DavidGF commited on
Commit
c485a63
1 Parent(s): 7e9bd37

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json CHANGED
@@ -1,31 +1,44 @@
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/kraken_router",
30
- "model_type": "kraken"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0462ee8274d9aab1297d68d7363e40940d90fd274cb2679c4790fdf4371f2808
3
+ size 1856004208
special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": "<|endoftext|>"
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff