RichardErkhov
commited on
Commit
•
4078c6b
1
Parent(s):
ab35f6b
uploaded model
Browse files- config.json +40 -0
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "GaMS-1B",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"do_layer_norm_before": true,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 8192,
|
16 |
+
"hidden_size": 2048,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
+
"layerdrop": 0.0,
|
20 |
+
"max_position_embeddings": 2048,
|
21 |
+
"model_type": "opt",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 24,
|
24 |
+
"pad_token_id": 3,
|
25 |
+
"quantization_config": {
|
26 |
+
"bits": 4,
|
27 |
+
"group_size": 128,
|
28 |
+
"modules_to_not_convert": null,
|
29 |
+
"quant_method": "awq",
|
30 |
+
"version": "gemm",
|
31 |
+
"zero_point": true
|
32 |
+
},
|
33 |
+
"sep_token_id": 5,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "float16",
|
36 |
+
"transformers_version": "4.46.2",
|
37 |
+
"use_cache": false,
|
38 |
+
"vocab_size": 80000,
|
39 |
+
"word_embed_proj_dim": 2048
|
40 |
+
}
|