issues Search Results · repo:GeneZC/MiniMA language:Python
Filter by
6 results
(60 ms)6 results
inGeneZC/MiniMA (press backspace or delete to remove)granite-7b-base is a reproduction of llama-2-7b, but with a more permissive license.
linux-leo
- Opened on Jun 27, 2024
- #7
@GeneZC Why the inference latency of model MiniMA-3B is longer than model Llama-7B: image image
qxpBlog
- 23
- Opened on Apr 15, 2024
- #6
Hi, happy new year!!
Good work, first of all!! I am trying to use MiniChat-3B as an interactive Chatbot in my application. However, the
response from the model either returns
1. ? or nothing
2. I am ...
rsong0606
- 2
- Opened on Jan 6, 2024
- #5
Can you please release code for upcycling LLMs to make MoEs? I have a use-case for multi-lingual LLMs where this would
be incredibly helpful!
enhancement
ojus1
- 1
- Opened on Dec 31, 2023
- #4
Mistral-7b is a much better model (and perhaps a teacher) than Llama-2-7b. Would you kindly release checkpoints for a
distilled mistral? Would greatly appreciate it!
enhancement
wontfix
- 1
- Opened on Dec 30, 2023
- #3
Trying with the llama2 base weights.
I get the following error:
File /root/MiniMA/minima/modules/flash_attn_monkey_patch_sparsellama.py , line 47, in forward
assert not use_cache, use_cache is ...
good first issue
l3utterfly
- 27
- Opened on Dec 2, 2023
- #2
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.