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_third1.json Normal file
View File

@@ -0,0 +1,142 @@
{
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.sinks": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.o_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.router.weight": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.router.bias": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.experts.down_proj": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00008.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.sinks": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.o_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.router.weight": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.router.bias": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.experts.down_proj": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00008.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.sinks": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.o_proj.bias": "model-00001-of-00008.safetensors",
"model.layers.2.mlp.router.weight": "model-00001-of-00008.safetensors",
"model.layers.2.mlp.router.bias": "model-00001-of-00008.safetensors",
"model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00008.safetensors",
"model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00008.safetensors",
"model.layers.2.mlp.experts.down_proj": "model-00002-of-00008.safetensors",
"model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00008.safetensors",
"model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.sinks": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.3.mlp.router.weight": "model-00002-of-00008.safetensors",
"model.layers.3.mlp.router.bias": "model-00002-of-00008.safetensors",
"model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00008.safetensors",
"model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00008.safetensors",
"model.layers.3.mlp.experts.down_proj": "model-00002-of-00008.safetensors",
"model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00008.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.sinks": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.router.weight": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.router.bias": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.experts.down_proj": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00008.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.sinks": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
"model.layers.5.mlp.router.weight": "model-00002-of-00008.safetensors",
"model.layers.5.mlp.router.bias": "model-00002-of-00008.safetensors",
"model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00008.safetensors",
"model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00008.safetensors",
"model.layers.5.mlp.experts.down_proj": "model-00003-of-00008.safetensors",
"model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00008.safetensors",
"model.layers.5.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.sinks": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.6.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
"model.layers.6.mlp.router.weight": "model-00003-of-00008.safetensors",
"model.layers.6.mlp.router.bias": "model-00003-of-00008.safetensors",
"model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00008.safetensors",
"model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00008.safetensors",
"model.layers.6.mlp.experts.down_proj": "model-00003-of-00008.safetensors",
"model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00008.safetensors",
"model.layers.6.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.sinks": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.7.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
"model.layers.7.mlp.router.weight": "model-00003-of-00008.safetensors",
"model.layers.7.mlp.router.bias": "model-00003-of-00008.safetensors",
"model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00008.safetensors",
"model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00008.safetensors",
"model.layers.7.mlp.experts.down_proj": "model-00003-of-00008.safetensors",
"model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00008.safetensors",
"model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors"
},
"shard_count": 3
}