RichardErkhov commited on
Commit
1ab8dee
1 Parent(s): 68cab98

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +47 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MultiPL-T-StarCoderBase_1b",
3
+ "activation_function": "gelu_pytorch_tanh",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 2048,
20
+ "n_head": 16,
21
+ "n_inner": 8192,
22
+ "n_layer": 24,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "quantization_config": {
27
+ "bits": 4,
28
+ "group_size": 128,
29
+ "modules_to_not_convert": null,
30
+ "quant_method": "awq",
31
+ "version": "gemm",
32
+ "zero_point": true
33
+ },
34
+ "resid_pdrop": 0.1,
35
+ "scale_attention_softmax_in_fp32": true,
36
+ "scale_attn_weights": true,
37
+ "summary_activation": null,
38
+ "summary_first_dropout": 0.1,
39
+ "summary_proj_to_labels": true,
40
+ "summary_type": "cls_index",
41
+ "summary_use_proj": true,
42
+ "torch_dtype": "float16",
43
+ "transformers_version": "4.46.2",
44
+ "use_cache": false,
45
+ "validate_runner_input": true,
46
+ "vocab_size": 49152
47
+ }