Hugging Face's logo

TheBloke
/
Vicuna-33B-1-3-SuperHOT-8K-fp16

Text Generation
Transformers
PyTorch
llama
custom_code
text-generation-inference
Model card Files Community
1
TheBloke commited on
Commit
0b64846
•
1 Parent(s): 19e4bab

Fix model description

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -19,7 +19,7 @@ license: other
19
 
20
  # LmSys' Vicuna 33B 1.3 (final) fp16
21
 
22
- These files are GPTQ 4bit model files for [LmSys' Vicuna 33B 1.3 (final)](https://huggingface.co/lmsys/vicuna-33b-v1.3) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test).
23
 
24
  [Kaio Ken's SuperHOT 30b LoRA](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
25
 
 
19
 
20
  # LmSys' Vicuna 33B 1.3 (final) fp16
21
 
22
+ This is fp16 pytorch format model files for [LmSys' Vicuna 33B 1.3 (final)](https://huggingface.co/lmsys/vicuna-33b-v1.3) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test).
23
 
24
  [Kaio Ken's SuperHOT 30b LoRA](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
25