Yarn-Llama-2-70B-32k-GGUF
TheBloke/Yarn-Llama-2-70B-32k-GGUF
- kind
- gguf
- quant
- gguf (2-bit)
- family
- llama
- modality
- —
- root model
- NousResearch/Yarn-Llama-2-70b-32k
- provider
- TheBloke
- license
- apache-2.0
- language
- en
- context
- 32k
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 426
- likes
- 9
- created
- —
- last modified
- 2023-11-20T22:31:30+00:00 (2023)
- huggingface
- https://huggingface.co/TheBloke/Yarn-Llama-2-70B-32k-GGUF
- tags
- transformersggufllamaendataset:emozilla/yarn-train-tokenized-8k-llamaarxiv:2309.00071base_model:NousResearch/Yarn-Llama-2-70b-32kbase_model:quantized:NousResearch/Yarn-Llama-2-70b-32klicense:apache-2.0region:us
Benchmark scores (1)
Discussions (0)
none scraped.