gate369 commited on
Commit
850bc79
·
verified ·
1 Parent(s): d8f6a20

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50257,
3
+ "dim": 1024,
4
+ "num_layers": 6,
5
+ "num_heads": 16,
6
+ "max_recursion": 4,
7
+ "ffn_expansion": 4,
8
+ "max_position_embeddings": 1024,
9
+ "balancing_weight": 0.01,
10
+ "temperature": 1.0,
11
+ "window_size": 2048,
12
+ "model_type": "MoR",
13
+ "architecture": "MixtureOfRecursions",
14
+ "hidden_act": "gelu"
15
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66dcce67090c115438c49bb028a478fb25b90b40e6a60f1f2669897def46528
3
+ size 724542240
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>",
5
+ "pad_token": null
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "GPT2Tokenizer",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>",
6
+ "pad_token": null,
7
+ "model_max_length": 1024
8
+ }
training_step.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ Step: 145000
vocab.json ADDED
The diff for this file is too large to render. See raw diff