loubnabnl HF staff commited on
Commit
ade8484
1 Parent(s): 3730921

iter_0050000

Browse files
Files changed (3) hide show
  1. config.json +39 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/fsx/bigcode/tinystarcoder/saves/large-model",
3
+ "activation_function": "gelu_pytorch_tanh",
4
+ "architectures": [
5
+ "GPTBigCodeLMHeadModel"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attention_type": 2,
9
+ "attn_pdrop": 0.1,
10
+ "bos_token_id": 50256,
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 50256,
13
+ "inference_runner": 0,
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "max_batch_size": null,
17
+ "max_sequence_length": null,
18
+ "model_type": "gpt_bigcode",
19
+ "n_embd": 768,
20
+ "n_head": 12,
21
+ "n_inner": 3072,
22
+ "n_layer": 20,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "resid_pdrop": 0.1,
27
+ "scale_attention_softmax_in_fp32": true,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.27.0.dev0",
36
+ "use_cache": true,
37
+ "validate_runner_input": true,
38
+ "vocab_size": 49152
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.27.0.dev0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55e857a0305b1975b3db160253c8ad9604c6cea2f176cc8e41f82b70025cb884
3
+ size 656652573