PicoKittens commited on
Commit
b1c0ada
·
verified ·
1 Parent(s): 29b65c1

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 6,
17
+ "num_hidden_layers": 8,
18
+ "num_key_value_heads": 2,
19
+ "pad_token_id": 0,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_parameters": {
22
+ "rope_theta": 10000.0,
23
+ "rope_type": "default"
24
+ },
25
+ "sliding_window": 4096,
26
+ "tie_word_embeddings": true,
27
+ "transformers_version": "5.2.0",
28
+ "use_cache": true,
29
+ "vocab_size": 16384
30
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "5.2.0",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de75683d99989dfe64778045979ecb35bb3e2482c16a8d607a96d375054f63a7
3
+ size 94406024
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "[BOS]",
4
+ "eos_token": "[EOS]",
5
+ "extra_special_tokens": [
6
+ "<|user|>",
7
+ "<|assistant|>",
8
+ "<|end|>"
9
+ ],
10
+ "model_max_length": 1000000000000000019884624838656,
11
+ "pad_token": "[PAD]",
12
+ "tokenizer_class": "TokenizersBackend",
13
+ "unk_token": "[UNK]"
14
+ }