Download quant_map.json from sayedM/cohere-transcribe-arabic-cpu-friendly: direct link, hf CLI and curl.
- Browser
- Download file 86.2 kB
-
https://huggingface.co/sayedM/cohere-transcribe-arabic-cpu-friendly/resolve/main/quant_map.json
- Command line
-
hf download hf://sayedM/cohere-transcribe-arabic-cpu-friendly/quant_map.json
-
curl -L -o quant_map.json https://huggingface.co/sayedM/cohere-transcribe-arabic-cpu-friendly/resolve/main/quant_map.json
86.2 kB
| { | |
| "quantized_modules": { | |
| "proj_out": { | |
| "in_features": 1024, | |
| "out_features": 16384, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.subsampling.linear": { | |
| "in_features": 4096, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.0.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.0.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.0.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.0.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.0.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.0.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.0.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.0.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.0.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.1.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.1.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.1.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.1.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.1.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.1.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.1.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.1.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.1.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.2.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.2.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.2.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.2.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.2.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.2.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.2.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.2.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.2.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.3.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.3.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.3.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.3.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.3.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.3.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.3.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.3.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.3.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.4.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.4.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.4.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.4.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.4.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.4.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.4.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.4.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.4.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.5.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.5.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.5.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.5.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.5.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.5.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.5.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.5.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.5.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.6.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.6.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.6.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.6.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.6.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.6.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.6.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.6.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.6.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.7.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.7.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.7.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.7.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.7.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.7.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.7.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.7.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.7.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.8.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.8.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.8.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.8.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.8.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.8.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.8.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.8.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.8.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.9.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.9.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.9.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.9.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.9.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.9.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.9.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.9.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.9.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.10.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.10.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.10.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.10.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.10.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.10.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.10.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.10.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.10.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.11.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.11.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.11.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.11.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.11.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.11.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.11.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.11.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.11.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.12.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.12.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.12.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.12.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.12.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.12.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.12.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.12.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.12.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.13.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.13.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.13.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.13.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.13.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.13.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.13.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.13.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.13.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.14.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.14.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.14.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.14.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.14.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.14.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.14.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.14.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.14.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.15.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.15.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.15.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.15.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.15.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.15.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.15.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.15.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.15.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.16.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.16.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.16.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.16.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.16.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.16.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.16.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.16.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.16.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.17.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.17.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.17.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.17.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.17.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.17.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.17.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.17.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.17.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.18.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.18.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.18.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.18.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.18.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.18.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.18.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.18.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.18.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.19.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.19.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.19.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.19.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.19.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.19.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.19.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.19.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.19.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.20.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.20.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.20.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.20.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.20.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.20.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.20.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.20.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.20.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.21.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.21.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.21.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.21.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.21.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.21.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.21.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.21.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.21.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.22.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.22.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.22.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.22.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.22.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.22.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.22.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.22.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.22.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.23.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.23.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.23.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.23.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.23.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.23.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.23.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.23.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.23.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.24.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.24.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.24.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.24.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.24.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.24.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.24.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.24.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.24.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.25.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.25.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.25.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.25.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.25.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.25.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.25.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.25.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.25.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.26.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.26.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.26.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.26.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.26.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.26.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.26.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.26.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.26.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.27.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.27.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.27.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.27.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.27.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.27.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.27.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.27.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.27.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.28.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.28.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.28.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.28.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.28.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.28.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.28.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.28.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.28.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.29.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.29.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.29.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.29.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.29.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.29.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.29.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.29.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.29.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.30.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.30.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.30.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.30.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.30.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.30.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.30.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.30.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.30.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.31.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.31.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.31.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.31.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.31.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.31.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.31.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.31.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.31.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.32.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.32.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.32.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.32.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.32.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.32.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.32.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.32.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.32.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.33.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.33.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.33.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.33.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.33.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.33.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.33.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.33.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.33.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.34.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.34.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.34.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.34.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.34.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.34.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.34.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.34.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.34.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.35.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.35.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.35.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.35.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.35.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.35.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.35.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.35.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.35.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.36.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.36.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.36.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.36.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.36.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.36.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.36.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.36.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.36.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.37.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.37.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.37.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.37.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.37.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.37.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.37.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.37.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.37.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.38.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.38.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.38.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.38.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.38.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.38.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.38.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.38.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.38.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.39.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.39.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.39.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.39.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.39.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.39.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.39.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.39.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.39.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.40.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.40.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.40.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.40.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.40.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.40.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.40.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.40.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.40.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.41.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.41.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.41.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.41.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.41.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.41.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.41.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.41.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.41.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.42.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.42.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.42.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.42.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.42.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.42.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.42.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.42.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.42.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.43.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.43.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.43.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.43.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.43.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.43.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.43.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.43.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.43.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.44.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.44.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.44.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.44.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.44.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.44.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.44.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.44.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.44.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.45.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.45.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.45.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.45.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.45.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.45.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.45.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.45.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.45.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.46.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.46.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.46.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.46.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.46.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.46.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.46.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.46.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.46.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.47.feed_forward1.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.47.feed_forward1.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.47.self_attn.q_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.47.self_attn.k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.47.self_attn.v_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.47.self_attn.o_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.47.self_attn.relative_k_proj": { | |
| "in_features": 1280, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": false | |
| }, | |
| "model.encoder.layers.47.feed_forward2.linear1": { | |
| "in_features": 1280, | |
| "out_features": 5120, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.encoder.layers.47.feed_forward2.linear2": { | |
| "in_features": 5120, | |
| "out_features": 1280, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.proj": { | |
| "in_features": 1280, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.self_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.self_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.self_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.self_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.encoder_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.encoder_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.encoder_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.encoder_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.mlp.fc1": { | |
| "in_features": 1024, | |
| "out_features": 4096, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.0.mlp.fc2": { | |
| "in_features": 4096, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.self_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.self_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.self_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.self_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.encoder_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.encoder_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.encoder_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.encoder_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.mlp.fc1": { | |
| "in_features": 1024, | |
| "out_features": 4096, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.1.mlp.fc2": { | |
| "in_features": 4096, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.self_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.self_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.self_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.self_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.encoder_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.encoder_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.encoder_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.encoder_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.mlp.fc1": { | |
| "in_features": 1024, | |
| "out_features": 4096, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.2.mlp.fc2": { | |
| "in_features": 4096, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.self_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.self_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.self_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.self_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.encoder_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.encoder_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.encoder_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.encoder_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.mlp.fc1": { | |
| "in_features": 1024, | |
| "out_features": 4096, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.3.mlp.fc2": { | |
| "in_features": 4096, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.self_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.self_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.self_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.self_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.encoder_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.encoder_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.encoder_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.encoder_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.mlp.fc1": { | |
| "in_features": 1024, | |
| "out_features": 4096, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.4.mlp.fc2": { | |
| "in_features": 4096, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.self_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.self_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.self_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.self_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.encoder_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.encoder_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.encoder_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.encoder_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.mlp.fc1": { | |
| "in_features": 1024, | |
| "out_features": 4096, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.5.mlp.fc2": { | |
| "in_features": 4096, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.self_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.self_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.self_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.self_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.encoder_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.encoder_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.encoder_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.encoder_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.mlp.fc1": { | |
| "in_features": 1024, | |
| "out_features": 4096, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.6.mlp.fc2": { | |
| "in_features": 4096, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.self_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.self_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.self_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.self_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.encoder_attn.q_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.encoder_attn.k_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.encoder_attn.v_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.encoder_attn.o_proj": { | |
| "in_features": 1024, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.mlp.fc1": { | |
| "in_features": 1024, | |
| "out_features": 4096, | |
| "zero_point": 0, | |
| "has_bias": true | |
| }, | |
| "model.decoder.layers.7.mlp.fc2": { | |
| "in_features": 4096, | |
| "out_features": 1024, | |
| "zero_point": 0, | |
| "has_bias": true | |
| } | |
| }, | |
| "nonpersistent_buffers": [ | |
| "model.encoder.encode_positions.inv_freq" | |
| ], | |
| "scheme": { | |
| "weights": "per-tensor symmetric qint8, scale = float32(max|W|/127.5)", | |
| "activations": "per-tensor affine quint8, dynamic, reduce_range (7-bit) -- computed at runtime by the kernel", | |
| "untouched": "convolutions, layer norms and embeddings stay fp32" | |
| }, | |
| "torch_version": "2.14.0+cpu", | |
| "note": "activation scales are not stored: quantized::linear_dynamic derives them from each input tensor at call time." | |
| } |