Hugging Face's logo

serpdotai
/
sparsetral-16x7B-v2-SPIN_iter0

Text Generation
Transformers
Safetensors
English
sparsetral
conversational
custom_code
Inference Endpoints
Model card Files Community
3
francislabounty commited on
Commit
05ea159
•
1 Parent(s): 93c3fdc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -10,6 +10,9 @@ language:
10
  ---
11
  This model is [sparsetral-16x7B-v2](https://huggingface.co/serpdotai/sparsetral-16x7B-v2) further tuned utilizing [SPIN](https://arxiv.org/abs/2401.01335) on [OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5) mixed with traditional DPO samples. This is iteration_0, plan to keep making iterations until improvements stop.
12
 
 
 
 
13
  ## Training
14
  - 8x A6000s
15
  - Base model is [sparsetral-16x7B-v2](https://huggingface.co/serpdotai/sparsetral-16x7B-v2)
 
10
  ---
11
  This model is [sparsetral-16x7B-v2](https://huggingface.co/serpdotai/sparsetral-16x7B-v2) further tuned utilizing [SPIN](https://arxiv.org/abs/2401.01335) on [OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5) mixed with traditional DPO samples. This is iteration_0, plan to keep making iterations until improvements stop.
12
 
13
+ Kuru~ Kuru~
14
+ ![Kuru~ Kuru~](https://github.com/duiqt/herta_kuru/raw/main/static/img/hertaa_github.gif)
15
+
16
  ## Training
17
  - 8x A6000s
18
  - Base model is [sparsetral-16x7B-v2](https://huggingface.co/serpdotai/sparsetral-16x7B-v2)