Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[pull] main from mlc-ai:main #17

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

[pull] main from mlc-ai:main #17

wants to merge 7 commits into from

Conversation

pull[bot]
Copy link

@pull pull bot commented Dec 9, 2024

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.1)

Can you help keep this open source service alive? 💖 Please sponsor : )

@pull pull bot added the ⤵️ pull label Dec 9, 2024
Neet-Nestor and others added 6 commits December 9, 2024 01:30
This PR adds the following models to the prebuilt list:

- `DeepSeek-R1-Distill-Qwen-7B-q4f16_1-MLC`
- `DeepSeek-R1-Distill-Qwen-7B-q4f32_1-MLC`
- `DeepSeek-R1-Distill-Llama-8B-q4f16_1-MLC`
- `DeepSeek-R1-Distill-Llama-8B-q4f32_1-MLC`
- `Hermes-3-Llama-3.2-3B-q4f16_1-MLC`
- `Hermes-3-Llama-3.2-3B-q4f32_1-MLC`

We will add `DeepSeek-R1-Distill-Qwen-1.5B` afterward, which is
currently experiencing correctness issues.

Separately, we fix the handling of `role_content_sep` and
`role_empty_sep` when it is `""`, which evaluates to false (currently we
make it `": "`, which is inconsistent with what the model expects).
### Change

- The only change is #652, adding
the following models:
  - `DeepSeek-R1-Distill-Qwen-7B-q4f16_1-MLC`
  - `DeepSeek-R1-Distill-Qwen-7B-q4f32_1-MLC`
  - `DeepSeek-R1-Distill-Llama-8B-q4f16_1-MLC`
  - `DeepSeek-R1-Distill-Llama-8B-q4f32_1-MLC`
  - `Hermes-3-Llama-3.2-3B-q4f16_1-MLC`
  - `Hermes-3-Llama-3.2-3B-q4f32_1-MLC`

### TVMjs
- No change, version `0.18.0-dev2` just like 0.2.71
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants