ahmed-masry/ColFlor
Updated
•
1.82k
•
18
Paul Lemaistre PRO
paulml
AI & ML interests
TTS - LLM - Agents |
Lead Dev @ TW3 Partners
Recent Activity
liked
a model
2 months ago
ahmed-masry/ColFlor
updated
a model
3 months ago
paulml/mcdse-2b-v1-AWQ
updated
a model
4 months ago
paulml/Qwen2.5-Coder-78B-Instruct
Organizations
paulml's activity
liked
a
model
2 months ago
updated
a
model
3 months ago
updated
a
model
4 months ago
updated
a
model
6 months ago
Adding Evaluation Results
#1 opened 6 months ago
by
leaderboard-pr-bot
Results for internlm/internlm2_5-7b-chat
#3 opened 6 months ago
by
paulml
reacted to
FeYuan's
post with 👍
6 months ago
Post
4766
Hi everyone,
I am excited to introduce our latest work, LLaMAX. 😁😁😁
LLaMAX is a powerful language model created specifically for multilingual scenarios. Built upon Meta's LLaMA series models, LLaMAX undergoes extensive training across more than 100 languages.
Remarkably, it enhances its multilingual capabilities without compromising its generalization ability, surpassing existing LLMs.
✨Highlights:
🎈 LLaMAX supports the 102 languages covered by Flores-101, and its performance in translating between low-resource languages far surpasses other decoder-only LLMs.
🎈 Even for languages not covered in Flores-200, LLaMAX still shows significant improvements in translation performance.
🎈 By performing simple SFT on English task data, LLaMAX demonstrates impressive multilingual transfer abilities in downstream tasks.
🎈 In our paper, we discuss effective methods for enhancing the multilingual capabilities of LLMs during the continued training phase.
We welcome you to use our model and provide feedback.
More Details:
🎉 Code: https://github.com/CONE-MT/LLaMAX/
🎉 Model: https://huggingface.co/LLaMAX/
I am excited to introduce our latest work, LLaMAX. 😁😁😁
LLaMAX is a powerful language model created specifically for multilingual scenarios. Built upon Meta's LLaMA series models, LLaMAX undergoes extensive training across more than 100 languages.
Remarkably, it enhances its multilingual capabilities without compromising its generalization ability, surpassing existing LLMs.
✨Highlights:
🎈 LLaMAX supports the 102 languages covered by Flores-101, and its performance in translating between low-resource languages far surpasses other decoder-only LLMs.
🎈 Even for languages not covered in Flores-200, LLaMAX still shows significant improvements in translation performance.
🎈 By performing simple SFT on English task data, LLaMAX demonstrates impressive multilingual transfer abilities in downstream tasks.
🎈 In our paper, we discuss effective methods for enhancing the multilingual capabilities of LLMs during the continued training phase.
We welcome you to use our model and provide feedback.
More Details:
🎉 Code: https://github.com/CONE-MT/LLaMAX/
🎉 Model: https://huggingface.co/LLaMAX/
- 3 replies
reacted to
clem's
post with ❤️
7 months ago
Post
5781
5,000 new repos (models, datasets, spaces) are created EVERY DAY on HF now. The community is amazing!
liked
a
model
7 months ago
updated
a
model
7 months ago
updated
a
dataset
9 months ago
updated
a
model
9 months ago
update config.json vocab_size to tokenizer length
5
#1 opened 10 months ago
by
sparsh35
updated
a
model
10 months ago
How to use this to create a specific writing style of the conversation?
1
#7 opened 10 months ago
by
paulml
Great model
2
#4 opened 11 months ago
by
RedLeader721
What a score!
#2 opened 11 months ago
by
paulml
The model is not performing well.
25
#1 opened 11 months ago
by
Liangmingxin
updated
2
models
11 months ago