Updating llama 2 7b to llama 3.1 8b Instruct and adding new LoRA adapters #578
Conversation
k8s-ci-robot
added
the
cncf-cla: yes
k8s-ci-robot
added
approved
✅ Deploy Preview for gateway-api-inference-extension ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
| - '{"name": "tweet-summary-0", "path": "vineetsharma/qlora-adapter-Llama-2-7b-hf-TweetSumm", "base_model_name": "llama-2"}' | ||
| - '{"name": "tweet-summary-1", "path": "vineetsharma/qlora-adapter-Llama-2-7b-hf-TweetSumm", "base_model_name": "llama-2"}' | ||
| # List of adapters for llama3.1-8b-instruct if these examples aren't preferred: | ||
| # https://huggingface.co/models?other=base_model:adapter:meta-llama%2FLlama-3.1-8B-Instruct&sort=downloads |
There was a problem hiding this comment.
This is where I sourced the adapters from, I tried to pick some innocuous ones.
There was a problem hiding this comment.
You picked llama 3.1 because there were no 3.3 lora adapters?
There was a problem hiding this comment.
3.1 just cause it was the version that had a model in the size class reasonably close to what we have benchmarked:
|
/lgtm |
k8s-ci-robot
added
the
lgtm
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: ahg-g, kfswain The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
Scrutiny here would be appreciated, this touches quite a bit of our documentation