Text Generation
Transformers
PyTorch
Safetensors
bloom
text-generation-inference
Inference Endpoints
ybelkada commited on
Commit
bccbc44
1 Parent(s): 1b7ec1b

first version

Browse files
Files changed (2) hide show
  1. config.json +35 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "architectures": [
4
+ "BloomModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_softmax_in_fp32": true,
8
+ "bias_dropout_fusion": true,
9
+ "bos_token_id": 1,
10
+ "depth_downsampling_rate": 0.5,
11
+ "eos_token_id": 2,
12
+ "hidden_dropout": 0.0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "layer_selection_strategy": "mean",
16
+ "masked_softmax_fusion": true,
17
+ "model_type": "bloom",
18
+ "n_embed": 512,
19
+ "n_inner": null,
20
+ "n_layer": 12,
21
+ "num_attention_heads": 4,
22
+ "offset_alibi": 100,
23
+ "pad_token_id": 3,
24
+ "pretraining_tp": 2,
25
+ "seq_length": 4096,
26
+ "skip_bias_add": true,
27
+ "skip_bias_add_qkv": false,
28
+ "slow_but_exact": false,
29
+ "transformers_version": "4.21.0.dev0",
30
+ "unk_token_id": 0,
31
+ "use_cache": true,
32
+ "vocab_size": 250880,
33
+ "weights_aggregation_strategy": "mean",
34
+ "width_downsampling_rate": 0.25
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ac3915371f4c6f8f57632f96a7f177f7c3ab5885d28989f02303eeb5dab1ff
3
+ size 332614039