BigL-7B-imatrix-GGUF

Quantizations of https://huggingface.co/Undi95/BigL-7B

Open source inference clients/UIs

• llama.cpp
• KoboldCPP
• text-generation-webui
• jan
• ik_llama.cpp
• croco.cpp

Closed source inference clients/UIs

• LM Studio
• More will be added...

---

From original readme

This repo contains fp16 files of BigL-7B.

The model was created by merging the basic Mistral-0.2-7B, a full finetuned RP model of it (Undi95/LewdMistral-7B-0.2) and some others top Mistral model I enjoyed (Toppy, ...)

It's a demonstration to show that merging Mistral 0.1 and 0.2 models is possible if done correctly, without the need to retrain entirely (dataset lost, repo deleted, etc...)

<!-- description end --> <!-- prompt-template start -->

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{system prompt}

### Input:
{prompt}

### Response:
{output}