mahek jasani
commited on
Commit
•
31e0d1b
1
Parent(s):
e9a54d6
Upload config.json
Browse files- config.json +28 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CohereForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 5,
|
| 8 |
+
"eos_token_id": 255001,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 12288,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 33792,
|
| 13 |
+
"layer_norm_eps": 1e-05,
|
| 14 |
+
"logit_scale": 0.8333333333333334,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"model_max_length": 131072,
|
| 17 |
+
"model_type": "cohere",
|
| 18 |
+
"num_attention_heads": 96,
|
| 19 |
+
"num_hidden_layers": 64,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"rope_theta": 75000000.0,
|
| 23 |
+
"torch_dtype": "float16",
|
| 24 |
+
"transformers_version": "4.40.0.dev0",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"use_qk_norm": true,
|
| 27 |
+
"vocab_size": 256000
|
| 28 |
+
}
|