Satyam-Singh
commited on
Commit
•
92ad81c
1
Parent(s):
d215d95
Upload 2 files
Browse files- config.json +29 -0
- generation_config.json +6 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MixtralForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 14336,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"model_type": "mixtral",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_experts_per_tok": 2,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"num_local_experts": 8,
|
19 |
+
"output_router_logits": false,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"router_aux_loss_coef": 0.02,
|
23 |
+
"sliding_window": null,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.36.0.dev0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.0.dev0"
|
6 |
+
}
|