Upload 6 files
Browse files- config.json +26 -0
- generation_config.json +7 -0
- measurement.json +0 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +13 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 1,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"hidden_act": "silu",
|
8 |
+
"hidden_size": 4096,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 11008,
|
11 |
+
"max_position_embeddings": 200000,
|
12 |
+
"model_type": "llama",
|
13 |
+
"num_attention_heads": 32,
|
14 |
+
"num_hidden_layers": 32,
|
15 |
+
"num_key_value_heads": 4,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"pretraining_tp": 1,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 5000000.0,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.34.0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 64000
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.34.0"
|
7 |
+
}
|
measurement.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"model_max_length": 200000,
|
5 |
+
"unk_token": "<unk>",
|
6 |
+
"bos_token": "<|startoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
8 |
+
"pad_token": "<unk>",
|
9 |
+
"sp_model_kwargs": {},
|
10 |
+
"clean_up_tokenization_spaces": false,
|
11 |
+
"legacy": true,
|
12 |
+
"tokenizer_class": "LlamaTokenizer"
|
13 |
+
}
|