alea-institute
commited on
Upload folder using huggingface_hub
Browse files- config.json +34 -0
- generation_config.json +8 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ubuntu/src/kl3m-trainer/checkpoints",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": true,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.1,
|
10 |
+
"eos_token_id": 1,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 1024,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 4096,
|
18 |
+
"model_type": "gpt_neox",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 16,
|
21 |
+
"num_key_value_heads": 8,
|
22 |
+
"pad_token_id": 2,
|
23 |
+
"rms_norm_eps": 1e-06,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 10000,
|
26 |
+
"rotary_emb_base": 10000,
|
27 |
+
"rotary_pct": 0.25,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.38.0.dev0",
|
31 |
+
"use_cache": false,
|
32 |
+
"use_parallel_residual": true,
|
33 |
+
"vocab_size": 32768
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 2,
|
6 |
+
"transformers_version": "4.38.0.dev0",
|
7 |
+
"use_cache": false
|
8 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca8b040769dea517ea7496cc3a62c1654dcd0d57873925933089712927c3623a
|
3 |
+
size 671818714
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|start|>",
|
3 |
+
"eos_token": "<|end|>",
|
4 |
+
"mask_token": "<|mask|>",
|
5 |
+
"pad_token": "<|pad|>",
|
6 |
+
"unk_token": {
|
7 |
+
"content": "<|unk|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
}
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|