DavidGF commited on
Commit
a131825
·
verified ·
1 Parent(s): 9ecf602

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +22 -35
config.json CHANGED
@@ -1,44 +1,31 @@
1
  {
2
- "_name_or_path": "Qwen/Qwen1.5-0.5B",
3
- "architectures": [
4
- "Qwen2ForSequenceClassification"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151643,
9
- "hidden_act": "silu",
10
- "hidden_size": 1024,
11
- "id2label": {
12
- "0": "LABEL_0",
13
- "1": "LABEL_1",
14
- "2": "LABEL_2",
15
- "3": "LABEL_3",
16
- "4": "LABEL_4"
17
  },
18
- "initializer_range": 0.02,
19
- "intermediate_size": 2816,
20
- "label2id": {
 
 
 
 
 
 
 
 
 
 
 
21
  "LABEL_0": 0,
22
  "LABEL_1": 1,
23
  "LABEL_2": 2,
24
  "LABEL_3": 3,
25
  "LABEL_4": 4
26
  },
27
- "max_position_embeddings": 32768,
28
- "max_window_layers": 21,
29
- "model_type": "qwen2",
30
- "num_attention_heads": 16,
31
- "num_hidden_layers": 24,
32
- "num_key_value_heads": 16,
33
- "pad_token_id": 151643,
34
- "problem_type": "single_label_classification",
35
- "rms_norm_eps": 1e-06,
36
- "rope_theta": 1000000.0,
37
- "sliding_window": 32768,
38
- "tie_word_embeddings": true,
39
- "torch_dtype": "float32",
40
- "transformers_version": "4.41.0",
41
- "use_cache": true,
42
- "use_sliding_window": false,
43
- "vocab_size": 151936
44
  }
 
1
  {
2
+ "tokenizers": {
3
+ "lora_expert1": "Llama-3-Smaug-8B-adapter",
4
+ "lora_expert2": "Meta-Llama-3-8B-Instruct-function-calling-json-mode-adapter",
5
+ "lora_expert3": "Llama-3-8B-Instruct-Coder-adapter",
6
+ "lora_expert4": "llama-3-sqlcoder-8b-adapter",
7
+ "lora_expert5": "Llama-3-SauerkrautLM-8b-Instruct-adapter"
 
 
 
 
 
 
 
 
 
8
  },
9
+ "models": {
10
+ "base": "meta-llama/Meta-Llama-3-8B-Instruct"
11
+ },
12
+ "lora_adapters": {
13
+ "lora_expert1": "Llama-3-Smaug-8B-adapter",
14
+ "lora_expert2": "Meta-Llama-3-8B-Instruct-function-calling-json-mode-adapter",
15
+ "lora_expert3": "Llama-3-8B-Instruct-Coder-adapter",
16
+ "lora_expert4": "llama-3-sqlcoder-8b-adapter",
17
+ "lora_expert5": "Llama-3-SauerkrautLM-8b-Instruct-adapter"
18
+ },
19
+ "quantization": {
20
+ "base": null
21
+ },
22
+ "class_indices": {
23
  "LABEL_0": 0,
24
  "LABEL_1": 1,
25
  "LABEL_2": 2,
26
  "LABEL_3": 3,
27
  "LABEL_4": 4
28
  },
29
+ "router": "../kraken_router",
30
+ "model_type": "kraken"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  }