Qwen2.5
Collection
Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B.
โข
45 items
โข
Updated
โข
392
M Veselovskiy
Yuuru
AI & ML interests
None yet
Recent Activity
New activity
about 1 month ago
TheDrummer/UnslopSmall-22B-v1-GGUF:Metharme format makes model extremely stupid
Organizations
Yuuru's activity
Metharme format makes model extremely stupid
2
#1 opened about 1 month ago
by
Ainonake
Ainonake
upvoted
a
collection
2 months ago
How to pay
1
#17 opened 2 months ago
by
Yuuru
Yuuru
DLETE THIS MODEL
2
#76 opened 3 months ago
by
MaziyarPanahi
MaziyarPanahi
Reacted to
m-ric's
post with ๐
3 months ago
Post
1912
๐คฏ ๐ ๐ป๐ฒ๐ ๐ณ๐ฌ๐ ๐ผ๐ฝ๐ฒ๐ป-๐๐ฒ๐ถ๐ด๐ต๐๐ ๐๐๐ ๐ฏ๐ฒ๐ฎ๐๐ ๐๐น๐ฎ๐๐ฑ๐ฒ-๐ฏ.๐ฑ-๐ฆ๐ผ๐ป๐ป๐ฒ๐ ๐ฎ๐ป๐ฑ ๐๐ฃ๐ง-๐ฐ๐ผ!
@mattshumer , CEO from Hyperwrite AI, had an idea he wanted to try out: why not fine-tune LLMs to always output their thoughts in specific parts, delineated by <thinking> tags?
Even better: inside of that, you could nest other sections, to reflect critically on previous output. Letโs name this part <reflection>. Planning is also put in a separate step.
He named the method โReflection tuningโ and set out to fine-tune a Llama-3.1-70B with it.
Well it turns out, it works mind-boggingly well!
๐คฏ Reflection-70B beats GPT-4o, Sonnet-3.5, and even the much bigger Llama-3.1-405B!
๐ง๐;๐๐ฅ
๐ฅ This new 70B open-weights model beats GPT-4o, Claude Sonnet, et al.
โฐ 405B in training, coming soon
๐ Report coming next week
โ๏ธ Uses GlaiveAI synthetic data
๐ค Available on HF!
Iโm starting an Inference Endpoint right now for this model to give it a spin!
Check it out ๐ mattshumer/Reflection-Llama-3.1-70B
@mattshumer , CEO from Hyperwrite AI, had an idea he wanted to try out: why not fine-tune LLMs to always output their thoughts in specific parts, delineated by <thinking> tags?
Even better: inside of that, you could nest other sections, to reflect critically on previous output. Letโs name this part <reflection>. Planning is also put in a separate step.
He named the method โReflection tuningโ and set out to fine-tune a Llama-3.1-70B with it.
Well it turns out, it works mind-boggingly well!
๐คฏ Reflection-70B beats GPT-4o, Sonnet-3.5, and even the much bigger Llama-3.1-405B!
๐ง๐;๐๐ฅ
๐ฅ This new 70B open-weights model beats GPT-4o, Claude Sonnet, et al.
โฐ 405B in training, coming soon
๐ Report coming next week
โ๏ธ Uses GlaiveAI synthetic data
๐ค Available on HF!
Iโm starting an Inference Endpoint right now for this model to give it a spin!
Check it out ๐ mattshumer/Reflection-Llama-3.1-70B
- 3 replies
Broken results
3
#1 opened 6 months ago
by
Yuuru
Yuuru
liked
a
model
7 months ago
liked
a
Space
7 months ago
Quantized GGUF available
3
#3 opened 9 months ago
by
MaziyarPanahi
MaziyarPanahi
liked
a
model
10 months ago
KingSlayer49
It works!!!
7
#1 opened 12 months ago
by
HoangHa
HoangHa
It works.
6
#3 opened 12 months ago
by
Yuuru
Yuuru
How is this different from v1?
7
#2 opened 12 months ago
by
amgadhasan
amgadhasan
What is this model?
3
#1 opened 12 months ago
by
Yuuru
Yuuru
Did anyone figured it out how to run it in low vRAM like 15-25 GB
5
#21 opened about 1 year ago
by
zohadev
zohadev
upvoted
a
collection
about 1 year ago
How do i run it?
4
#2 opened about 1 year ago
by
Yuuru
Yuuru
liked
a
Space
over 1 year ago
liked
a
model
over 1 year ago
