tencent/HunyuanVideo
Text-to-Video
•
Updated
•
8.08k
•
1.44k
jbp
jensbosseparra
·
AI & ML interests
None yet
Recent Activity
liked
a model
11 days ago
tencent/HunyuanVideo
liked
a model
16 days ago
gokaygokay/Flux-Miniature-LoRA
liked
a model
4 months ago
mlx-community/pixtral-12b-8bit
Organizations
jensbosseparra's activity
liked
a
model
11 days ago
liked
a
model
16 days ago
liked
3
models
4 months ago
liked
6
models
5 months ago
mattshumer/Reflection-Llama-3.1-70B
Text Generation
•
Updated
•
617
•
1.71k
prithivMLmods/Canopus-LoRA-Flux-FaceRealism
Text-to-Image
•
Updated
•
10.6k
•
•
65
terminusresearch/flux-lokr-garfield-nomask
Text-to-Image
•
Updated
•
19
•
•
3
p1atdev/flux.1-schnell-pvc-style-lora
Text-to-Image
•
Updated
•
111
•
•
17
ostris/OpenFLUX.1
Text-to-Image
•
Updated
•
9.45k
•
609
markury/FLUX-dev-LoRA-test
Text-to-Image
•
Updated
•
37
•
•
1
reacted to
singhsidhukuldeep's
post with 🤗
8 months ago
Post
1031
You are happy that
@Meta
has open-sourced Llama 3 😃...
So you jump on @HuggingFace Hub to download the new shiny Llama 3 model only to see a few quintillion Llama 3's! 🦙✨
Which one should you use? 🤔
Not all Llamas are created equal! 🦙⚖️
An absolutely crazy comparison experiment by Wolfram Ravenwolf ( @Wolfram ) might answer your question! 🧪🧙♂️
- Comprehensive assessment of Llama 3 Instruct 70B and 8B models. 📊
- Tested 20 versions across HF, GGUF, and EXL2 formats. 🔄
- Methodology: The process tested translation capabilities and cross-language understanding, using deterministic generation settings to minimize random factors. Used German data protection training exams to evaluate cross-language understanding. 🌐📝
- Best performance from EXL2 4.5bpw quant, scoring perfect in all tests. 🏆✅
- GGUF 8-bit to 4-bit quants also performed exceptionally. 🌟
- Llama 3 8B unquantized is best in its size class but not as good as 70B quants. 📏🔍
- 1-bit quantizations showed significant quality drops. ⚠️⬇️
Best models:
- turboderp/Llama-3-70B-Instruct-exl2
- casperhansen/llama-3-70b-instruct-awq
Blog: https://huggingface.co/blog/wolfram/llm-comparison-test-llama-3
So you jump on @HuggingFace Hub to download the new shiny Llama 3 model only to see a few quintillion Llama 3's! 🦙✨
Which one should you use? 🤔
Not all Llamas are created equal! 🦙⚖️
An absolutely crazy comparison experiment by Wolfram Ravenwolf ( @Wolfram ) might answer your question! 🧪🧙♂️
- Comprehensive assessment of Llama 3 Instruct 70B and 8B models. 📊
- Tested 20 versions across HF, GGUF, and EXL2 formats. 🔄
- Methodology: The process tested translation capabilities and cross-language understanding, using deterministic generation settings to minimize random factors. Used German data protection training exams to evaluate cross-language understanding. 🌐📝
- Best performance from EXL2 4.5bpw quant, scoring perfect in all tests. 🏆✅
- GGUF 8-bit to 4-bit quants also performed exceptionally. 🌟
- Llama 3 8B unquantized is best in its size class but not as good as 70B quants. 📏🔍
- 1-bit quantizations showed significant quality drops. ⚠️⬇️
Best models:
- turboderp/Llama-3-70B-Instruct-exl2
- casperhansen/llama-3-70b-instruct-awq
Blog: https://huggingface.co/blog/wolfram/llm-comparison-test-llama-3
liked
a
model
10 months ago
liked
a
model
11 months ago
