mahimairaja commited on
Commit
067ba29
·
1 Parent(s): 5529fac

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +25 -10
config.json CHANGED
@@ -1,10 +1,25 @@
1
- {'quant_method': <QuantizationMethod.BITS_AND_BYTES: 'bitsandbytes'>,
2
- 'load_in_8bit': False,
3
- 'load_in_4bit': True,
4
- 'llm_int8_threshold': 6.0,
5
- 'llm_int8_skip_modules': None,
6
- 'llm_int8_enable_fp32_cpu_offload': False,
7
- 'llm_int8_has_fp16_weight': False,
8
- 'bnb_4bit_quant_type': 'nf4',
9
- 'bnb_4bit_use_double_quant': False,
10
- 'bnb_4bit_compute_dtype': 'float16'}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mahimairaja/tweet-summarization-llama-2-finetuned",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.31.0.dev0",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }