{ "format": "MiniMax-H3-NF4", "version": 1, "quantized": { "proj_in": { "file": "proj_in.safetensors", "file_size": 279056, "in_features": 96, "out_features": 5376, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "audio_proj_in": { "file": "audio_proj_in.safetensors", "file_size": 101564, "in_features": 32, "out_features": 5376, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "context_embedder": { "file": "context_embedder.safetensors", "file_size": 14212202, "in_features": 5120, "out_features": 5376, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "time_embedder.linear_1": { "file": "time_embedder__linear_1.safetensors", "file_size": 722802, "in_features": 256, "out_features": 5376, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "time_embedder.linear_2": { "file": "time_embedder__linear_2.safetensors", "file_size": 7462132, "in_features": 5376, "out_features": 2688, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.0.attn.to_q": { "file": "token_refiner__refiner_blocks__0__attn__to_q.safetensors", "file_size": 19881155, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.0.attn.to_k": { "file": "token_refiner__refiner_blocks__0__attn__to_k.safetensors", "file_size": 19881155, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.0.attn.to_v": { "file": "token_refiner__refiner_blocks__0__attn__to_v.safetensors", "file_size": 19881155, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.0.attn.to_out.0": { "file": "token_refiner__refiner_blocks__0__attn__to_out__0.safetensors", "file_size": 19881155, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.0.ff.net.0.proj": { "file": "token_refiner__refiner_blocks__0__ff__net__0__proj.safetensors", "file_size": 79518475, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.0.ff.net.2": { "file": "token_refiner__refiner_blocks__0__ff__net__2.safetensors", "file_size": 39760268, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.1.attn.to_q": { "file": "token_refiner__refiner_blocks__1__attn__to_q.safetensors", "file_size": 19881155, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.1.attn.to_k": { "file": "token_refiner__refiner_blocks__1__attn__to_k.safetensors", "file_size": 19881154, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.1.attn.to_v": { "file": "token_refiner__refiner_blocks__1__attn__to_v.safetensors", "file_size": 19881153, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.1.attn.to_out.0": { "file": "token_refiner__refiner_blocks__1__attn__to_out__0.safetensors", "file_size": 19881155, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.1.ff.net.0.proj": { "file": "token_refiner__refiner_blocks__1__ff__net__0__proj.safetensors", "file_size": 79518476, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "token_refiner.refiner_blocks.1.ff.net.2": { "file": "token_refiner__refiner_blocks__1__ff__net__2.safetensors", "file_size": 39760267, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.0.attn.to_q": { "file": "transformer_blocks__0__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.0.attn.to_k": { "file": "transformer_blocks__0__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.0.attn.to_v": { "file": "transformer_blocks__0__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.0.attn.to_out.0": { "file": "transformer_blocks__0__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.0.ff.net.0.proj": { "file": "transformer_blocks__0__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.0.ff.net.2": { "file": "transformer_blocks__0__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.0.adaln_proj.linear": { "file": "transformer_blocks__0__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.1.attn.to_q": { "file": "transformer_blocks__1__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.1.attn.to_k": { "file": "transformer_blocks__1__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.1.attn.to_v": { "file": "transformer_blocks__1__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.1.attn.to_out.0": { "file": "transformer_blocks__1__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.1.ff.net.0.proj": { "file": "transformer_blocks__1__ff__net__0__proj.safetensors", "file_size": 79518466, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.1.ff.net.2": { "file": "transformer_blocks__1__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.1.adaln_proj.linear": { "file": "transformer_blocks__1__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.2.attn.to_q": { "file": "transformer_blocks__2__attn__to_q.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.2.attn.to_k": { "file": "transformer_blocks__2__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.2.attn.to_v": { "file": "transformer_blocks__2__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.2.attn.to_out.0": { "file": "transformer_blocks__2__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.2.ff.net.0.proj": { "file": "transformer_blocks__2__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.2.ff.net.2": { "file": "transformer_blocks__2__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.2.adaln_proj.linear": { "file": "transformer_blocks__2__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.3.attn.to_q": { "file": "transformer_blocks__3__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.3.attn.to_k": { "file": "transformer_blocks__3__attn__to_k.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.3.attn.to_v": { "file": "transformer_blocks__3__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.3.attn.to_out.0": { "file": "transformer_blocks__3__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.3.ff.net.0.proj": { "file": "transformer_blocks__3__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.3.ff.net.2": { "file": "transformer_blocks__3__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.3.adaln_proj.linear": { "file": "transformer_blocks__3__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.4.attn.to_q": { "file": "transformer_blocks__4__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.4.attn.to_k": { "file": "transformer_blocks__4__attn__to_k.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.4.attn.to_v": { "file": "transformer_blocks__4__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.4.attn.to_out.0": { "file": "transformer_blocks__4__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.4.ff.net.0.proj": { "file": "transformer_blocks__4__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.4.ff.net.2": { "file": "transformer_blocks__4__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.4.adaln_proj.linear": { "file": "transformer_blocks__4__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.5.attn.to_q": { "file": "transformer_blocks__5__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.5.attn.to_k": { "file": "transformer_blocks__5__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.5.attn.to_v": { "file": "transformer_blocks__5__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.5.attn.to_out.0": { "file": "transformer_blocks__5__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.5.ff.net.0.proj": { "file": "transformer_blocks__5__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.5.ff.net.2": { "file": "transformer_blocks__5__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.5.adaln_proj.linear": { "file": "transformer_blocks__5__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.6.attn.to_q": { "file": "transformer_blocks__6__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.6.attn.to_k": { "file": "transformer_blocks__6__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.6.attn.to_v": { "file": "transformer_blocks__6__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.6.attn.to_out.0": { "file": "transformer_blocks__6__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.6.ff.net.0.proj": { "file": "transformer_blocks__6__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.6.ff.net.2": { "file": "transformer_blocks__6__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.6.adaln_proj.linear": { "file": "transformer_blocks__6__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.7.attn.to_q": { "file": "transformer_blocks__7__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.7.attn.to_k": { "file": "transformer_blocks__7__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.7.attn.to_v": { "file": "transformer_blocks__7__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.7.attn.to_out.0": { "file": "transformer_blocks__7__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.7.ff.net.0.proj": { "file": "transformer_blocks__7__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.7.ff.net.2": { "file": "transformer_blocks__7__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.7.adaln_proj.linear": { "file": "transformer_blocks__7__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.8.attn.to_q": { "file": "transformer_blocks__8__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.8.attn.to_k": { "file": "transformer_blocks__8__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.8.attn.to_v": { "file": "transformer_blocks__8__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.8.attn.to_out.0": { "file": "transformer_blocks__8__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.8.ff.net.0.proj": { "file": "transformer_blocks__8__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.8.ff.net.2": { "file": "transformer_blocks__8__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.8.adaln_proj.linear": { "file": "transformer_blocks__8__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.9.attn.to_q": { "file": "transformer_blocks__9__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.9.attn.to_k": { "file": "transformer_blocks__9__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.9.attn.to_v": { "file": "transformer_blocks__9__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.9.attn.to_out.0": { "file": "transformer_blocks__9__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.9.ff.net.0.proj": { "file": "transformer_blocks__9__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.9.ff.net.2": { "file": "transformer_blocks__9__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.9.adaln_proj.linear": { "file": "transformer_blocks__9__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.10.attn.to_q": { "file": "transformer_blocks__10__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.10.attn.to_k": { "file": "transformer_blocks__10__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.10.attn.to_v": { "file": "transformer_blocks__10__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.10.attn.to_out.0": { "file": "transformer_blocks__10__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.10.ff.net.0.proj": { "file": "transformer_blocks__10__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.10.ff.net.2": { "file": "transformer_blocks__10__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.10.adaln_proj.linear": { "file": "transformer_blocks__10__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.11.attn.to_q": { "file": "transformer_blocks__11__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.11.attn.to_k": { "file": "transformer_blocks__11__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.11.attn.to_v": { "file": "transformer_blocks__11__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.11.attn.to_out.0": { "file": "transformer_blocks__11__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.11.ff.net.0.proj": { "file": "transformer_blocks__11__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.11.ff.net.2": { "file": "transformer_blocks__11__ff__net__2.safetensors", "file_size": 39760257, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.11.adaln_proj.linear": { "file": "transformer_blocks__11__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.12.attn.to_q": { "file": "transformer_blocks__12__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.12.attn.to_k": { "file": "transformer_blocks__12__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.12.attn.to_v": { "file": "transformer_blocks__12__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.12.attn.to_out.0": { "file": "transformer_blocks__12__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.12.ff.net.0.proj": { "file": "transformer_blocks__12__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.12.ff.net.2": { "file": "transformer_blocks__12__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.12.adaln_proj.linear": { "file": "transformer_blocks__12__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.13.attn.to_q": { "file": "transformer_blocks__13__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.13.attn.to_k": { "file": "transformer_blocks__13__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.13.attn.to_v": { "file": "transformer_blocks__13__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.13.attn.to_out.0": { "file": "transformer_blocks__13__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.13.ff.net.0.proj": { "file": "transformer_blocks__13__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.13.ff.net.2": { "file": "transformer_blocks__13__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.13.adaln_proj.linear": { "file": "transformer_blocks__13__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.14.attn.to_q": { "file": "transformer_blocks__14__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.14.attn.to_k": { "file": "transformer_blocks__14__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.14.attn.to_v": { "file": "transformer_blocks__14__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.14.attn.to_out.0": { "file": "transformer_blocks__14__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.14.ff.net.0.proj": { "file": "transformer_blocks__14__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.14.ff.net.2": { "file": "transformer_blocks__14__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.14.adaln_proj.linear": { "file": "transformer_blocks__14__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.15.attn.to_q": { "file": "transformer_blocks__15__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.15.attn.to_k": { "file": "transformer_blocks__15__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.15.attn.to_v": { "file": "transformer_blocks__15__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.15.attn.to_out.0": { "file": "transformer_blocks__15__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.15.ff.net.0.proj": { "file": "transformer_blocks__15__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.15.ff.net.2": { "file": "transformer_blocks__15__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.15.adaln_proj.linear": { "file": "transformer_blocks__15__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.16.attn.to_q": { "file": "transformer_blocks__16__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.16.attn.to_k": { "file": "transformer_blocks__16__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.16.attn.to_v": { "file": "transformer_blocks__16__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.16.attn.to_out.0": { "file": "transformer_blocks__16__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.16.ff.net.0.proj": { "file": "transformer_blocks__16__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.16.ff.net.2": { "file": "transformer_blocks__16__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.16.adaln_proj.linear": { "file": "transformer_blocks__16__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.17.attn.to_q": { "file": "transformer_blocks__17__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.17.attn.to_k": { "file": "transformer_blocks__17__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.17.attn.to_v": { "file": "transformer_blocks__17__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.17.attn.to_out.0": { "file": "transformer_blocks__17__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.17.ff.net.0.proj": { "file": "transformer_blocks__17__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.17.ff.net.2": { "file": "transformer_blocks__17__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.17.adaln_proj.linear": { "file": "transformer_blocks__17__adaln_proj__linear.safetensors", "file_size": 134379618, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.18.attn.to_q": { "file": "transformer_blocks__18__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.18.attn.to_k": { "file": "transformer_blocks__18__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.18.attn.to_v": { "file": "transformer_blocks__18__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.18.attn.to_out.0": { "file": "transformer_blocks__18__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.18.ff.net.0.proj": { "file": "transformer_blocks__18__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.18.ff.net.2": { "file": "transformer_blocks__18__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.18.adaln_proj.linear": { "file": "transformer_blocks__18__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.19.attn.to_q": { "file": "transformer_blocks__19__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.19.attn.to_k": { "file": "transformer_blocks__19__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.19.attn.to_v": { "file": "transformer_blocks__19__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.19.attn.to_out.0": { "file": "transformer_blocks__19__attn__to_out__0.safetensors", "file_size": 19881145, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.19.ff.net.0.proj": { "file": "transformer_blocks__19__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.19.ff.net.2": { "file": "transformer_blocks__19__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.19.adaln_proj.linear": { "file": "transformer_blocks__19__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.20.attn.to_q": { "file": "transformer_blocks__20__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.20.attn.to_k": { "file": "transformer_blocks__20__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.20.attn.to_v": { "file": "transformer_blocks__20__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.20.attn.to_out.0": { "file": "transformer_blocks__20__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.20.ff.net.0.proj": { "file": "transformer_blocks__20__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.20.ff.net.2": { "file": "transformer_blocks__20__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.20.adaln_proj.linear": { "file": "transformer_blocks__20__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.21.attn.to_q": { "file": "transformer_blocks__21__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.21.attn.to_k": { "file": "transformer_blocks__21__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.21.attn.to_v": { "file": "transformer_blocks__21__attn__to_v.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.21.attn.to_out.0": { "file": "transformer_blocks__21__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.21.ff.net.0.proj": { "file": "transformer_blocks__21__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.21.ff.net.2": { "file": "transformer_blocks__21__ff__net__2.safetensors", "file_size": 39760258, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.21.adaln_proj.linear": { "file": "transformer_blocks__21__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.22.attn.to_q": { "file": "transformer_blocks__22__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.22.attn.to_k": { "file": "transformer_blocks__22__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.22.attn.to_v": { "file": "transformer_blocks__22__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.22.attn.to_out.0": { "file": "transformer_blocks__22__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.22.ff.net.0.proj": { "file": "transformer_blocks__22__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.22.ff.net.2": { "file": "transformer_blocks__22__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.22.adaln_proj.linear": { "file": "transformer_blocks__22__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.23.attn.to_q": { "file": "transformer_blocks__23__attn__to_q.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.23.attn.to_k": { "file": "transformer_blocks__23__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.23.attn.to_v": { "file": "transformer_blocks__23__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.23.attn.to_out.0": { "file": "transformer_blocks__23__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.23.ff.net.0.proj": { "file": "transformer_blocks__23__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.23.ff.net.2": { "file": "transformer_blocks__23__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.23.adaln_proj.linear": { "file": "transformer_blocks__23__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.24.attn.to_q": { "file": "transformer_blocks__24__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.24.attn.to_k": { "file": "transformer_blocks__24__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.24.attn.to_v": { "file": "transformer_blocks__24__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.24.attn.to_out.0": { "file": "transformer_blocks__24__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.24.ff.net.0.proj": { "file": "transformer_blocks__24__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.24.ff.net.2": { "file": "transformer_blocks__24__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.24.adaln_proj.linear": { "file": "transformer_blocks__24__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.25.attn.to_q": { "file": "transformer_blocks__25__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.25.attn.to_k": { "file": "transformer_blocks__25__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.25.attn.to_v": { "file": "transformer_blocks__25__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.25.attn.to_out.0": { "file": "transformer_blocks__25__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.25.ff.net.0.proj": { "file": "transformer_blocks__25__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.25.ff.net.2": { "file": "transformer_blocks__25__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.25.adaln_proj.linear": { "file": "transformer_blocks__25__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.26.attn.to_q": { "file": "transformer_blocks__26__attn__to_q.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.26.attn.to_k": { "file": "transformer_blocks__26__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.26.attn.to_v": { "file": "transformer_blocks__26__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.26.attn.to_out.0": { "file": "transformer_blocks__26__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.26.ff.net.0.proj": { "file": "transformer_blocks__26__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.26.ff.net.2": { "file": "transformer_blocks__26__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.26.adaln_proj.linear": { "file": "transformer_blocks__26__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.27.attn.to_q": { "file": "transformer_blocks__27__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.27.attn.to_k": { "file": "transformer_blocks__27__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.27.attn.to_v": { "file": "transformer_blocks__27__attn__to_v.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.27.attn.to_out.0": { "file": "transformer_blocks__27__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.27.ff.net.0.proj": { "file": "transformer_blocks__27__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.27.ff.net.2": { "file": "transformer_blocks__27__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.27.adaln_proj.linear": { "file": "transformer_blocks__27__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.28.attn.to_q": { "file": "transformer_blocks__28__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.28.attn.to_k": { "file": "transformer_blocks__28__attn__to_k.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.28.attn.to_v": { "file": "transformer_blocks__28__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.28.attn.to_out.0": { "file": "transformer_blocks__28__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.28.ff.net.0.proj": { "file": "transformer_blocks__28__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.28.ff.net.2": { "file": "transformer_blocks__28__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.28.adaln_proj.linear": { "file": "transformer_blocks__28__adaln_proj__linear.safetensors", "file_size": 134379618, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.29.attn.to_q": { "file": "transformer_blocks__29__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.29.attn.to_k": { "file": "transformer_blocks__29__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.29.attn.to_v": { "file": "transformer_blocks__29__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.29.attn.to_out.0": { "file": "transformer_blocks__29__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.29.ff.net.0.proj": { "file": "transformer_blocks__29__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.29.ff.net.2": { "file": "transformer_blocks__29__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.29.adaln_proj.linear": { "file": "transformer_blocks__29__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.30.attn.to_q": { "file": "transformer_blocks__30__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.30.attn.to_k": { "file": "transformer_blocks__30__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.30.attn.to_v": { "file": "transformer_blocks__30__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.30.attn.to_out.0": { "file": "transformer_blocks__30__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.30.ff.net.0.proj": { "file": "transformer_blocks__30__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.30.ff.net.2": { "file": "transformer_blocks__30__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.30.adaln_proj.linear": { "file": "transformer_blocks__30__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.31.attn.to_q": { "file": "transformer_blocks__31__attn__to_q.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.31.attn.to_k": { "file": "transformer_blocks__31__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.31.attn.to_v": { "file": "transformer_blocks__31__attn__to_v.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.31.attn.to_out.0": { "file": "transformer_blocks__31__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.31.ff.net.0.proj": { "file": "transformer_blocks__31__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.31.ff.net.2": { "file": "transformer_blocks__31__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.31.adaln_proj.linear": { "file": "transformer_blocks__31__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.32.attn.to_q": { "file": "transformer_blocks__32__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.32.attn.to_k": { "file": "transformer_blocks__32__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.32.attn.to_v": { "file": "transformer_blocks__32__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.32.attn.to_out.0": { "file": "transformer_blocks__32__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.32.ff.net.0.proj": { "file": "transformer_blocks__32__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.32.ff.net.2": { "file": "transformer_blocks__32__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.32.adaln_proj.linear": { "file": "transformer_blocks__32__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.33.attn.to_q": { "file": "transformer_blocks__33__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.33.attn.to_k": { "file": "transformer_blocks__33__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.33.attn.to_v": { "file": "transformer_blocks__33__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.33.attn.to_out.0": { "file": "transformer_blocks__33__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.33.ff.net.0.proj": { "file": "transformer_blocks__33__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.33.ff.net.2": { "file": "transformer_blocks__33__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.33.adaln_proj.linear": { "file": "transformer_blocks__33__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.34.attn.to_q": { "file": "transformer_blocks__34__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.34.attn.to_k": { "file": "transformer_blocks__34__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.34.attn.to_v": { "file": "transformer_blocks__34__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.34.attn.to_out.0": { "file": "transformer_blocks__34__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.34.ff.net.0.proj": { "file": "transformer_blocks__34__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.34.ff.net.2": { "file": "transformer_blocks__34__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.34.adaln_proj.linear": { "file": "transformer_blocks__34__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.35.attn.to_q": { "file": "transformer_blocks__35__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.35.attn.to_k": { "file": "transformer_blocks__35__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.35.attn.to_v": { "file": "transformer_blocks__35__attn__to_v.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.35.attn.to_out.0": { "file": "transformer_blocks__35__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.35.ff.net.0.proj": { "file": "transformer_blocks__35__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.35.ff.net.2": { "file": "transformer_blocks__35__ff__net__2.safetensors", "file_size": 39760258, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.35.adaln_proj.linear": { "file": "transformer_blocks__35__adaln_proj__linear.safetensors", "file_size": 134379618, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.36.attn.to_q": { "file": "transformer_blocks__36__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.36.attn.to_k": { "file": "transformer_blocks__36__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.36.attn.to_v": { "file": "transformer_blocks__36__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.36.attn.to_out.0": { "file": "transformer_blocks__36__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.36.ff.net.0.proj": { "file": "transformer_blocks__36__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.36.ff.net.2": { "file": "transformer_blocks__36__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.36.adaln_proj.linear": { "file": "transformer_blocks__36__adaln_proj__linear.safetensors", "file_size": 134379618, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.37.attn.to_q": { "file": "transformer_blocks__37__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.37.attn.to_k": { "file": "transformer_blocks__37__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.37.attn.to_v": { "file": "transformer_blocks__37__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.37.attn.to_out.0": { "file": "transformer_blocks__37__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.37.ff.net.0.proj": { "file": "transformer_blocks__37__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.37.ff.net.2": { "file": "transformer_blocks__37__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.37.adaln_proj.linear": { "file": "transformer_blocks__37__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.38.attn.to_q": { "file": "transformer_blocks__38__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.38.attn.to_k": { "file": "transformer_blocks__38__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.38.attn.to_v": { "file": "transformer_blocks__38__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.38.attn.to_out.0": { "file": "transformer_blocks__38__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.38.ff.net.0.proj": { "file": "transformer_blocks__38__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.38.ff.net.2": { "file": "transformer_blocks__38__ff__net__2.safetensors", "file_size": 39760258, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.38.adaln_proj.linear": { "file": "transformer_blocks__38__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.39.attn.to_q": { "file": "transformer_blocks__39__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.39.attn.to_k": { "file": "transformer_blocks__39__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.39.attn.to_v": { "file": "transformer_blocks__39__attn__to_v.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.39.attn.to_out.0": { "file": "transformer_blocks__39__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.39.ff.net.0.proj": { "file": "transformer_blocks__39__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.39.ff.net.2": { "file": "transformer_blocks__39__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.39.adaln_proj.linear": { "file": "transformer_blocks__39__adaln_proj__linear.safetensors", "file_size": 134379618, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.40.attn.to_q": { "file": "transformer_blocks__40__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.40.attn.to_k": { "file": "transformer_blocks__40__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.40.attn.to_v": { "file": "transformer_blocks__40__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.40.attn.to_out.0": { "file": "transformer_blocks__40__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.40.ff.net.0.proj": { "file": "transformer_blocks__40__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.40.ff.net.2": { "file": "transformer_blocks__40__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.40.adaln_proj.linear": { "file": "transformer_blocks__40__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.41.attn.to_q": { "file": "transformer_blocks__41__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.41.attn.to_k": { "file": "transformer_blocks__41__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.41.attn.to_v": { "file": "transformer_blocks__41__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.41.attn.to_out.0": { "file": "transformer_blocks__41__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.41.ff.net.0.proj": { "file": "transformer_blocks__41__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.41.ff.net.2": { "file": "transformer_blocks__41__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.41.adaln_proj.linear": { "file": "transformer_blocks__41__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.42.attn.to_q": { "file": "transformer_blocks__42__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.42.attn.to_k": { "file": "transformer_blocks__42__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.42.attn.to_v": { "file": "transformer_blocks__42__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.42.attn.to_out.0": { "file": "transformer_blocks__42__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.42.ff.net.0.proj": { "file": "transformer_blocks__42__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.42.ff.net.2": { "file": "transformer_blocks__42__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.42.adaln_proj.linear": { "file": "transformer_blocks__42__adaln_proj__linear.safetensors", "file_size": 134379618, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.43.attn.to_q": { "file": "transformer_blocks__43__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.43.attn.to_k": { "file": "transformer_blocks__43__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.43.attn.to_v": { "file": "transformer_blocks__43__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.43.attn.to_out.0": { "file": "transformer_blocks__43__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.43.ff.net.0.proj": { "file": "transformer_blocks__43__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.43.ff.net.2": { "file": "transformer_blocks__43__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.43.adaln_proj.linear": { "file": "transformer_blocks__43__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.44.attn.to_q": { "file": "transformer_blocks__44__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.44.attn.to_k": { "file": "transformer_blocks__44__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.44.attn.to_v": { "file": "transformer_blocks__44__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.44.attn.to_out.0": { "file": "transformer_blocks__44__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.44.ff.net.0.proj": { "file": "transformer_blocks__44__ff__net__0__proj.safetensors", "file_size": 79518468, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.44.ff.net.2": { "file": "transformer_blocks__44__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.44.adaln_proj.linear": { "file": "transformer_blocks__44__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.45.attn.to_q": { "file": "transformer_blocks__45__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.45.attn.to_k": { "file": "transformer_blocks__45__attn__to_k.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.45.attn.to_v": { "file": "transformer_blocks__45__attn__to_v.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.45.attn.to_out.0": { "file": "transformer_blocks__45__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.45.ff.net.0.proj": { "file": "transformer_blocks__45__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.45.ff.net.2": { "file": "transformer_blocks__45__ff__net__2.safetensors", "file_size": 39760259, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.45.adaln_proj.linear": { "file": "transformer_blocks__45__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.46.attn.to_q": { "file": "transformer_blocks__46__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.46.attn.to_k": { "file": "transformer_blocks__46__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.46.attn.to_v": { "file": "transformer_blocks__46__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.46.attn.to_out.0": { "file": "transformer_blocks__46__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.46.ff.net.0.proj": { "file": "transformer_blocks__46__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.46.ff.net.2": { "file": "transformer_blocks__46__ff__net__2.safetensors", "file_size": 39760258, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.46.adaln_proj.linear": { "file": "transformer_blocks__46__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.47.attn.to_q": { "file": "transformer_blocks__47__attn__to_q.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.47.attn.to_k": { "file": "transformer_blocks__47__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.47.attn.to_v": { "file": "transformer_blocks__47__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.47.attn.to_out.0": { "file": "transformer_blocks__47__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.47.ff.net.0.proj": { "file": "transformer_blocks__47__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.47.ff.net.2": { "file": "transformer_blocks__47__ff__net__2.safetensors", "file_size": 39760258, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.47.adaln_proj.linear": { "file": "transformer_blocks__47__adaln_proj__linear.safetensors", "file_size": 134379618, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.48.attn.to_q": { "file": "transformer_blocks__48__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.48.attn.to_k": { "file": "transformer_blocks__48__attn__to_k.safetensors", "file_size": 19881145, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.48.attn.to_v": { "file": "transformer_blocks__48__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.48.attn.to_out.0": { "file": "transformer_blocks__48__attn__to_out__0.safetensors", "file_size": 19881146, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.48.ff.net.0.proj": { "file": "transformer_blocks__48__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.48.ff.net.2": { "file": "transformer_blocks__48__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.48.adaln_proj.linear": { "file": "transformer_blocks__48__adaln_proj__linear.safetensors", "file_size": 134379619, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.49.attn.to_q": { "file": "transformer_blocks__49__attn__to_q.safetensors", "file_size": 19881147, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.49.attn.to_k": { "file": "transformer_blocks__49__attn__to_k.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.49.attn.to_v": { "file": "transformer_blocks__49__attn__to_v.safetensors", "file_size": 19881146, "in_features": 5376, "out_features": 7168, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.49.attn.to_out.0": { "file": "transformer_blocks__49__attn__to_out__0.safetensors", "file_size": 19881147, "in_features": 7168, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.49.ff.net.0.proj": { "file": "transformer_blocks__49__ff__net__0__proj.safetensors", "file_size": 79518467, "in_features": 5376, "out_features": 28672, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.49.ff.net.2": { "file": "transformer_blocks__49__ff__net__2.safetensors", "file_size": 39760260, "in_features": 14336, "out_features": 5376, "bias": false, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "transformer_blocks.49.adaln_proj.linear": { "file": "transformer_blocks__49__adaln_proj__linear.safetensors", "file_size": 134379620, "in_features": 2688, "out_features": 96768, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "norm_out.linear": { "file": "norm_out__linear.safetensors", "file_size": 14932923, "in_features": 2688, "out_features": 10752, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "proj_out": { "file": "proj_out.safetensors", "file_size": 268488, "in_features": 5376, "out_features": 96, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" }, "audio_proj_out": { "file": "audio_proj_out.safetensors", "file_size": 90868, "in_features": 5376, "out_features": 32, "bias": true, "quant_type": "nf4", "compute_dtype": "bfloat16", "status": "saved" } }, "unquantized": {}, "other": { "norm_out.norm.weight": { "file": "other-norm_out__norm__weight.safetensors", "file_size": 10848, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.final_norm.weight": { "file": "other-token_refiner__final_norm__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.0.attn.norm_k.weight": { "file": "other-transformer_blocks__0__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.0.attn.norm_q.weight": { "file": "other-transformer_blocks__0__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.0.norm1.weight": { "file": "other-transformer_blocks__0__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.0.norm2.weight": { "file": "other-transformer_blocks__0__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.1.attn.norm_k.weight": { "file": "other-transformer_blocks__1__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.1.attn.norm_q.weight": { "file": "other-transformer_blocks__1__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.1.norm1.weight": { "file": "other-transformer_blocks__1__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.1.norm2.weight": { "file": "other-transformer_blocks__1__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.2.attn.norm_k.weight": { "file": "other-transformer_blocks__2__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.2.attn.norm_q.weight": { "file": "other-transformer_blocks__2__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.2.norm1.weight": { "file": "other-transformer_blocks__2__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.2.norm2.weight": { "file": "other-transformer_blocks__2__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.3.attn.norm_k.weight": { "file": "other-transformer_blocks__3__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.3.attn.norm_q.weight": { "file": "other-transformer_blocks__3__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.3.norm1.weight": { "file": "other-transformer_blocks__3__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.3.norm2.weight": { "file": "other-transformer_blocks__3__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.4.attn.norm_k.weight": { "file": "other-transformer_blocks__4__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.4.attn.norm_q.weight": { "file": "other-transformer_blocks__4__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.4.norm1.weight": { "file": "other-transformer_blocks__4__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.4.norm2.weight": { "file": "other-transformer_blocks__4__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.5.attn.norm_k.weight": { "file": "other-transformer_blocks__5__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.5.attn.norm_q.weight": { "file": "other-transformer_blocks__5__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.5.norm1.weight": { "file": "other-transformer_blocks__5__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.5.norm2.weight": { "file": "other-transformer_blocks__5__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.6.attn.norm_k.weight": { "file": "other-transformer_blocks__6__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.6.attn.norm_q.weight": { "file": "other-transformer_blocks__6__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.6.norm1.weight": { "file": "other-transformer_blocks__6__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.6.norm2.weight": { "file": "other-transformer_blocks__6__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.7.attn.norm_k.weight": { "file": "other-transformer_blocks__7__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.7.attn.norm_q.weight": { "file": "other-transformer_blocks__7__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.7.norm1.weight": { "file": "other-transformer_blocks__7__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.7.norm2.weight": { "file": "other-transformer_blocks__7__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.10.attn.norm_k.weight": { "file": "other-transformer_blocks__10__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.10.attn.norm_q.weight": { "file": "other-transformer_blocks__10__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.10.norm1.weight": { "file": "other-transformer_blocks__10__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.10.norm2.weight": { "file": "other-transformer_blocks__10__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.11.norm1.weight": { "file": "other-transformer_blocks__11__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.11.norm2.weight": { "file": "other-transformer_blocks__11__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.8.attn.norm_k.weight": { "file": "other-transformer_blocks__8__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.8.attn.norm_q.weight": { "file": "other-transformer_blocks__8__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.8.norm1.weight": { "file": "other-transformer_blocks__8__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.8.norm2.weight": { "file": "other-transformer_blocks__8__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.9.attn.norm_k.weight": { "file": "other-transformer_blocks__9__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.9.attn.norm_q.weight": { "file": "other-transformer_blocks__9__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.9.norm1.weight": { "file": "other-transformer_blocks__9__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.9.norm2.weight": { "file": "other-transformer_blocks__9__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.11.attn.norm_k.weight": { "file": "other-transformer_blocks__11__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.11.attn.norm_q.weight": { "file": "other-transformer_blocks__11__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.12.attn.norm_k.weight": { "file": "other-transformer_blocks__12__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.12.attn.norm_q.weight": { "file": "other-transformer_blocks__12__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.12.norm1.weight": { "file": "other-transformer_blocks__12__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.12.norm2.weight": { "file": "other-transformer_blocks__12__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.13.attn.norm_k.weight": { "file": "other-transformer_blocks__13__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.13.attn.norm_q.weight": { "file": "other-transformer_blocks__13__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.13.norm1.weight": { "file": "other-transformer_blocks__13__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.13.norm2.weight": { "file": "other-transformer_blocks__13__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.14.attn.norm_k.weight": { "file": "other-transformer_blocks__14__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.14.attn.norm_q.weight": { "file": "other-transformer_blocks__14__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.14.norm1.weight": { "file": "other-transformer_blocks__14__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.14.norm2.weight": { "file": "other-transformer_blocks__14__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.15.attn.norm_k.weight": { "file": "other-transformer_blocks__15__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.15.attn.norm_q.weight": { "file": "other-transformer_blocks__15__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.15.norm1.weight": { "file": "other-transformer_blocks__15__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.15.norm2.weight": { "file": "other-transformer_blocks__15__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.16.attn.norm_k.weight": { "file": "other-transformer_blocks__16__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.16.attn.norm_q.weight": { "file": "other-transformer_blocks__16__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.16.norm1.weight": { "file": "other-transformer_blocks__16__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.16.norm2.weight": { "file": "other-transformer_blocks__16__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.17.attn.norm_k.weight": { "file": "other-transformer_blocks__17__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.17.attn.norm_q.weight": { "file": "other-transformer_blocks__17__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.17.norm1.weight": { "file": "other-transformer_blocks__17__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.17.norm2.weight": { "file": "other-transformer_blocks__17__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.18.attn.norm_k.weight": { "file": "other-transformer_blocks__18__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.18.attn.norm_q.weight": { "file": "other-transformer_blocks__18__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.18.norm1.weight": { "file": "other-transformer_blocks__18__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.18.norm2.weight": { "file": "other-transformer_blocks__18__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.19.attn.norm_k.weight": { "file": "other-transformer_blocks__19__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.19.attn.norm_q.weight": { "file": "other-transformer_blocks__19__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.19.norm1.weight": { "file": "other-transformer_blocks__19__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.19.norm2.weight": { "file": "other-transformer_blocks__19__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.20.attn.norm_k.weight": { "file": "other-transformer_blocks__20__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.20.attn.norm_q.weight": { "file": "other-transformer_blocks__20__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.20.norm1.weight": { "file": "other-transformer_blocks__20__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.20.norm2.weight": { "file": "other-transformer_blocks__20__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.21.attn.norm_k.weight": { "file": "other-transformer_blocks__21__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.21.attn.norm_q.weight": { "file": "other-transformer_blocks__21__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.21.norm1.weight": { "file": "other-transformer_blocks__21__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.21.norm2.weight": { "file": "other-transformer_blocks__21__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.22.norm1.weight": { "file": "other-transformer_blocks__22__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.22.norm2.weight": { "file": "other-transformer_blocks__22__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.22.attn.norm_k.weight": { "file": "other-transformer_blocks__22__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.22.attn.norm_q.weight": { "file": "other-transformer_blocks__22__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.23.attn.norm_k.weight": { "file": "other-transformer_blocks__23__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.23.attn.norm_q.weight": { "file": "other-transformer_blocks__23__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.23.norm1.weight": { "file": "other-transformer_blocks__23__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.23.norm2.weight": { "file": "other-transformer_blocks__23__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.24.attn.norm_k.weight": { "file": "other-transformer_blocks__24__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.24.attn.norm_q.weight": { "file": "other-transformer_blocks__24__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.24.norm1.weight": { "file": "other-transformer_blocks__24__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.24.norm2.weight": { "file": "other-transformer_blocks__24__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.25.attn.norm_k.weight": { "file": "other-transformer_blocks__25__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.25.attn.norm_q.weight": { "file": "other-transformer_blocks__25__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.25.norm1.weight": { "file": "other-transformer_blocks__25__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.25.norm2.weight": { "file": "other-transformer_blocks__25__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.26.attn.norm_k.weight": { "file": "other-transformer_blocks__26__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.26.attn.norm_q.weight": { "file": "other-transformer_blocks__26__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.26.norm1.weight": { "file": "other-transformer_blocks__26__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.26.norm2.weight": { "file": "other-transformer_blocks__26__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.27.attn.norm_k.weight": { "file": "other-transformer_blocks__27__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.27.attn.norm_q.weight": { "file": "other-transformer_blocks__27__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.27.norm1.weight": { "file": "other-transformer_blocks__27__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.27.norm2.weight": { "file": "other-transformer_blocks__27__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.28.attn.norm_k.weight": { "file": "other-transformer_blocks__28__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.28.attn.norm_q.weight": { "file": "other-transformer_blocks__28__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.28.norm1.weight": { "file": "other-transformer_blocks__28__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.28.norm2.weight": { "file": "other-transformer_blocks__28__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.29.attn.norm_k.weight": { "file": "other-transformer_blocks__29__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.29.attn.norm_q.weight": { "file": "other-transformer_blocks__29__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.29.norm1.weight": { "file": "other-transformer_blocks__29__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.29.norm2.weight": { "file": "other-transformer_blocks__29__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.30.attn.norm_k.weight": { "file": "other-transformer_blocks__30__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.30.attn.norm_q.weight": { "file": "other-transformer_blocks__30__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.30.norm1.weight": { "file": "other-transformer_blocks__30__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.30.norm2.weight": { "file": "other-transformer_blocks__30__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.31.attn.norm_k.weight": { "file": "other-transformer_blocks__31__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.31.attn.norm_q.weight": { "file": "other-transformer_blocks__31__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.31.norm1.weight": { "file": "other-transformer_blocks__31__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.31.norm2.weight": { "file": "other-transformer_blocks__31__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.32.attn.norm_k.weight": { "file": "other-transformer_blocks__32__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.32.attn.norm_q.weight": { "file": "other-transformer_blocks__32__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.32.norm1.weight": { "file": "other-transformer_blocks__32__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.32.norm2.weight": { "file": "other-transformer_blocks__32__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.33.norm1.weight": { "file": "other-transformer_blocks__33__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.33.norm2.weight": { "file": "other-transformer_blocks__33__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.33.attn.norm_k.weight": { "file": "other-transformer_blocks__33__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.33.attn.norm_q.weight": { "file": "other-transformer_blocks__33__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.34.attn.norm_k.weight": { "file": "other-transformer_blocks__34__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.34.attn.norm_q.weight": { "file": "other-transformer_blocks__34__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.34.norm1.weight": { "file": "other-transformer_blocks__34__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.34.norm2.weight": { "file": "other-transformer_blocks__34__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.35.attn.norm_k.weight": { "file": "other-transformer_blocks__35__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.35.attn.norm_q.weight": { "file": "other-transformer_blocks__35__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.35.norm1.weight": { "file": "other-transformer_blocks__35__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.35.norm2.weight": { "file": "other-transformer_blocks__35__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.36.attn.norm_k.weight": { "file": "other-transformer_blocks__36__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.36.attn.norm_q.weight": { "file": "other-transformer_blocks__36__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.36.norm1.weight": { "file": "other-transformer_blocks__36__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.36.norm2.weight": { "file": "other-transformer_blocks__36__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.37.attn.norm_k.weight": { "file": "other-transformer_blocks__37__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.37.attn.norm_q.weight": { "file": "other-transformer_blocks__37__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.37.norm1.weight": { "file": "other-transformer_blocks__37__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.37.norm2.weight": { "file": "other-transformer_blocks__37__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.38.attn.norm_k.weight": { "file": "other-transformer_blocks__38__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.38.attn.norm_q.weight": { "file": "other-transformer_blocks__38__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.38.norm1.weight": { "file": "other-transformer_blocks__38__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.38.norm2.weight": { "file": "other-transformer_blocks__38__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.39.attn.norm_k.weight": { "file": "other-transformer_blocks__39__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.39.attn.norm_q.weight": { "file": "other-transformer_blocks__39__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.39.norm1.weight": { "file": "other-transformer_blocks__39__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.39.norm2.weight": { "file": "other-transformer_blocks__39__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.40.attn.norm_k.weight": { "file": "other-transformer_blocks__40__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.40.attn.norm_q.weight": { "file": "other-transformer_blocks__40__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.40.norm1.weight": { "file": "other-transformer_blocks__40__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.40.norm2.weight": { "file": "other-transformer_blocks__40__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.41.attn.norm_k.weight": { "file": "other-transformer_blocks__41__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.41.attn.norm_q.weight": { "file": "other-transformer_blocks__41__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.41.norm1.weight": { "file": "other-transformer_blocks__41__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.41.norm2.weight": { "file": "other-transformer_blocks__41__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.42.attn.norm_k.weight": { "file": "other-transformer_blocks__42__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.42.attn.norm_q.weight": { "file": "other-transformer_blocks__42__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.42.norm1.weight": { "file": "other-transformer_blocks__42__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.42.norm2.weight": { "file": "other-transformer_blocks__42__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.43.attn.norm_k.weight": { "file": "other-transformer_blocks__43__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.43.attn.norm_q.weight": { "file": "other-transformer_blocks__43__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.43.norm1.weight": { "file": "other-transformer_blocks__43__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.43.norm2.weight": { "file": "other-transformer_blocks__43__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.44.norm1.weight": { "file": "other-transformer_blocks__44__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.44.norm2.weight": { "file": "other-transformer_blocks__44__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.44.attn.norm_k.weight": { "file": "other-transformer_blocks__44__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.44.attn.norm_q.weight": { "file": "other-transformer_blocks__44__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.45.attn.norm_k.weight": { "file": "other-transformer_blocks__45__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.45.attn.norm_q.weight": { "file": "other-transformer_blocks__45__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.45.norm1.weight": { "file": "other-transformer_blocks__45__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.45.norm2.weight": { "file": "other-transformer_blocks__45__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.46.attn.norm_k.weight": { "file": "other-transformer_blocks__46__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.46.attn.norm_q.weight": { "file": "other-transformer_blocks__46__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.46.norm1.weight": { "file": "other-transformer_blocks__46__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.46.norm2.weight": { "file": "other-transformer_blocks__46__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.47.attn.norm_k.weight": { "file": "other-transformer_blocks__47__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.47.attn.norm_q.weight": { "file": "other-transformer_blocks__47__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.47.norm1.weight": { "file": "other-transformer_blocks__47__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.47.norm2.weight": { "file": "other-transformer_blocks__47__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.refiner_blocks.0.attn.norm_k.weight": { "file": "other-token_refiner__refiner_blocks__0__attn__norm_k__weight.safetensors", "file_size": 376, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.refiner_blocks.0.attn.norm_q.weight": { "file": "other-token_refiner__refiner_blocks__0__attn__norm_q__weight.safetensors", "file_size": 376, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.refiner_blocks.0.norm1.weight": { "file": "other-token_refiner__refiner_blocks__0__norm1__weight.safetensors", "file_size": 10864, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.refiner_blocks.0.norm2.weight": { "file": "other-token_refiner__refiner_blocks__0__norm2__weight.safetensors", "file_size": 10864, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.refiner_blocks.1.attn.norm_k.weight": { "file": "other-token_refiner__refiner_blocks__1__attn__norm_k__weight.safetensors", "file_size": 376, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.refiner_blocks.1.attn.norm_q.weight": { "file": "other-token_refiner__refiner_blocks__1__attn__norm_q__weight.safetensors", "file_size": 376, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.refiner_blocks.1.norm1.weight": { "file": "other-token_refiner__refiner_blocks__1__norm1__weight.safetensors", "file_size": 10864, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "token_refiner.refiner_blocks.1.norm2.weight": { "file": "other-token_refiner__refiner_blocks__1__norm2__weight.safetensors", "file_size": 10864, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.48.attn.norm_k.weight": { "file": "other-transformer_blocks__48__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.48.attn.norm_q.weight": { "file": "other-transformer_blocks__48__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.48.norm1.weight": { "file": "other-transformer_blocks__48__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.48.norm2.weight": { "file": "other-transformer_blocks__48__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.49.attn.norm_k.weight": { "file": "other-transformer_blocks__49__attn__norm_k__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.49.attn.norm_q.weight": { "file": "other-transformer_blocks__49__attn__norm_q__weight.safetensors", "file_size": 368, "shape": [ 128 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.49.norm1.weight": { "file": "other-transformer_blocks__49__norm1__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" }, "transformer_blocks.49.norm2.weight": { "file": "other-transformer_blocks__49__norm2__weight.safetensors", "file_size": 10856, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_raw" } }, "precision_critical": { "audio_proj_in.bias": { "file": "pc-audio_proj_in__bias.safetensors", "file_size": 21592, "shape": [ 5376 ], "dtype": "float32", "status": "saved_unquantized" }, "audio_proj_in.weight": { "file": "pc-audio_proj_in__weight.safetensors", "file_size": 688224, "shape": [ 5376, 32 ], "dtype": "float32", "status": "saved_unquantized" }, "audio_proj_out.bias": { "file": "pc-audio_proj_out__bias.safetensors", "file_size": 216, "shape": [ 32 ], "dtype": "float32", "status": "saved_unquantized" }, "audio_proj_out.weight": { "file": "pc-audio_proj_out__weight.safetensors", "file_size": 688224, "shape": [ 32, 5376 ], "dtype": "float32", "status": "saved_unquantized" }, "norm_out.linear.bias": { "file": "pc-norm_out__linear__bias.safetensors", "file_size": 21600, "shape": [ 10752 ], "dtype": "bfloat16", "status": "saved_unquantized" }, "norm_out.linear.weight": { "file": "pc-norm_out__linear__weight.safetensors", "file_size": 57802856, "shape": [ 10752, 2688 ], "dtype": "bfloat16", "status": "saved_unquantized" }, "norm_out.norm.weight": { "file": "pc-norm_out__norm__weight.safetensors", "file_size": 10848, "shape": [ 5376 ], "dtype": "bfloat16", "status": "saved_unquantized" }, "proj_in.bias": { "file": "pc-proj_in__bias.safetensors", "file_size": 21584, "shape": [ 5376 ], "dtype": "float32", "status": "saved_unquantized" }, "proj_in.weight": { "file": "pc-proj_in__weight.safetensors", "file_size": 2064472, "shape": [ 5376, 96 ], "dtype": "float32", "status": "saved_unquantized" }, "proj_out.bias": { "file": "pc-proj_out__bias.safetensors", "file_size": 464, "shape": [ 96 ], "dtype": "float32", "status": "saved_unquantized" }, "proj_out.weight": { "file": "pc-proj_out__weight.safetensors", "file_size": 2064472, "shape": [ 96, 5376 ], "dtype": "float32", "status": "saved_unquantized" }, "time_embedder.linear_1.bias": { "file": "pc-time_embedder__linear_1__bias.safetensors", "file_size": 21600, "shape": [ 5376 ], "dtype": "float32", "status": "saved_unquantized" }, "time_embedder.linear_1.weight": { "file": "pc-time_embedder__linear_1__weight.safetensors", "file_size": 5505128, "shape": [ 5376, 256 ], "dtype": "float32", "status": "saved_unquantized" }, "time_embedder.linear_2.bias": { "file": "pc-time_embedder__linear_2__bias.safetensors", "file_size": 10848, "shape": [ 2688 ], "dtype": "float32", "status": "saved_unquantized" }, "time_embedder.linear_2.weight": { "file": "pc-time_embedder__linear_2__weight.safetensors", "file_size": 57802864, "shape": [ 2688, 5376 ], "dtype": "float32", "status": "saved_unquantized" } } }