Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Edit Models filters
Tasks
Libraries
Datasets
Languages
Licenses
Other
1
Model Tree
Reset
aws-prototyping/MegaBeam-Mistral-7B-512k
Finetunes
Quantizations
Merges
Inference status
Reset Inference status
Warm
Cold
Frozen
Misc
Reset Misc
Inference Endpoints
AutoTrain Compatible
text-generation-inference
Eval Results
Merge
4-bit precision
custom_code
text-embeddings-inference
8-bit precision
Carbon Emissions
Mixture of Experts
Apply filters
Models
7
Full-text search
Edit filters
Sort: Trending
Active filters:
aws-prototyping/MegaBeam-Mistral-7B-512k
Clear all
PrunaAI/aws-prototyping-MegaBeam-Mistral-7B-512k-QUANTO-int8bit-smashed
Updated
Aug 17
•
8
PrunaAI/aws-prototyping-MegaBeam-Mistral-7B-512k-QUANTO-int4bit-smashed
Updated
Aug 17
•
8
PrunaAI/aws-prototyping-MegaBeam-Mistral-7B-512k-QUANTO-float8bit-smashed
Updated
Aug 17
•
8
PrunaAI/aws-prototyping-MegaBeam-Mistral-7B-512k-QUANTO-int2bit-smashed
Updated
Aug 17
•
8
PrunaAI/aws-prototyping-MegaBeam-Mistral-7B-512k-HQQ-1bit-smashed
Updated
Aug 17
•
9
PrunaAI/aws-prototyping-MegaBeam-Mistral-7B-512k-HQQ-2bit-smashed
Updated
Aug 17
•
9
PrunaAI/aws-prototyping-MegaBeam-Mistral-7B-512k-HQQ-4bit-smashed
Updated
Aug 17
•
9