5 lines
169 B
Markdown
5 lines
169 B
Markdown
---
|
|
pipeline_tag: text-generation
|
|
---
|
|
GGML/GGUF(v2) Quantizations of the model: https://huggingface.co/winglian/llama-2-4b
|
|
Which is a Llama2 4B model based on Llama2 7B. |