intfloat/mmE5-mllama-11b-instruct
Zero-Shot Image Classification
β’
Updated
β’
5.38k
β’
17
Simeon Emanuilov PRO
s-emanuilov
AI & ML interests
Software Engineer & Ph.D. candidate | Specializing in ML/DL system development & applying AI to solve real-world business problems.
Recent Activity
liked
a model
15 days ago
intfloat/mmE5-mllama-11b-instruct
liked
a Space
16 days ago
nanotron/ultrascale-playbook
upvoted
an
article
16 days ago
PaliGemma 2 Mix - New Instruction Vision Language Models by Google
Organizations
s-emanuilov's activity
liked
a
model
15 days ago
liked
a
Space
16 days ago
upvoted
2
articles
16 days ago
Article
PaliGemma 2 Mix - New Instruction Vision Language Models by Google
β’
65
Article
SigLIP 2: A better multilingual vision language encoder
β’
130
liked
2
models
28 days ago
upvoted
an
article
28 days ago
Article
Merge Large Language Models with mergekit
By
β’
β’
102
liked
3
models
28 days ago
replied to
their
post
29 days ago
try to reduce gpu_memory_utilization to some lower coefficient
upvoted
a
paper
about 1 month ago
replied to
their
post
about 1 month ago
Thank you.
Iβm also a big fan of Qwen models. However, in this case, I donβt think they are appropriate because Iβm not entirely confident in their capabilities regarding multilingual contexts. Thatβs why I chose Llama.
Overall, I agree that the Qwen series is excellent for most tasks.
posted
an
update
about 1 month ago
Post
5189
Tutorial π₯ Training a non-English reasoning model with GRPO and Unsloth
I wanted to share my experiment with training reasoning models in languages other than English/Chinese.
Using Llama 3.1 8B as base, GRPO trainer from trl, and Unsloth optimizations, I got a working prototype in Bulgarian after ~5 hours on an L40S GPU. The approach should work for any language where the base model has some pre-training coverage.
Full code and tutorial here: https://unfoldai.com/reasoning-in-a-non-english-language/
The model itself: s-emanuilov/LLMBG-Llama-3.1-8B-BG-Reasoning-v0.1
I hope this helps anyone looking to build reasoning models in their language.
I wanted to share my experiment with training reasoning models in languages other than English/Chinese.
Using Llama 3.1 8B as base, GRPO trainer from trl, and Unsloth optimizations, I got a working prototype in Bulgarian after ~5 hours on an L40S GPU. The approach should work for any language where the base model has some pre-training coverage.
Full code and tutorial here: https://unfoldai.com/reasoning-in-a-non-english-language/
The model itself: s-emanuilov/LLMBG-Llama-3.1-8B-BG-Reasoning-v0.1
I hope this helps anyone looking to build reasoning models in their language.
-
- 4 replies
updated
a
model
about 1 month ago
upvoted
a
paper
about 1 month ago
published
a
model
about 1 month ago
liked
a
model
about 1 month ago
updated
a
model
about 1 month ago
upvoted
a
paper
about 1 month ago