DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters
Updated
ā¢
25
Raven
raveninrhythm
AI & ML interests
None yet
Recent Activity
liked
a model
about 4 hours ago
DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters
upvoted
a
collection
about 10 hours ago
200+ Roleplay, Creative Writing, Uncensored, NSFW models.
New activity
about 13 hours ago
DavidAU/L3-Grand-HORROR-20.7B-V1.9-STABLE-Hathors-Revenge-GGUF:Weird pronoun and anatomy issues
Organizations
None yet
raveninrhythm's activity
liked
a
model
about 4 hours ago
upvoted
a
collection
about 10 hours ago
Weird pronoun and anatomy issues
7
#2 opened 3 months ago
by
raveninrhythm
raveninrhythm
liked
a
model
2 months ago
liked
2
models
3 months ago
liked
2
models
4 months ago
Reacted to
fdaudens's
post with š¤š„
4 months ago
Post
3288
Small models, BIG impact: SmolLM is here! šš¬
We're launching a series of small but mighty language models:
šļø Super fast - runs on laptops, phones, you name it!
š 3 sizes: 130M, 350M, and 1.5B parameters
š„ Outperforms same size models from Meta, Microsoft, and Qwen
š Fully open-source: datasets, training code, models
ššš² ššššš®š«šš¬
- Trained on FineWeb-Edu and Cosmopedia v2 (largest synthetic pre-training dataset)
- No cloud needed - run locally for privacy and energy efficiency
- Everything is public, from data curation to training steps
ššØššš§šš¢šš„ š®š¬š ššš¬šš¬
- On-device autocomplete
- Local request parsing
- Custom fine-tuning for specific needs without the need for expensive GPUs
ššØ šššš©šš«
š Check it out: https://huggingface.co/collections/HuggingFaceTB/smollm-models-6695016cad7167254ce15966
š Run the 360M model in your browser, 100 % private: HuggingFaceTB/SmolLM-360M-Instruct-WebGPU
š Read the blog explaining everything in detail: huggingface.co/blog/smollm
Kudos to the stellar team who worked on this project: @loubnabnl @anton-l @eliebak @lvwerra
We're launching a series of small but mighty language models:
šļø Super fast - runs on laptops, phones, you name it!
š 3 sizes: 130M, 350M, and 1.5B parameters
š„ Outperforms same size models from Meta, Microsoft, and Qwen
š Fully open-source: datasets, training code, models
ššš² ššššš®š«šš¬
- Trained on FineWeb-Edu and Cosmopedia v2 (largest synthetic pre-training dataset)
- No cloud needed - run locally for privacy and energy efficiency
- Everything is public, from data curation to training steps
ššØššš§šš¢šš„ š®š¬š ššš¬šš¬
- On-device autocomplete
- Local request parsing
- Custom fine-tuning for specific needs without the need for expensive GPUs
ššØ šššš©šš«
š Check it out: https://huggingface.co/collections/HuggingFaceTB/smollm-models-6695016cad7167254ce15966
š Run the 360M model in your browser, 100 % private: HuggingFaceTB/SmolLM-360M-Instruct-WebGPU
š Read the blog explaining everything in detail: huggingface.co/blog/smollm
Kudos to the stellar team who worked on this project: @loubnabnl @anton-l @eliebak @lvwerra
liked
2
models
5 months ago
liked
a
dataset
5 months ago
liked
a
model
7 months ago
liked
4
models
9 months ago
liked
2
models
about 1 year ago
