Commit
•
a684dd0
1
Parent(s):
6eed56a
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,9 @@ tags:
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# byroneverson/glm-4-9b-chat-abliterated-gguf
|
|
|
|
|
|
|
|
|
|
| 22 |
This model was converted to GGUF format from [`byroneverson/glm-4-9b-chat-abliterated`](https://huggingface.co/byroneverson/glm-4-9b-chat-abliterated) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 23 |
Refer to the [original model card](https://huggingface.co/byroneverson/glm-4-9b-chat-abliterated) for more details on the model.
|
| 24 |
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# byroneverson/glm-4-9b-chat-abliterated-gguf
|
| 22 |
+
|
| 23 |
+
## Version 1.1 (Updated 9/1/2024): Layer 17 is used for abliteration instead of 16. Refusal mitigation tends to work better with this layer. PCA and cosine similarity tests seem to agree.
|
| 24 |
+
|
| 25 |
This model was converted to GGUF format from [`byroneverson/glm-4-9b-chat-abliterated`](https://huggingface.co/byroneverson/glm-4-9b-chat-abliterated) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 26 |
Refer to the [original model card](https://huggingface.co/byroneverson/glm-4-9b-chat-abliterated) for more details on the model.
|
| 27 |
|