Hugging Face's logo

Apel-sin
/
llama-3-NeuralDaredevil-8B-abliterated-exl2

Transformers
Inference Endpoints
Model card Files Community
1
Apel-sin commited on
Commit
07da86e
•
1 Parent(s): 5fba40a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -14,7 +14,6 @@ Original model: <a href="https://huggingface.co/mlabonne/NeuralDaredevil-8B-abli
14
  Calibration dataset: <a href="https://huggingface.co/datasets/cosmicvalor/toxic-qna">toxic-qna</a>
15
 
16
  ## Available sizes
17
-
18
  | Branch | Bits | lm_head bits | Description |
19
  | ----- | ---- | ------- | ------------ |
20
  | [8_0](https://huggingface.co/Apel-sin/llama-3-NeuralDaredevil-8B-abliterated-exl2/tree/8_0) | 8.0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
 
14
  Calibration dataset: <a href="https://huggingface.co/datasets/cosmicvalor/toxic-qna">toxic-qna</a>
15
 
16
  ## Available sizes
 
17
  | Branch | Bits | lm_head bits | Description |
18
  | ----- | ---- | ------- | ------------ |
19
  | [8_0](https://huggingface.co/Apel-sin/llama-3-NeuralDaredevil-8B-abliterated-exl2/tree/8_0) | 8.0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |