rwitz2 commited on
Commit
cbb491e
1 Parent(s): 9769a6d

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +28 -0
  2. model.safetensors +3 -0
  3. tokenizer.model +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./results6",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2816,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 16,
18
+ "pad_token_id": 0,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 2048,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.41.2",
25
+ "unsloth_version": "2024.5",
26
+ "use_cache": true,
27
+ "vocab_size": 32064
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370c9640d5260902c1a22f9033c80a6a6f0cf400627fd25c7a35c642da7dacac
3
+ size 748022128
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723