AdamJaber commited on
Commit
8067617
·
verified ·
1 Parent(s): b60eb38

Upload step-4600 checkpoint (weights + tokenizer)

Browse files
Files changed (4) hide show
  1. config.json +21 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +10 -0
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "model_type": "llama",
6
+ "hidden_size": 960,
7
+ "intermediate_size": 2560,
8
+ "num_hidden_layers": 32,
9
+ "num_attention_heads": 15,
10
+ "num_key_value_heads": 5,
11
+ "vocab_size": 65536,
12
+ "max_position_embeddings": 2048,
13
+ "rms_norm_eps": 1e-05,
14
+ "rope_theta": 10000.0,
15
+ "tie_word_embeddings": false,
16
+ "bos_token_id": 0,
17
+ "eos_token_id": 0,
18
+ "pad_token_id": null,
19
+ "use_cache": true,
20
+ "hidden_act": "silu"
21
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad76c884e5c92b67636df47de1856c9afef7a273ba959c54077f5fc3059ca95
3
+ size 1761890112
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "bos_token": null,
5
+ "eos_token": "<|endoftext|>",
6
+ "unk_token": null,
7
+ "pad_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "tokenizer_class": "PreTrainedTokenizerFast"
10
+ }