Hugging Face's logo

Nitral-AI
/
Hathor_Tahsin-L3-8B-v0.9-5bpw-exl2

Safetensors
English
llama
Model card Files Community
Nitral-AI commited on
Commit
addb6c4
•
1 Parent(s): 7b1ab6c

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +38 -39
config.json CHANGED
@@ -1,39 +1,38 @@
1
- {
2
- "_name_or_path": "./Hathor_Tahsin-L3-8B-v0.9",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "hidden_act": "silu",
15
- "hidden_size": 4096,
16
- "initializer_range": 0.02,
17
- "intermediate_size": 14336,
18
- "max_position_embeddings": 131072,
19
- "mlp_bias": false,
20
- "model_type": "llama",
21
- "num_attention_heads": 32,
22
- "num_hidden_layers": 32,
23
- "num_key_value_heads": 8,
24
- "pretraining_tp": 1,
25
- "rms_norm_eps": 1e-05,
26
- "rope_scaling": {
27
- "factor": 8.0,
28
- "low_freq_factor": 1.0,
29
- "high_freq_factor": 4.0,
30
- "original_max_position_embeddings": 8192,
31
- "rope_type": "llama3"
32
- },
33
- "rope_theta": 500000.0,
34
- "tie_word_embeddings": false,
35
- "torch_dtype": "bfloat16",
36
- "transformers_version": "4.38.1",
37
- "use_cache": true,
38
- "vocab_size": 128256
39
- }
 
1
+ {
2
+ "_name_or_path": "./Hathor_Tahsin-L3-8B-v0.9",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.38.1",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }