Upload folder using huggingface_hub
Browse files- config.json +18 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +23 -0
- tokenizer_config.json +23 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_type": "deepseek",
|
3 |
+
"architectures": [
|
4 |
+
"DeepSeekForCausalLM"
|
5 |
+
],
|
6 |
+
"vocab_size": 50257,
|
7 |
+
"hidden_size": 512,
|
8 |
+
"num_hidden_layers": 6,
|
9 |
+
"num_attention_heads": 8,
|
10 |
+
"max_position_embeddings": 1024,
|
11 |
+
"use_mla": true,
|
12 |
+
"mla_kv_heads": 4,
|
13 |
+
"moe_num_experts": 4,
|
14 |
+
"multi_token_predict": 2,
|
15 |
+
"pad_token_id": 0,
|
16 |
+
"bos_token_id": 1,
|
17 |
+
"eos_token_id": 2
|
18 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:235b113b49f4ad4d9f9e00968144ea8d241ac65afc168070e7d4087b19a9996a
|
3 |
+
size 520131015
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"bos_token": "<|endoftext|>",
|
15 |
+
"clean_up_tokenization_spaces": false,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"errors": "replace",
|
18 |
+
"extra_special_tokens": {},
|
19 |
+
"model_max_length": 1024,
|
20 |
+
"pad_token": null,
|
21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
22 |
+
"unk_token": "<|endoftext|>"
|
23 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|