| { |
| "vision_model": "bfloat16", |
| "projector": "bfloat16", |
| "language_model.model.embed_tokens": "mxfp8", |
| "language_model.model.norm": "bfloat16", |
| "language_model.lm_head": "affine8", |
| "language_model.model.layers.*.input_layernorm": "bfloat16", |
| "language_model.model.layers.*.post_attention_layernorm": "bfloat16", |
| "language_model.model.layers.*.self_attn.q_proj": "mxfp8", |
| "language_model.model.layers.*.self_attn.k_proj": "mxfp8", |
| "language_model.model.layers.*.self_attn.v_proj": "mxfp8", |
| "language_model.model.layers.*.self_attn.o_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.gate_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.up_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.down_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.shared_experts.gate_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.shared_experts.up_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.shared_experts.down_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.switch_mlp.gate_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.switch_mlp.up_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.switch_mlp.down_proj": "mxfp8", |
| "language_model.model.layers.*.mlp.gate": "bfloat16", |
| "sam_model": "bfloat16", |
| "_generated_from": { |
| "source_model": "baidu/Unlimited-OCR", |
| "thresholds": { |
| "cer_delta": 0.02, |
| "digit_cer_delta": 0.02, |
| "table_score_degradation": 0.01 |
| }, |
| "decisions": { |
| "vision_encoder": { |
| "precision": "bfloat16", |
| "reasons": [ |
| "cer_delta=2.272233", |
| "digit_cer_delta=1.696454", |
| "table_score_degradation=1.000000", |
| "protected OCR-critical group" |
| ] |
| }, |
| "vision_projector": { |
| "precision": "bfloat16", |
| "reasons": [ |
| "protected unless all measured quality deltas are non-degrading" |
| ] |
| }, |
| "token_embeddings": { |
| "precision": "mxfp8", |
| "reasons": [ |
| "all measured quality deltas were non-degrading" |
| ] |
| }, |
| "attention_q_proj": { |
| "precision": "base-map", |
| "reasons": [ |
| "within thresholds" |
| ] |
| }, |
| "attention_k_proj": { |
| "precision": "base-map", |
| "reasons": [ |
| "within thresholds" |
| ] |
| }, |
| "attention_v_proj": { |
| "precision": "base-map", |
| "reasons": [ |
| "within thresholds" |
| ] |
| }, |
| "attention_o_proj": { |
| "precision": "base-map", |
| "reasons": [ |
| "within thresholds" |
| ] |
| }, |
| "dense_mlp": { |
| "precision": "base-map", |
| "reasons": [ |
| "within thresholds" |
| ] |
| }, |
| "shared_experts": { |
| "precision": "base-map", |
| "reasons": [ |
| "within thresholds" |
| ] |
| }, |
| "routed_experts": { |
| "precision": "base-map", |
| "reasons": [ |
| "within thresholds" |
| ] |
| }, |
| "lm_head": { |
| "precision": "affine8", |
| "reasons": [ |
| "selected by joint quality/throughput calibration: affine8-head" |
| ] |
| } |
| }, |
| "calibration": { |
| "selected": { |
| "label": "affine8-head", |
| "precision": "affine8" |
| }, |
| "selection_policy": "fastest candidate passing existing quality and throughput limits" |
| } |
| } |
| } |
|
|
