominator", | |
| "weight_transform": "nvfp4_nearest" | |
| }, | |
| { | |
| "compute_dtype": "mxfp8", | |
| "output_dtype": "float8_e4m3fn", | |
| "required_activation_quantization": { | |
| "block_size": 32, | |
| "format": "mxfp8_e4m3", | |
| "rounding": "nearest", | |
| "scale_dtype": "ue8m0" | |
| }, | |
| "tensors": [ | |
| "model.llm.layers.6.mlp.experts.w13_weight", | |
| "model.llm.layers.6.mlp.experts.w2_weight", | |
| "model.llm.layers.7.mlp.experts.w13_weight", | |
| "model.llm.layers.7.mlp.experts.w2_weight" | |
| ], | |
| "weight_block_shape": [ | |
| 32, | |
| 32 | |
| ], | |
| "weight_transform": "mxfp8_nearest" | |
| }, | |
| { | |
| "compute_dtype": "bfloat16", | |
| "fwd_output_dtype": "float32", | |
| "output_dtype": "bfloat16", | |
| "required_activation_quantization": null, | |
| "tensors": [ | |
| "model.llm.unembed.weight" | |
| ], | |
| "weight_block_shape": [], | |
| "weight_transform": "cast" | |
| } | |
| ] | |
| }, | |
| "quant_method": "inkling2" | |
| } |