Upload 2 files
Browse files- config.json +7 -18
- generation_config.json +2 -4
config.json
CHANGED
@@ -1,39 +1,28 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
-
"eos_token_id":
|
10 |
-
128001,
|
11 |
-
128008,
|
12 |
-
128009
|
13 |
-
],
|
14 |
"hidden_act": "silu",
|
15 |
"hidden_size": 4096,
|
16 |
"initializer_range": 0.02,
|
17 |
"intermediate_size": 14336,
|
18 |
-
"max_position_embeddings":
|
19 |
-
"mlp_bias": false,
|
20 |
"model_type": "llama",
|
21 |
"num_attention_heads": 32,
|
22 |
"num_hidden_layers": 32,
|
23 |
"num_key_value_heads": 8,
|
24 |
"pretraining_tp": 1,
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
-
"rope_scaling":
|
27 |
-
"factor": 8.0,
|
28 |
-
"high_freq_factor": 4.0,
|
29 |
-
"low_freq_factor": 1.0,
|
30 |
-
"original_max_position_embeddings": 8192,
|
31 |
-
"rope_type": "llama3"
|
32 |
-
},
|
33 |
"rope_theta": 500000.0,
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "float32",
|
36 |
-
"transformers_version": "4.
|
37 |
-
"use_cache":
|
38 |
-
"vocab_size":
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128256,
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
|
|
15 |
"model_type": "llama",
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
19 |
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"rope_theta": 500000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.40.0.dev0",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 128257
|
28 |
}
|
generation_config.json
CHANGED
@@ -1,12 +1,10 @@
|
|
1 |
{
|
|
|
2 |
"bos_token_id": 128000,
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
128001,
|
6 |
-
128008,
|
7 |
128009
|
8 |
],
|
9 |
-
"
|
10 |
-
"top_p": 0.9,
|
11 |
-
"transformers_version": "4.44.2"
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
4 |
"do_sample": true,
|
5 |
"eos_token_id": [
|
6 |
128001,
|
|
|
7 |
128009
|
8 |
],
|
9 |
+
"transformers_version": "4.40.0.dev0"
|
|
|
|
|
10 |
}
|