mlx-community/Llama-3.2-1B-Instruct-MLXTuned
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

fine-tuned model

Browse Source
This commit is contained in:
ai-modelscope
2025-01-03 13:04:20 +08:00
parent e2e5c6b027
commit 90669c93d6
9 changed files with 2520 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

153
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,153 @@
{
"metadata": {
"total_size": 2471628800
},
"weight_map": {
"model.embed_tokens.weight": "model.safetensors",
"model.layers.0.input_layernorm.weight": "model.safetensors",
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
"model.layers.1.input_layernorm.weight": "model.safetensors",
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
"model.layers.10.input_layernorm.weight": "model.safetensors",
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
"model.layers.11.input_layernorm.weight": "model.safetensors",
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
"model.layers.12.input_layernorm.weight": "model.safetensors",
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
"model.layers.13.input_layernorm.weight": "model.safetensors",
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
"model.layers.14.input_layernorm.weight": "model.safetensors",
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
"model.layers.15.input_layernorm.weight": "model.safetensors",
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
"model.layers.2.input_layernorm.weight": "model.safetensors",
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
"model.layers.3.input_layernorm.weight": "model.safetensors",
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
"model.layers.4.input_layernorm.weight": "model.safetensors",
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
"model.layers.5.input_layernorm.weight": "model.safetensors",
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
"model.layers.6.input_layernorm.weight": "model.safetensors",
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
"model.layers.7.input_layernorm.weight": "model.safetensors",
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
"model.layers.8.input_layernorm.weight": "model.safetensors",
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
"model.layers.9.input_layernorm.weight": "model.safetensors",
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
"model.norm.weight": "model.safetensors"
}
}