medmekk HF Staff commited on
Commit
c046a61
·
verified ·
1 Parent(s): 8079c8f

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +57 -0
  2. generation_config.json +11 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "float32",
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128004,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "include_input_output_embeddings": false,
25
+ "modules_to_not_convert": null,
26
+ "quant_method": "torchao",
27
+ "quant_type": {
28
+ "default": {
29
+ "_data": {
30
+ "set_inductor_config": true,
31
+ "weight_dtype": {
32
+ "_data": "float8_e4m3fn",
33
+ "_type": "torch.dtype"
34
+ }
35
+ },
36
+ "_type": "Float8WeightOnlyConfig",
37
+ "_version": 2
38
+ }
39
+ },
40
+ "quant_type_kwargs": {},
41
+ "untie_embedding_weights": false
42
+ },
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_scaling": {
45
+ "factor": 32.0,
46
+ "high_freq_factor": 4.0,
47
+ "low_freq_factor": 1.0,
48
+ "original_max_position_embeddings": 8192,
49
+ "rope_type": "llama3"
50
+ },
51
+ "rope_theta": 500000.0,
52
+ "tie_word_embeddings": true,
53
+ "transformers_version": "4.57.1",
54
+ "unsloth_fixed": true,
55
+ "use_cache": true,
56
+ "vocab_size": 128256
57
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "max_length": 131072,
7
+ "pad_token_id": 128004,
8
+ "temperature": 0.6,
9
+ "top_p": 0.9,
10
+ "transformers_version": "4.57.1"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633ef853f40b976a8e90713113b2899142ad636362baed207d59c3095cb0cf26
3
+ size 3076276784