4r7i5t commited on
Commit
2ec4cb7
·
verified ·
1 Parent(s): 46bcc64

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "float32",
9
+ "eos_token_id": 0,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 960,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2560,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 15,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 5,
22
+ "pad_token_id": null,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_parameters": {
27
+ "rope_theta": 100000,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.2.0",
32
+ "use_cache": true,
33
+ "vocab_size": 49152
34
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "5.2.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a559b875a5f8d163e9a3c6acb8c7ed2b62b178381ec3450b3d796448c20fcccb
3
+ size 1447317080
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "extra_special_tokens": [
8
+ "<|endoftext|>",
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<repo_name>",
12
+ "<reponame>",
13
+ "<file_sep>",
14
+ "<filename>",
15
+ "<gh_stars>",
16
+ "<issue_start>",
17
+ "<issue_comment>",
18
+ "<issue_closed>",
19
+ "<jupyter_start>",
20
+ "<jupyter_text>",
21
+ "<jupyter_code>",
22
+ "<jupyter_output>",
23
+ "<jupyter_script>",
24
+ "<empty_output>"
25
+ ],
26
+ "is_local": false,
27
+ "model_max_length": 8192,
28
+ "tokenizer_class": "TokenizersBackend",
29
+ "unk_token": "<|endoftext|>",
30
+ "vocab_size": 49152
31
+ }