*.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text *.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text *.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text *.npy filter=lfs diff=lfs merge=lfs -text *.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text *.pickle filter=lfs diff=lfs merge=lfs -text *.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text *.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text *.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights filter=lfs diff=lfs merge=lfs -text triton_models/interactive filter=lfs diff=lfs merge=lfs -text triton_models/postprocessing filter=lfs diff=lfs merge=lfs -text triton_models/preprocessing filter=lfs diff=lfs merge=lfs -text triton_models/tokenizer filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/config.ini filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/tok_embeddings.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.2.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.23.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.28.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.9.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.29.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.8.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.19.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.31.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/output.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.4.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.30.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.15.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.25.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.27.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.12.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.13.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.1.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.3.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.10.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.24.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.0.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.16.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.7.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.14.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.6.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.11.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.17.attention_norm.weight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.18.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.20.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.21.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.22.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.26.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text triton_models/weights/layers.5.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text