groupuser/qwen3-4b-instruct-gguf
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Upload config.json

Browse Source
This commit is contained in:
Darren Oberst 2025-07-05 13:36:27 +00:00 committed by system
parent 9d8a1d5be0
commit 6d335f68f6
No known key found for this signature in database
GPG Key ID: 6A528E38E0733467
1 changed files with 30 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
config.json Normal file
View File

@ -0,0 +1,30 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"max_position_embeddings": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}