Skip to content

Commit

Permalink
updated text
Browse files Browse the repository at this point in the history
  • Loading branch information
kunalchamoli committed Feb 19, 2024
1 parent 3dd4741 commit 5ece1bb
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion index.html
Original file line number Diff line number Diff line change
Expand Up @@ -208,7 +208,7 @@ <h3 class="ds-work-tilte"> <a href="https://huggingface.co/spaces/kunalchamoli/p
<div class="col-12 col-sm-12 col-md-7 col-lg-7 col-xl-7 col-xxl-7">
<section>
<h3 class="ds-work-tilte">Fine-Tuning and Hosting Mistral-7B using TGI</a></h3>
<p>Fine-Tuned a 7billion parameter model using huggingface on a 24GB VRAM A10g. The process involved creation of synthetic dataset using GPT4 APIs, which was cleaned before undergoing Parameter-Efficient Fine-Tuning (PEFT) on our systems. This process leveraged advanced quantization methods provided by quantization techinques from <a href="https://huggingface.co/blog/4bit-transformers-bitsandbytes"> bits and bytes </a> and <a href="https://mlabonne.github.io/blog/posts/A_Beginners_Guide_to_LLM_Finetuning.html">Axotol</a>.
<p>Fine-Tuned a 7billion parameter model using huggingface on a 24GB VRAM A10g. The process involved creation of synthetic dataset using GPT4 APIs, which was cleaned before undergoing Parameter-Efficient Fine-Tuning (PEFT) on our systems. This process leveraged advanced quantization methods provided from <a href="https://huggingface.co/blog/4bit-transformers-bitsandbytes"> bits and bytes </a> and <a href="https://mlabonne.github.io/blog/posts/A_Beginners_Guide_to_LLM_Finetuning.html">Axotol</a>.
<br>The Model will be hosted using <a href = "https://huggingface.co/docs/text-generation-inference/en/index"> TGI </a>framework by huggingface.
</p>
<!-- <a href="works-setails.html" class="ds-button">Details</a> -->
Expand Down

0 comments on commit 5ece1bb

Please sign in to comment.