Downloads · 30 days
24
15% of all-time downloads
DeepSeek-R1-Distill-Qwen-14B-abliterated-remap
djuna/DeepSeek-R1-Distill-Qwen-14B-abliterated-remap
DeepSeek-R1-Distill-Qwen-14B-abliterated-remap is a text generation model from djuna. Use it when you need the model to write or continue text. It is set up for transformers.
This is a merge of pre-trained language models created using mergekit.
All-time downloads
163
Public
Parameters
14.8B
29.5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors29.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen2
- Access
- Public
- Created
- Mar 11, 2025
- Updated
- Mar 11, 2025
- SHA
- 9ecbcc49
Try a prompt
Base models
Model card
From the Hugging Face model README
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
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
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- Created
- Mar 11, 2025
- Updated
- Mar 11, 2025