unsubscribe's picture
new model
cc06cac
raw
history blame
58.2 kB
*.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.32.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.39.attention.wo.0.scales_zeros 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.17.feed_forward.w13.0.qweight 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.37.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.37.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.40.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.18.feed_forward.w13.0.qweight 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.44.feed_forward.w2.0.qweight 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.23.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.42.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.44.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.attention.w_qkv.0.scales_zeros 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.24.feed_forward.w2.0.scales_zeros 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.35.attention.wo.0.scales_zeros 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.5.attention.w_qkv.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.40.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.45.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.48.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.33.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.41.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.42.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.45.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.53.feed_forward.w13.0.qweight 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.16.attention_norm.weight 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.23.attention_norm.weight 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.44.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.ffn_norm.weight 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.14.attention.w_qkv.0.qweight 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.20.feed_forward.w13.0.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.28.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.54.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.56.feed_forward.w13.0.qweight 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.25.attention_norm.weight 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.30.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.46.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.54.feed_forward.w13.0.scales_zeros 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.34.feed_forward.w13.0.qweight 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.0.attention.w_qkv.0.qweight 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.48.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.48.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.48.feed_forward.w13.0.scales_zeros 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.27.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.36.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.49.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.54.feed_forward.w2.0.scales_zeros 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.18.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.41.attention.wo.0.scales_zeros 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.58.ffn_norm.weight 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.42.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.46.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.50.feed_forward.w2.0.scales_zeros 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.14.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.40.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.42.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.50.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.feed_forward.w2.0.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/layers.11.attention.w_qkv.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/norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.52.attention.w_qkv.0.qweight 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.23.feed_forward.w13.0.qweight 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.55.feed_forward.w13.0.scales_zeros 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.11.attention.wo.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.43.attention.wo.0.scales_zeros 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.7.feed_forward.w13.0.scales_zeros 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.21.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.32.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.39.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.44.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.52.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.feed_forward.w2.0.scales_zeros 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.28.attention.wo.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.7.feed_forward.w2.0.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.35.feed_forward.w13.0.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.45.attention.w_qkv.0.scales_zeros 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/tok_embeddings.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.32.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.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.55.attention.wo.0.scales_zeros 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.56.attention_norm.weight 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.39.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.48.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.52.attention_norm.weight 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.46.attention.wo.0.scales_zeros 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.29.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.53.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.feed_forward.w13.0.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.3.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.44.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.36.attention.w_qkv.0.scales_zeros 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.24.attention.w_qkv.0.qweight 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.35.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.53.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.attention.wo.0.scales_zeros 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.9.attention.w_qkv.0.scales_zeros 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.39.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.43.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.48.attention.w_qkv.0.qweight 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.57.attention_norm.weight 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.27.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.34.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.58.feed_forward.w13.0.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.46.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.53.attention.wo.0.qweight 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.22.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.23.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.41.attention.wo.0.qweight 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.8.feed_forward.w13.0.qweight 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.28.feed_forward.w13.0.qweight 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.43.attention.w_qkv.0.qweight 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.26.feed_forward.w2.0.scales_zeros 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.55.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.18.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.attention.wo.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.50.attention.wo.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.2.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.40.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.45.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.18.feed_forward.w2.0.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.40.attention.wo.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.27.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.attention.wo.0.qweight 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.41.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.34.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.44.attention.w_qkv.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.38.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.40.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.50.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.56.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.37.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.49.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.53.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.55.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.38.ffn_norm.weight 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.53.attention.wo.0.scales_zeros 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.26.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.33.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.attention.w_qkv.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.14.feed_forward.w13.0.qweight 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.36.ffn_norm.weight 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.20.feed_forward.w2.0.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.41.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.41.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.43.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.45.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.58.attention_norm.weight 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.20.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.38.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.41.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.49.attention.w_qkv.0.qweight 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.9.attention.wo.0.qweight 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.42.feed_forward.w2.0.scales_zeros 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.18.feed_forward.w2.0.scales_zeros 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.34.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.39.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.46.feed_forward.w13.0.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.3.attention.w_qkv.0.scales_zeros 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.22.attention.w_qkv.0.qweight 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.34.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.49.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.53.feed_forward.w2.0.scales_zeros 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
triton_models/weights/layers.0.feed_forward.w2.0.scales_zeros 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/layers.22.ffn_norm.weight 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.10.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.35.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.39.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.46.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.attention.wo.0.qweight 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.22.attention.wo.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.36.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.37.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.38.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.41.feed_forward.w13.0.qweight 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.13.attention.wo.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.33.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.36.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.56.attention.wo.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.15.attention_norm.weight 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.48.attention.wo.0.qweight 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.8.feed_forward.w2.0.scales_zeros 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.12.feed_forward.w2.0.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.38.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.37.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.49.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.55.attention.wo.0.qweight 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.40.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.43.feed_forward.w13.0.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.58.feed_forward.w2.0.qweight 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.15.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.56.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.42.attention_norm.weight 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.27.attention.w_qkv.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.28.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.55.feed_forward.w13.0.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.12.attention.wo.0.qweight 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.31.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.attention.wo.0.scales_zeros 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.27.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.0.attention.wo.0.scales_zeros 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.17.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.32.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.33.attention_norm.weight 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.1.feed_forward.w13.0.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.35.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.54.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.feed_forward.w13.0.scales_zeros 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.15.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.33.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.58.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.32.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.54.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.35.attention.w_qkv.0.qweight 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.28.feed_forward.w2.0.scales_zeros 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.56.feed_forward.w2.0.scales_zeros 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.19.attention.w_qkv.0.scales_zeros 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.31.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.attention_norm.weight 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.13.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.30.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.32.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.42.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.58.attention.wo.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.36.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.44.ffn_norm.weight 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.33.ffn_norm.weight 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.49.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.attention.w_qkv.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.11.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.33.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.36.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.43.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.43.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.45.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.50.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.53.attention.w_qkv.0.qweight 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.8.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.34.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.42.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.49.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.feed_forward.w13.0.scales_zeros 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.25.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.38.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.39.ffn_norm.weight 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.6.attention.w_qkv.0.scales_zeros 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/layers.24.attention.w_qkv.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.1.attention.wo.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.29.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.32.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.attention.wo.0.scales_zeros 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.29.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.attention.w_qkv.0.qweight 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.26.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.52.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.44.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.48.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.55.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.feed_forward.w13.0.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.2.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.35.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.36.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.55.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.30.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.42.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.46.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.50.attention.w_qkv.0.scales_zeros 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.37.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.feed_forward.w2.0.scales_zeros 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.14.ffn_norm.weight 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.37.attention.w_qkv.0.scales_zeros 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.58.attention.w_qkv.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.34.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.44.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.55.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.ffn_norm.weight 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.25.attention.wo.0.qweight 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.23.feed_forward.w2.0.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.30.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.35.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.49.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.feed_forward.w2.0.qweight 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.17.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.41.feed_forward.w2.0.scales_zeros 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.13.feed_forward.w13.0.qweight 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.15.feed_forward.w2.0.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.40.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.43.attention_norm.weight 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.54.attention_norm.weight 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.5.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.56.attention.w_qkv.0.qweight 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.36.attention.wo.0.qweight 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.26.attention.w_qkv.0.scales_zeros 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.31.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.33.attention.wo.0.qweight 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.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.55.attention.w_qkv.0.qweight 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.25.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.41.ffn_norm.weight 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.34.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.38.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.50.attention.wo.0.scales_zeros 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.0.attention_norm.weight 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.38.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.40.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.50.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.56.attention.wo.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.52.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.40.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.27.attention_norm.weight 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.36.feed_forward.w2.0.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.12.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.38.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.52.feed_forward.w2.0.qweight 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.16.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.31.attention.w_qkv.0.qweight 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.50.ffn_norm.weight 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.1.feed_forward.w2.0.qweight 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.52.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.53.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.54.attention.wo.0.qweight 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.46.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.51.attention.wo.0.scales_zeros 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.20.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.43.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.45.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.12.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.39.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.54.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.54.attention.w_qkv.0.qweight 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.19.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.feed_forward.w13.0.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.32.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.50.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.17.attention.w_qkv.0.scales_zeros 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.29.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.58.attention.w_qkv.0.qweight 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.49.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.52.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.56.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.58.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.w_qkv.0.scales_zeros 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.48.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.33.feed_forward.w2.0.qweight 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.22.feed_forward.w2.0.scales_zeros 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.44.feed_forward.w2.0.scales_zeros 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.52.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.ffn_norm.weight 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.24.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.52.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.58.feed_forward.w13.0.scales_zeros 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.feed_forward.w13.0.scales_zeros 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.2.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.39.feed_forward.w2.0.scales_zeros 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.20.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.34.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.42.attention.w_qkv.0.scales_zeros 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.1.feed_forward.w2.0.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.feed_forward.w13.0.qweight 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.35.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.37.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.37.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/output.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.11.attention.w_qkv.0.qweight 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.27.attention.wo.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.45.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.45.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.47.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.54.feed_forward.w13.0.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.5.attention.wo.0.scales_zeros 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.24.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.39.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.attention.w_qkv.0.scales_zeros 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.28.attention.w_qkv.0.qweight 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/layers.46.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.56.ffn_norm.weight 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.28.ffn_norm.weight 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.38.feed_forward.w2.0.qweight 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.1.attention.w_qkv.0.qweight 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.37.feed_forward.w13.0.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.43.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.49.feed_forward.w2.0.qweight 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.14.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.34.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.45.attention.wo.0.qweight 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.26.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.33.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.53.attention.w_qkv.0.scales_zeros 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.31.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.32.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.46.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.48.attention.w_qkv.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.35.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.57.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.59.feed_forward.w2.0.scales_zeros 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.17.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
triton_models/weights/layers.32.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text