RichardErkhov
commited on
Commit
•
1cde9e7
1
Parent(s):
5a360bc
uploaded model
Browse files- config.json +37 -0
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Sailor-4B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 2560,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 6912,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 21,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 20,
|
17 |
+
"num_hidden_layers": 40,
|
18 |
+
"num_key_value_heads": 20,
|
19 |
+
"quantization_config": {
|
20 |
+
"bits": 4,
|
21 |
+
"group_size": 128,
|
22 |
+
"modules_to_not_convert": null,
|
23 |
+
"quant_method": "awq",
|
24 |
+
"version": "gemm",
|
25 |
+
"zero_point": true
|
26 |
+
},
|
27 |
+
"rms_norm_eps": 1e-06,
|
28 |
+
"rope_scaling": null,
|
29 |
+
"rope_theta": 5000000.0,
|
30 |
+
"sliding_window": null,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "float16",
|
33 |
+
"transformers_version": "4.46.3",
|
34 |
+
"use_cache": false,
|
35 |
+
"use_sliding_window": false,
|
36 |
+
"vocab_size": 151936
|
37 |
+
}
|