Upload 5 files
Browse files- config.json +32 -0
- model.safetensors +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_qkv_bias": false,
|
3 |
+
"codebook_size": 2048,
|
4 |
+
"dim": 768,
|
5 |
+
"dropout": 0.1,
|
6 |
+
"fast_attention_qkv_bias": false,
|
7 |
+
"fast_dim": 768,
|
8 |
+
"fast_head_dim": 64,
|
9 |
+
"fast_intermediate_size": 3072,
|
10 |
+
"fast_n_head": 12,
|
11 |
+
"fast_n_local_heads": 4,
|
12 |
+
"head_dim": 64,
|
13 |
+
"initializer_range": 0.041666666666666664,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"is_reward_model": false,
|
16 |
+
"max_seq_len": 2048,
|
17 |
+
"model_type": "dual_ar",
|
18 |
+
"n_fast_layer": 4,
|
19 |
+
"n_head": 12,
|
20 |
+
"n_layer": 10,
|
21 |
+
"n_local_heads": 4,
|
22 |
+
"depthwise_wte": true,
|
23 |
+
"depthwise_output": true,
|
24 |
+
"norm_eps": 1e-5,
|
25 |
+
"num_codebooks": 8,
|
26 |
+
"rope_base": 100000,
|
27 |
+
"scale_codebook_embeddings": false,
|
28 |
+
"share_codebook_embeddings": true,
|
29 |
+
"tie_word_embeddings": true,
|
30 |
+
"use_gradient_checkpointing": true,
|
31 |
+
"vocab_size": 2368
|
32 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f6274ab57d5eb5a7a69f3bf38486a593b364800b7d8d83e35af261e909bd6f0
|
3 |
+
size 318266952
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|im_start|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|pad|>",
|
5 |
+
"unk_token": "<|unknown|>"
|
6 |
+
}
|
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
|
|