RichardErkhov commited on
Commit
4bb45b7
1 Parent(s): ede788e

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +57 -0
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt4all-j",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gptj",
15
+ "n_embd": 4096,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 28,
19
+ "n_positions": 2048,
20
+ "quantization_config": {
21
+ "_load_in_4bit": false,
22
+ "_load_in_8bit": true,
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "fp4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": false,
32
+ "load_in_8bit": true,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "resid_pdrop": 0.0,
36
+ "rotary": true,
37
+ "rotary_dim": 64,
38
+ "scale_attn_weights": true,
39
+ "summary_activation": null,
40
+ "summary_first_dropout": 0.1,
41
+ "summary_proj_to_labels": true,
42
+ "summary_type": "cls_index",
43
+ "summary_use_proj": true,
44
+ "task_specific_params": {
45
+ "text-generation": {
46
+ "do_sample": true,
47
+ "max_length": 50,
48
+ "temperature": 1.0
49
+ }
50
+ },
51
+ "tie_word_embeddings": false,
52
+ "tokenizer_class": "GPT2Tokenizer",
53
+ "torch_dtype": "float16",
54
+ "transformers_version": "4.44.2",
55
+ "use_cache": false,
56
+ "vocab_size": 50400
57
+ }