Initial GPTQ model commit
Browse files- config.json +24 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/data/project/private/limerobot/repos/workspace/project/llm-tf/limerobot/output/llama-65b/checkpoint-594",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 8192,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 22016,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"max_sequence_length": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 64,
|
16 |
+
"num_hidden_layers": 80,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "bfloat16",
|
21 |
+
"transformers_version": "4.30.2",
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 32000
|
24 |
+
}
|