huizimao commited on
Commit
0009cc1
·
verified ·
1 Parent(s): 51aaed8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -7,6 +7,9 @@ base_model:
7
  This is the BF16 version and cannot be hosted with vLLM. TensorRT-LLM is supported but not tested.
8
  For the MXFP4 version that is vLLM compatible, check out [gpt-oss-20b-uncensored-mxfp4](https://huggingface.co/huizimao/gpt-oss-20b-uncensored-mxfp4/)
9
 
 
 
 
10
  Finetuning is done by LoRA on [Amazon FalseReject](https://huggingface.co/datasets/AmazonScience/FalseReject) train set with 800 samples.
11
 
12
  PTQ is done with [NVIDIA ModelOpt](https://github.com/NVIDIA/TensorRT-Model-Optimizer)
 
7
  This is the BF16 version and cannot be hosted with vLLM. TensorRT-LLM is supported but not tested.
8
  For the MXFP4 version that is vLLM compatible, check out [gpt-oss-20b-uncensored-mxfp4](https://huggingface.co/huizimao/gpt-oss-20b-uncensored-mxfp4/)
9
 
10
+ GGUF available at [gpt-oss-20b-uncensored-bf16-GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-uncensored-bf16-GGUF) (Thanks to team mradermacher)
11
+
12
+
13
  Finetuning is done by LoRA on [Amazon FalseReject](https://huggingface.co/datasets/AmazonScience/FalseReject) train set with 800 samples.
14
 
15
  PTQ is done with [NVIDIA ModelOpt](https://github.com/NVIDIA/TensorRT-Model-Optimizer)