alphatozeta commited on
Commit
46c012e
·
1 Parent(s): bbf0930

removed metal and original weights

Browse files
metal/model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:725b7f996b5a226d922f034a731aefc398652f670dcafc2efd78620509a0fef1
3
- size 13750886400
 
 
 
 
original/config.json DELETED
@@ -1 +0,0 @@
1
- {"num_hidden_layers": 24, "num_experts": 32, "experts_per_token": 4, "vocab_size": 201088, "hidden_size": 2880, "intermediate_size": 2880, "swiglu_limit": 7.0, "head_dim": 64, "num_attention_heads": 64, "num_key_value_heads": 8, "sliding_window": 128, "initial_context_length": 4096, "rope_theta": 150000, "rope_scaling_factor": 32.0, "rope_ntk_alpha": 1, "rope_ntk_beta": 32}
 
 
original/dtypes.json DELETED
@@ -1 +0,0 @@
1
- {"embedding.weight": "BF16", "block.0.attn.norm.scale": "BF16", "block.0.attn.qkv.weight": "BF16", "block.0.attn.qkv.bias": "BF16", "block.0.attn.sinks": "BF16", "block.0.attn.out.weight": "BF16", "block.0.attn.out.bias": "BF16", "block.0.mlp.norm.scale": "BF16", "block.0.mlp.gate.weight": "BF16", "block.0.mlp.gate.bias": "BF16", "block.0.mlp.mlp1_weight.blocks": "FP4", "block.0.mlp.mlp1_weight.scales": "UE8", "block.0.mlp.mlp1_bias": "BF16", "block.0.mlp.mlp2_weight.blocks": "FP4", "block.0.mlp.mlp2_weight.scales": "UE8", "block.0.mlp.mlp2_bias": "BF16", "block.1.attn.norm.scale": "BF16", "block.1.attn.qkv.weight": "BF16", "block.1.attn.qkv.bias": "BF16", "block.1.attn.sinks": "BF16", "block.1.attn.out.weight": "BF16", "block.1.attn.out.bias": "BF16", "block.1.mlp.norm.scale": "BF16", "block.1.mlp.gate.weight": "BF16", "block.1.mlp.gate.bias": "BF16", "block.1.mlp.mlp1_weight.blocks": "FP4", "block.1.mlp.mlp1_weight.scales": "UE8", "block.1.mlp.mlp1_bias": "BF16", "block.1.mlp.mlp2_weight.blocks": "FP4", "block.1.mlp.mlp2_weight.scales": "UE8", "block.1.mlp.mlp2_bias": "BF16", "block.2.attn.norm.scale": "BF16", "block.2.attn.qkv.weight": "BF16", "block.2.attn.qkv.bias": "BF16", "block.2.attn.sinks": "BF16", "block.2.attn.out.weight": "BF16", "block.2.attn.out.bias": "BF16", "block.2.mlp.norm.scale": "BF16", "block.2.mlp.gate.weight": "BF16", "block.2.mlp.gate.bias": "BF16", "block.2.mlp.mlp1_weight.blocks": "FP4", "block.2.mlp.mlp1_weight.scales": "UE8", "block.2.mlp.mlp1_bias": "BF16", "block.2.mlp.mlp2_weight.blocks": "FP4", "block.2.mlp.mlp2_weight.scales": "UE8", "block.2.mlp.mlp2_bias": "BF16", "block.3.attn.norm.scale": "BF16", "block.3.attn.qkv.weight": "BF16", "block.3.attn.qkv.bias": "BF16", "block.3.attn.sinks": "BF16", "block.3.attn.out.weight": "BF16", "block.3.attn.out.bias": "BF16", "block.3.mlp.norm.scale": "BF16", "block.3.mlp.gate.weight": "BF16", "block.3.mlp.gate.bias": "BF16", "block.3.mlp.mlp1_weight.blocks": "FP4", "block.3.mlp.mlp1_weight.scales": "UE8", "block.3.mlp.mlp1_bias": "BF16", "block.3.mlp.mlp2_weight.blocks": "FP4", "block.3.mlp.mlp2_weight.scales": "UE8", "block.3.mlp.mlp2_bias": "BF16", "block.4.attn.norm.scale": "BF16", "block.4.attn.qkv.weight": "BF16", "block.4.attn.qkv.bias": "BF16", "block.4.attn.sinks": "BF16", "block.4.attn.out.weight": "BF16", "block.4.attn.out.bias": "BF16", "block.4.mlp.norm.scale": "BF16", "block.4.mlp.gate.weight": "BF16", "block.4.mlp.gate.bias": "BF16", "block.4.mlp.mlp1_weight.blocks": "FP4", "block.4.mlp.mlp1_weight.scales": "UE8", "block.4.mlp.mlp1_bias": "BF16", "block.4.mlp.mlp2_weight.blocks": "FP4", "block.4.mlp.mlp2_weight.scales": "UE8", "block.4.mlp.mlp2_bias": "BF16", "block.5.attn.norm.scale": "BF16", "block.5.attn.qkv.weight": "BF16", "block.5.attn.qkv.bias": "BF16", "block.5.attn.sinks": "BF16", "block.5.attn.out.weight": "BF16", "block.5.attn.out.bias": "BF16", "block.5.mlp.norm.scale": "BF16", "block.5.mlp.gate.weight": "BF16", "block.5.mlp.gate.bias": "BF16", "block.5.mlp.mlp1_weight.blocks": "FP4", "block.5.mlp.mlp1_weight.scales": "UE8", "block.5.mlp.mlp1_bias": "BF16", "block.5.mlp.mlp2_weight.blocks": "FP4", "block.5.mlp.mlp2_weight.scales": "UE8", "block.5.mlp.mlp2_bias": "BF16", "block.6.attn.norm.scale": "BF16", "block.6.attn.qkv.weight": "BF16", "block.6.attn.qkv.bias": "BF16", "block.6.attn.sinks": "BF16", "block.6.attn.out.weight": "BF16", "block.6.attn.out.bias": "BF16", "block.6.mlp.norm.scale": "BF16", "block.6.mlp.gate.weight": "BF16", "block.6.mlp.gate.bias": "BF16", "block.6.mlp.mlp1_weight.blocks": "FP4", "block.6.mlp.mlp1_weight.scales": "UE8", "block.6.mlp.mlp1_bias": "BF16", "block.6.mlp.mlp2_weight.blocks": "FP4", "block.6.mlp.mlp2_weight.scales": "UE8", "block.6.mlp.mlp2_bias": "BF16", "block.7.attn.norm.scale": "BF16", "block.7.attn.qkv.weight": "BF16", "block.7.attn.qkv.bias": "BF16", "block.7.attn.sinks": "BF16", "block.7.attn.out.weight": "BF16", "block.7.attn.out.bias": "BF16", "block.7.mlp.norm.scale": "BF16", "block.7.mlp.gate.weight": "BF16", "block.7.mlp.gate.bias": "BF16", "block.7.mlp.mlp1_weight.blocks": "FP4", "block.7.mlp.mlp1_weight.scales": "UE8", "block.7.mlp.mlp1_bias": "BF16", "block.7.mlp.mlp2_weight.blocks": "FP4", "block.7.mlp.mlp2_weight.scales": "UE8", "block.7.mlp.mlp2_bias": "BF16", "block.8.attn.norm.scale": "BF16", "block.8.attn.qkv.weight": "BF16", "block.8.attn.qkv.bias": "BF16", "block.8.attn.sinks": "BF16", "block.8.attn.out.weight": "BF16", "block.8.attn.out.bias": "BF16", "block.8.mlp.norm.scale": "BF16", "block.8.mlp.gate.weight": "BF16", "block.8.mlp.gate.bias": "BF16", "block.8.mlp.mlp1_weight.blocks": "FP4", "block.8.mlp.mlp1_weight.scales": "UE8", "block.8.mlp.mlp1_bias": "BF16", "block.8.mlp.mlp2_weight.blocks": "FP4", "block.8.mlp.mlp2_weight.scales": "UE8", "block.8.mlp.mlp2_bias": "BF16", "block.9.attn.norm.scale": "BF16", "block.9.attn.qkv.weight": "BF16", "block.9.attn.qkv.bias": "BF16", "block.9.attn.sinks": "BF16", "block.9.attn.out.weight": "BF16", "block.9.attn.out.bias": "BF16", "block.9.mlp.norm.scale": "BF16", "block.9.mlp.gate.weight": "BF16", "block.9.mlp.gate.bias": "BF16", "block.9.mlp.mlp1_weight.blocks": "FP4", "block.9.mlp.mlp1_weight.scales": "UE8", "block.9.mlp.mlp1_bias": "BF16", "block.9.mlp.mlp2_weight.blocks": "FP4", "block.9.mlp.mlp2_weight.scales": "UE8", "block.9.mlp.mlp2_bias": "BF16", "block.10.attn.norm.scale": "BF16", "block.10.attn.qkv.weight": "BF16", "block.10.attn.qkv.bias": "BF16", "block.10.attn.sinks": "BF16", "block.10.attn.out.weight": "BF16", "block.10.attn.out.bias": "BF16", "block.10.mlp.norm.scale": "BF16", "block.10.mlp.gate.weight": "BF16", "block.10.mlp.gate.bias": "BF16", "block.10.mlp.mlp1_weight.blocks": "FP4", "block.10.mlp.mlp1_weight.scales": "UE8", "block.10.mlp.mlp1_bias": "BF16", "block.10.mlp.mlp2_weight.blocks": "FP4", "block.10.mlp.mlp2_weight.scales": "UE8", "block.10.mlp.mlp2_bias": "BF16", "block.11.attn.norm.scale": "BF16", "block.11.attn.qkv.weight": "BF16", "block.11.attn.qkv.bias": "BF16", "block.11.attn.sinks": "BF16", "block.11.attn.out.weight": "BF16", "block.11.attn.out.bias": "BF16", "block.11.mlp.norm.scale": "BF16", "block.11.mlp.gate.weight": "BF16", "block.11.mlp.gate.bias": "BF16", "block.11.mlp.mlp1_weight.blocks": "FP4", "block.11.mlp.mlp1_weight.scales": "UE8", "block.11.mlp.mlp1_bias": "BF16", "block.11.mlp.mlp2_weight.blocks": "FP4", "block.11.mlp.mlp2_weight.scales": "UE8", "block.11.mlp.mlp2_bias": "BF16", "block.12.attn.norm.scale": "BF16", "block.12.attn.qkv.weight": "BF16", "block.12.attn.qkv.bias": "BF16", "block.12.attn.sinks": "BF16", "block.12.attn.out.weight": "BF16", "block.12.attn.out.bias": "BF16", "block.12.mlp.norm.scale": "BF16", "block.12.mlp.gate.weight": "BF16", "block.12.mlp.gate.bias": "BF16", "block.12.mlp.mlp1_weight.blocks": "FP4", "block.12.mlp.mlp1_weight.scales": "UE8", "block.12.mlp.mlp1_bias": "BF16", "block.12.mlp.mlp2_weight.blocks": "FP4", "block.12.mlp.mlp2_weight.scales": "UE8", "block.12.mlp.mlp2_bias": "BF16", "block.13.attn.norm.scale": "BF16", "block.13.attn.qkv.weight": "BF16", "block.13.attn.qkv.bias": "BF16", "block.13.attn.sinks": "BF16", "block.13.attn.out.weight": "BF16", "block.13.attn.out.bias": "BF16", "block.13.mlp.norm.scale": "BF16", "block.13.mlp.gate.weight": "BF16", "block.13.mlp.gate.bias": "BF16", "block.13.mlp.mlp1_weight.blocks": "FP4", "block.13.mlp.mlp1_weight.scales": "UE8", "block.13.mlp.mlp1_bias": "BF16", "block.13.mlp.mlp2_weight.blocks": "FP4", "block.13.mlp.mlp2_weight.scales": "UE8", "block.13.mlp.mlp2_bias": "BF16", "block.14.attn.norm.scale": "BF16", "block.14.attn.qkv.weight": "BF16", "block.14.attn.qkv.bias": "BF16", "block.14.attn.sinks": "BF16", "block.14.attn.out.weight": "BF16", "block.14.attn.out.bias": "BF16", "block.14.mlp.norm.scale": "BF16", "block.14.mlp.gate.weight": "BF16", "block.14.mlp.gate.bias": "BF16", "block.14.mlp.mlp1_weight.blocks": "FP4", "block.14.mlp.mlp1_weight.scales": "UE8", "block.14.mlp.mlp1_bias": "BF16", "block.14.mlp.mlp2_weight.blocks": "FP4", "block.14.mlp.mlp2_weight.scales": "UE8", "block.14.mlp.mlp2_bias": "BF16", "block.15.attn.norm.scale": "BF16", "block.15.attn.qkv.weight": "BF16", "block.15.attn.qkv.bias": "BF16", "block.15.attn.sinks": "BF16", "block.15.attn.out.weight": "BF16", "block.15.attn.out.bias": "BF16", "block.15.mlp.norm.scale": "BF16", "block.15.mlp.gate.weight": "BF16", "block.15.mlp.gate.bias": "BF16", "block.15.mlp.mlp1_weight.blocks": "FP4", "block.15.mlp.mlp1_weight.scales": "UE8", "block.15.mlp.mlp1_bias": "BF16", "block.15.mlp.mlp2_weight.blocks": "FP4", "block.15.mlp.mlp2_weight.scales": "UE8", "block.15.mlp.mlp2_bias": "BF16", "block.16.attn.norm.scale": "BF16", "block.16.attn.qkv.weight": "BF16", "block.16.attn.qkv.bias": "BF16", "block.16.attn.sinks": "BF16", "block.16.attn.out.weight": "BF16", "block.16.attn.out.bias": "BF16", "block.16.mlp.norm.scale": "BF16", "block.16.mlp.gate.weight": "BF16", "block.16.mlp.gate.bias": "BF16", "block.16.mlp.mlp1_weight.blocks": "FP4", "block.16.mlp.mlp1_weight.scales": "UE8", "block.16.mlp.mlp1_bias": "BF16", "block.16.mlp.mlp2_weight.blocks": "FP4", "block.16.mlp.mlp2_weight.scales": "UE8", "block.16.mlp.mlp2_bias": "BF16", "block.17.attn.norm.scale": "BF16", "block.17.attn.qkv.weight": "BF16", "block.17.attn.qkv.bias": "BF16", "block.17.attn.sinks": "BF16", "block.17.attn.out.weight": "BF16", "block.17.attn.out.bias": "BF16", "block.17.mlp.norm.scale": "BF16", "block.17.mlp.gate.weight": "BF16", "block.17.mlp.gate.bias": "BF16", "block.17.mlp.mlp1_weight.blocks": "FP4", "block.17.mlp.mlp1_weight.scales": "UE8", "block.17.mlp.mlp1_bias": "BF16", "block.17.mlp.mlp2_weight.blocks": "FP4", "block.17.mlp.mlp2_weight.scales": "UE8", "block.17.mlp.mlp2_bias": "BF16", "block.18.attn.norm.scale": "BF16", "block.18.attn.qkv.weight": "BF16", "block.18.attn.qkv.bias": "BF16", "block.18.attn.sinks": "BF16", "block.18.attn.out.weight": "BF16", "block.18.attn.out.bias": "BF16", "block.18.mlp.norm.scale": "BF16", "block.18.mlp.gate.weight": "BF16", "block.18.mlp.gate.bias": "BF16", "block.18.mlp.mlp1_weight.blocks": "FP4", "block.18.mlp.mlp1_weight.scales": "UE8", "block.18.mlp.mlp1_bias": "BF16", "block.18.mlp.mlp2_weight.blocks": "FP4", "block.18.mlp.mlp2_weight.scales": "UE8", "block.18.mlp.mlp2_bias": "BF16", "block.19.attn.norm.scale": "BF16", "block.19.attn.qkv.weight": "BF16", "block.19.attn.qkv.bias": "BF16", "block.19.attn.sinks": "BF16", "block.19.attn.out.weight": "BF16", "block.19.attn.out.bias": "BF16", "block.19.mlp.norm.scale": "BF16", "block.19.mlp.gate.weight": "BF16", "block.19.mlp.gate.bias": "BF16", "block.19.mlp.mlp1_weight.blocks": "FP4", "block.19.mlp.mlp1_weight.scales": "UE8", "block.19.mlp.mlp1_bias": "BF16", "block.19.mlp.mlp2_weight.blocks": "FP4", "block.19.mlp.mlp2_weight.scales": "UE8", "block.19.mlp.mlp2_bias": "BF16", "block.20.attn.norm.scale": "BF16", "block.20.attn.qkv.weight": "BF16", "block.20.attn.qkv.bias": "BF16", "block.20.attn.sinks": "BF16", "block.20.attn.out.weight": "BF16", "block.20.attn.out.bias": "BF16", "block.20.mlp.norm.scale": "BF16", "block.20.mlp.gate.weight": "BF16", "block.20.mlp.gate.bias": "BF16", "block.20.mlp.mlp1_weight.blocks": "FP4", "block.20.mlp.mlp1_weight.scales": "UE8", "block.20.mlp.mlp1_bias": "BF16", "block.20.mlp.mlp2_weight.blocks": "FP4", "block.20.mlp.mlp2_weight.scales": "UE8", "block.20.mlp.mlp2_bias": "BF16", "block.21.attn.norm.scale": "BF16", "block.21.attn.qkv.weight": "BF16", "block.21.attn.qkv.bias": "BF16", "block.21.attn.sinks": "BF16", "block.21.attn.out.weight": "BF16", "block.21.attn.out.bias": "BF16", "block.21.mlp.norm.scale": "BF16", "block.21.mlp.gate.weight": "BF16", "block.21.mlp.gate.bias": "BF16", "block.21.mlp.mlp1_weight.blocks": "FP4", "block.21.mlp.mlp1_weight.scales": "UE8", "block.21.mlp.mlp1_bias": "BF16", "block.21.mlp.mlp2_weight.blocks": "FP4", "block.21.mlp.mlp2_weight.scales": "UE8", "block.21.mlp.mlp2_bias": "BF16", "block.22.attn.norm.scale": "BF16", "block.22.attn.qkv.weight": "BF16", "block.22.attn.qkv.bias": "BF16", "block.22.attn.sinks": "BF16", "block.22.attn.out.weight": "BF16", "block.22.attn.out.bias": "BF16", "block.22.mlp.norm.scale": "BF16", "block.22.mlp.gate.weight": "BF16", "block.22.mlp.gate.bias": "BF16", "block.22.mlp.mlp1_weight.blocks": "FP4", "block.22.mlp.mlp1_weight.scales": "UE8", "block.22.mlp.mlp1_bias": "BF16", "block.22.mlp.mlp2_weight.blocks": "FP4", "block.22.mlp.mlp2_weight.scales": "UE8", "block.22.mlp.mlp2_bias": "BF16", "block.23.attn.norm.scale": "BF16", "block.23.attn.qkv.weight": "BF16", "block.23.attn.qkv.bias": "BF16", "block.23.attn.sinks": "BF16", "block.23.attn.out.weight": "BF16", "block.23.attn.out.bias": "BF16", "block.23.mlp.norm.scale": "BF16", "block.23.mlp.gate.weight": "BF16", "block.23.mlp.gate.bias": "BF16", "block.23.mlp.mlp1_weight.blocks": "FP4", "block.23.mlp.mlp1_weight.scales": "UE8", "block.23.mlp.mlp1_bias": "BF16", "block.23.mlp.mlp2_weight.blocks": "FP4", "block.23.mlp.mlp2_weight.scales": "UE8", "block.23.mlp.mlp2_bias": "BF16", "norm.scale": "BF16", "unembedding.weight": "BF16"}
 
 
original/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3340a61d1a0391e8c5b5d3463d18d4c48129a84bbc04a554c762c99020aa06ed
3
- size 13761300984