Update README.md
Browse files
README.md
CHANGED
|
@@ -7,8 +7,6 @@ tags:
|
|
| 7 |
---
|
| 8 |
|
| 9 |
|
| 10 |
-
shoutout to https://huggingface.co/soob3123/amoral-gemma3-27B-v2-qat
|
| 11 |
-
|
| 12 |
Produces analytically neutral responses to sensitive queries
|
| 13 |
|
| 14 |
[NOTE!] Make sure to use chat completions endpoint and have a system message that says "You are an assistant"
|
|
@@ -21,6 +19,7 @@ messages = [
|
|
| 21 |
]
|
| 22 |
```
|
| 23 |
* **bfloat16 quantization:** Needs 4 H100s to run
|
|
|
|
| 24 |
|
| 25 |
# Inference Examples
|
| 26 |
|
|
@@ -38,3 +37,5 @@ If you don't have 4 H100s lying around try running this lora adapter in Mxfp4
|
|
| 38 |
https://huggingface.co/michaelwaves/gpt-120b-fun-weights
|
| 39 |
|
| 40 |
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
|
|
|
|
|
|
|
| 10 |
Produces analytically neutral responses to sensitive queries
|
| 11 |
|
| 12 |
[NOTE!] Make sure to use chat completions endpoint and have a system message that says "You are an assistant"
|
|
|
|
| 19 |
]
|
| 20 |
```
|
| 21 |
* **bfloat16 quantization:** Needs 4 H100s to run
|
| 22 |
+
* **finetuned from:** openai/gpt-oss-120b
|
| 23 |
|
| 24 |
# Inference Examples
|
| 25 |
|
|
|
|
| 37 |
https://huggingface.co/michaelwaves/gpt-120b-fun-weights
|
| 38 |
|
| 39 |
|
| 40 |
+
shoutout to https://huggingface.co/soob3123/amoral-gemma3-27B-v2-qat
|
| 41 |
+
|