mistrallite:7b-v0.1-q5_1

33.1K 1 year ago

MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.

7b

1 year ago

e09d24104dd5 · 5.4GB

model
llama
·
7.24B
·
Q5_1
template
<|prompter|>{{ .System }} {{ .Prompt }}</s><|assistant|>
params
{ "num_ctx": 32768, "stop": [ "<|prompter|>", "<|assistant|>", "</s>

Readme

Mistrallite is a fine-tuned model based on Mistral, with enhanced capabilities of processing long context (up to 32K tokens). This model is able to perform significantly better on several long context retrieve and answering tasks.

Reference

Hugging Face