Hugging Face's logo

mostafatarek4
/
FitReccomendation

Text Generation
Transformers
Safetensors
llama
unsloth
text-generation-inference
Inference Endpoints
4-bit precision
Model card Files Community
mostafatarek4 commited on
Commit
33e09be
•
1 Parent(s): ede5a88

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +24 -23
config.json CHANGED
@@ -1,25 +1,26 @@
1
  {
2
- "model_type": "llama",
3
- "hidden_size": 4096,
4
- "intermediate_size": 11008,
5
- "num_attention_heads": 32,
6
- "num_hidden_layers": 32,
7
- "vocab_size": 32000,
8
- "max_position_embeddings": 2048,
9
- "rope_scaling": {
10
- "type": "dynamic",
11
- "factor": 2
12
- },
13
- "rotary_embedding_base": 10000,
14
- "tie_word_embeddings": false,
15
- "torch_dtype": "float16",
16
- "use_cache": true,
17
- "pad_token_id": 0,
18
- "bos_token_id": 1,
19
- "eos_token_id": 2,
20
- "quantization_config": {
21
- "load_in_4bit": true,
22
- "bnb_4bit_use_double_quant": true,
23
- "bnb_4bit_quant_type": "nf4"
24
- }
 
25
  }
 
1
  {
2
+ "model_type": "llama",
3
+ "architectures": ["LlamaForCausalLM"],
4
+ "hidden_size": 4096,
5
+ "intermediate_size": 11008,
6
+ "num_attention_heads": 32,
7
+ "num_hidden_layers": 32,
8
+ "vocab_size": 32000,
9
+ "max_position_embeddings": 2048,
10
+ "rope_scaling": {
11
+ "type": "dynamic",
12
+ "factor": 1.0
13
+ },
14
+ "rotary_embedding_base": 10000,
15
+ "tie_word_embeddings": false,
16
+ "torch_dtype": "float16",
17
+ "use_cache": true,
18
+ "pad_token_id": 0,
19
+ "bos_token_id": 1,
20
+ "eos_token_id": 2,
21
+ "quantization_config": {
22
+ "load_in_4bit": true,
23
+ "bnb_4bit_use_double_quant": true,
24
+ "bnb_4bit_quant_type": "nf4"
25
+ }
26
  }