khalidalt commited on
Commit
fbc52c7
1 Parent(s): a5c4ce6

Upload model

Browse files
Files changed (2) hide show
  1. config.json +45 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/media/khalid/HDD2/Huggingface_models/bloom1b7",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomModel"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_softmax_in_fp32": true,
9
+ "bias_dropout_fusion": true,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "masked_softmax_fusion": true,
17
+ "model_type": "bloom",
18
+ "n_head": 16,
19
+ "n_inner": null,
20
+ "n_layer": 24,
21
+ "offset_alibi": 100,
22
+ "pad_token_id": 3,
23
+ "pretraining_tp": 2,
24
+ "quantization_config": {
25
+ "bnb_4bit_compute_dtype": "float32",
26
+ "bnb_4bit_quant_type": "fp4",
27
+ "bnb_4bit_use_double_quant": false,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": false,
33
+ "load_in_8bit": true,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "seq_length": 4096,
37
+ "skip_bias_add": true,
38
+ "skip_bias_add_qkv": false,
39
+ "slow_but_exact": false,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.33.0.dev0",
42
+ "unk_token_id": 0,
43
+ "use_cache": true,
44
+ "vocab_size": 250880
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bda3cb520d7d853ac99f40f09b5e7f98d63e468f0ea3698cefec0d344686278
3
+ size 2238754465