PingVortex commited on
Commit
219c92c
·
verified ·
1 Parent(s): 40f7ee6

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50256,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 50256,
10
+ "head_dim": 32,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 256,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 688,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 8,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": null,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_parameters": {
25
+ "factor": 4.0,
26
+ "rope_theta": 10000.0,
27
+ "rope_type": "dynamic"
28
+ },
29
+ "tie_word_embeddings": true,
30
+ "transformers_version": "5.3.0",
31
+ "use_cache": false,
32
+ "vocab_size": 50259
33
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.3.0",
8
+ "use_cache": false
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76c2aef135f296b3014d6b003adc63816a671c84e1c62c79f225c3ed2a72aed
3
+ size 38397880
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "extra_special_tokens": [
6
+ "<|im_start|>",
7
+ "<|im_end|>"
8
+ ],
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "TokenizersBackend"
12
+ }