Upload 6 files
Browse files- codec.pth +3 -0
- config.json +32 -0
- model.pth +3 -0
- special_tokens.json +0 -0
- tokenizer.tiktoken +0 -0
codec.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74fc41c5a7151c6f350af8bd7e5d6e3accfcc7f3dfbfac23afd35af07052bb2f
|
| 3 |
+
size 1871099728
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_o_bias": false,
|
| 3 |
+
"attention_qk_norm": true,
|
| 4 |
+
"attention_qkv_bias": false,
|
| 5 |
+
"codebook_size": 4096,
|
| 6 |
+
"dim": 1024,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"fast_attention_o_bias": false,
|
| 9 |
+
"fast_attention_qk_norm": false,
|
| 10 |
+
"fast_attention_qkv_bias": false,
|
| 11 |
+
"fast_dim": 1024,
|
| 12 |
+
"fast_head_dim": 64,
|
| 13 |
+
"fast_intermediate_size": 3072,
|
| 14 |
+
"fast_n_head": 16,
|
| 15 |
+
"fast_n_local_heads": 8,
|
| 16 |
+
"head_dim": 128,
|
| 17 |
+
"initializer_range": 0.03125,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"max_seq_len": 8192,
|
| 20 |
+
"model_type": "dual_ar",
|
| 21 |
+
"n_fast_layer": 4,
|
| 22 |
+
"n_head": 16,
|
| 23 |
+
"n_layer": 28,
|
| 24 |
+
"n_local_heads": 8,
|
| 25 |
+
"norm_eps": 1e-06,
|
| 26 |
+
"num_codebooks": 10,
|
| 27 |
+
"rope_base": 1000000,
|
| 28 |
+
"scale_codebook_embeddings": true,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"use_gradient_checkpointing": true,
|
| 31 |
+
"vocab_size": 155776
|
| 32 |
+
}
|
model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e59be7dc6714040dce3cde1f41e730c2f0daa5339785b1cd3b60041208c35e6
|
| 3 |
+
size 1735122974
|
special_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.tiktoken
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|