OLMo-1.7-7B-GGUF / README.md
nopperl's picture
update bpe pre-tokenizer
4a0bc0a
|
raw
history blame contribute delete
No virus
786 Bytes
metadata
language:
  - en
license: apache-2.0
model_creator: allenai
pipeline_tag: text-generation

OLMo-1.7-7b-GGUF

This repo contains GGUF files of the allenai/OLMo-1.7-7B-hf model. These files can be used with llama.cpp or other software like ollama and LM Studio. Most quanitzation versions based on the bf16 file are provided.

Note: this is a base model, not an instruction-tuned model. Hence, there is no specified prompt template.

For GGUF conversions of other OLMo versions, refer to nopperl/OLMo-1B-GGUF and nopperl/OLMo-7B-GGUF.