RichardErkhov commited on
Commit
1229ded
·
verified ·
1 Parent(s): eb505e3

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +43 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "phi3-mini-python-code-20k",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 4096,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 32000,
25
+ "quantization_config": {
26
+ "bits": 4,
27
+ "group_size": 128,
28
+ "modules_to_not_convert": null,
29
+ "quant_method": "awq",
30
+ "version": "gemm",
31
+ "zero_point": true
32
+ },
33
+ "resid_pdrop": 0.0,
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": null,
36
+ "rope_theta": 10000.0,
37
+ "sliding_window": 2047,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.46.3",
41
+ "use_cache": false,
42
+ "vocab_size": 32011
43
+ }