a14195657895178240309011
/
deepspeak-R1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add config.json 

Signed-off-by: a14195657895178240309011 <a14195657895178240309011@hero.ai>
This commit is contained in:
a14195657895178240309011 2025-02-03 14:39:05 +08:00
parent ffa0d3476f
commit 7a1952920c
1 changed files with 28 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
config.json Normal file
View File

@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"max_position_embeddings": 131072,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_theta": 10000,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.0",
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 151936
}