llama : add Deepseek support

[ggerganov]

Support is almost complete. There is a dangling issue with the pre-tokenizer: #7036

A useful discussion related to that is here: #7144

---

Outdated below

Creating this issue for more visibility

The main problem is around tokenization support, since the models use some variation of the BPE pre-processing regex. There are also some issues with the conversion scripts.

Anyway, looking for contributions to help with this

Previous unfinished work:

• Update gpt2 preprocess and add deepseek coder preprocess #4070
• Deepseek coder merge #5464

Possible implementation plan: #5464 (comment)

[dragnil1]

Hello, @ggerganov, I'd like to try working on it as my good first issue.

[ggerganov]

Ok 👍 keep us posted

[Kangmo]

Waiting for this to come. deepseek model is famouse for coding well and Korean language ability.

[fostiropoulos]

In the supported models there is Deepseek. I am able to use DeepSeekCoder-33B with comparatively similar results to their API. Can someone please clarify what are the failure cases with the current tokenization?