tensorhydra/gpt-oss-20b-numinamath
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: tensorhydra/gpt-oss-20b-numinamath
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-20 11:13:05 +08:00
commit d0dfd3d9ea
20 changed files with 1637 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

142
weight_map_third2.json Normal file
View File

@@ -0,0 +1,142 @@
{
"weight_map": {
"model.layers.8.self_attn.sinks": "model-00004-of-00008.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.8.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.8.mlp.router.weight": "model-00004-of-00008.safetensors",
"model.layers.8.mlp.router.bias": "model-00004-of-00008.safetensors",
"model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
"model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
"model.layers.8.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
"model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
"model.layers.8.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.sinks": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.9.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.9.mlp.router.weight": "model-00004-of-00008.safetensors",
"model.layers.9.mlp.router.bias": "model-00004-of-00008.safetensors",
"model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
"model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
"model.layers.9.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
"model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
"model.layers.9.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.sinks": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.10.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.10.mlp.router.weight": "model-00004-of-00008.safetensors",
"model.layers.10.mlp.router.bias": "model-00004-of-00008.safetensors",
"model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
"model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
"model.layers.10.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
"model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
"model.layers.10.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.sinks": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.11.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
"model.layers.11.mlp.router.weight": "model-00004-of-00008.safetensors",
"model.layers.11.mlp.router.bias": "model-00004-of-00008.safetensors",
"model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
"model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
"model.layers.11.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
"model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
"model.layers.11.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.sinks": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.12.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.12.mlp.router.weight": "model-00005-of-00008.safetensors",
"model.layers.12.mlp.router.bias": "model-00005-of-00008.safetensors",
"model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
"model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
"model.layers.12.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
"model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
"model.layers.12.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.sinks": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.13.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.13.mlp.router.weight": "model-00005-of-00008.safetensors",
"model.layers.13.mlp.router.bias": "model-00005-of-00008.safetensors",
"model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
"model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
"model.layers.13.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
"model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
"model.layers.13.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.sinks": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.14.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
"model.layers.14.mlp.router.weight": "model-00005-of-00008.safetensors",
"model.layers.14.mlp.router.bias": "model-00005-of-00008.safetensors",
"model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00008.safetensors",
"model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00008.safetensors",
"model.layers.14.mlp.experts.down_proj": "model-00006-of-00008.safetensors",
"model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00008.safetensors",
"model.layers.14.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.sinks": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.15.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
"model.layers.15.mlp.router.weight": "model-00006-of-00008.safetensors",
"model.layers.15.mlp.router.bias": "model-00006-of-00008.safetensors",
"model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00008.safetensors",
"model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00008.safetensors",
"model.layers.15.mlp.experts.down_proj": "model-00006-of-00008.safetensors",
"model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00008.safetensors",
"model.layers.15.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.16.self_attn.sinks": "model-00006-of-00008.safetensors"
},
"shard_count": 3
}