luckyvishwa commited on
Commit
dd5217c
·
verified ·
1 Parent(s): 4a986cd

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float16",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 256,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 4,
19
+ "num_hidden_layers": 4,
20
+ "num_key_value_heads": 4,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_parameters": {
25
+ "rope_theta": 10000.0,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": false,
29
+ "transformers_version": "5.0.0",
30
+ "use_cache": true,
31
+ "vocab_size": 119547
32
+ }
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": "5.0.0",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be869dea795491b68a2cfbdb94f96635940fe5f8f518d0522db1d6ec05a68778
3
+ size 192155360
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": true,
6
+ "mask_token": "[MASK]",
7
+ "max_length": 128,
8
+ "model_max_length": 512,
9
+ "pad_to_multiple_of": null,
10
+ "pad_token": "[PAD]",
11
+ "pad_token_type_id": 0,
12
+ "padding_side": "right",
13
+ "sep_token": "[SEP]",
14
+ "stride": 0,
15
+ "strip_accents": null,
16
+ "tokenize_chinese_chars": true,
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "truncation_side": "right",
19
+ "truncation_strategy": "longest_first",
20
+ "unk_token": "[UNK]"
21
+ }