leafspark commited on
Commit
cea0863
·
verified ·
1 Parent(s): f21d996

model: add config and tokenizer

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 12288,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 28672,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 96,
15
+ "num_hidden_layers": 88,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 1000000.0,
19
+ "sliding_window": null,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.42.3",
23
+ "use_cache": true,
24
+ "vocab_size": 32768
25
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.42.3"
6
+ }
params.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dim": 12288,
3
+ "n_layers": 88,
4
+ "head_dim": 128,
5
+ "hidden_dim": 28672,
6
+ "n_heads": 96,
7
+ "n_kv_heads": 8,
8
+ "norm_eps": 1e-05,
9
+ "vocab_size": 32768,
10
+ "rope_theta": 1000000.0
11
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer.model.v3 ADDED
Binary file (588 kB). View file
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff