Here are a few GGUF(v2) quantizations of the model conceptofmind/Open-LLongMA-3b
Which is Based on: openlm-research/open_llama_3b
Open LLongMA 3B is a language model trained to have 8192 tokens of context size using linear rope_scaling 0.25, Using 1.0 it will output gibberish.
- Downloads last month
- 126