Hugging Face's logo

djuna
/
TEST2-Q2.5-Lenned-14B

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
text-generation-inference
Model card Files Community
1
TEST2-Q2.5-Lenned-14B
File size: 2,050 Bytes 
1b2989f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
 
models:
  - model: Qwen/Qwen2.5-14B
  - model: netease-youdao/Confucius-o1-14B
  - model: djuna/Q2.5-Veltha-14B-0.5
  - model: Krystalan/DRT-o1-14B
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
merge_method: sce
base_model: Qwen/Qwen2.5-14B
tokenizer:
  source: "union"
  tokens: 
    <|endoftext|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|im_start|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|im_end|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|object_ref_start|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|object_ref_end|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|box_start|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|box_end|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <｜end▁of▁sentence｜>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
    <|EOT|>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<|EOT|>"
      force: true
    <think>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<think>"
      force: true
    </think>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "</think>"
      force: true
dtype: float32
out_dtype: bfloat16