Hugging Face's logo

djuna
/
DeepSeek-R1-Distill-Qwen-14B-abliterated-remap

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
text-generation-inference
Model card Files Community
1
DeepSeek-R1-Distill-Qwen-14B-abliterated-remap
File size: 2,797 Bytes 
7c6438e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
---
base_model:
- djuna/Q2.5-Veltha-14B-0.5
- huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
library_name: transformers
tags:
- mergekit
- merge

---
# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.

### Models Merged

The following models were included in the merge:
* [djuna/Q2.5-Veltha-14B-0.5](https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5)
* [huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
  - model: djuna/Q2.5-Veltha-14B-0.5
merge_method: slerp
base_model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
parameters:
  t: 0
tokenizer:
  source: "djuna/Q2.5-Veltha-14B-0.5"
  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
```