xinyun/QwQ-32B
1
0
Fork 0
mirror of https://www.modelscope.cn/Qwen/QwQ-32B.git synced 2025-12-09 05:44:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update config.json

Browse Source
This commit is contained in:
Cherrytest 2025-03-05 16:27:05 +00:00
parent 247d06c0e3
commit f5244dd874
1 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
config.json
View File

@ -1,5 +1,4 @@
{
"_name_or_path": "/cpfs01/data/shared/Group-m6/chuanyi.yl/ckpts/sft/dense/hf-ckpts/32b.stage2--cptv9-base100w-cpt32k-0218_Ma_Co_STE_Rea_Age_Gen_dgb-32B.qwen2.5B-bf16-mp8-pp1-lr-7e-6-minlr-7e-7-bs-128-gpus-128-seqlen-32768-step8392",
"architectures": [
"Qwen2ForCausalLM"
],
@ -10,20 +9,19 @@
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 65536,
"max_position_embeddings": 131072,
"max_window_layers": 64,
"model_type": "qwen2",
"num_attention_heads": 40,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.2",
"transformers_version": "4.43.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}
}