chrisociepa
commited on
Commit
•
bd2aa78
1
Parent(s):
29372d7
Upload model and tokenizer files
Browse files- config.json +25 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +5 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 1,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"hidden_act": "silu",
|
8 |
+
"hidden_size": 1024,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 2816,
|
11 |
+
"max_position_embeddings": 2048,
|
12 |
+
"model_type": "llama",
|
13 |
+
"num_attention_heads": 16,
|
14 |
+
"num_hidden_layers": 73,
|
15 |
+
"num_key_value_heads": 16,
|
16 |
+
"pretraining_tp": 1,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"rope_scaling": null,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.33.2",
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 8000
|
25 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5ab400b903c7d02fe4b57b0a4b75acc760f41975f75912e394da3b72c3fa8f3
|
3 |
+
size 3817108634
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"sep_token": "<sep>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 2048,
|
4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
+
}
|