MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
7b
26.8K Pulls Updated 12 months ago
Updated 12 months ago
12 months ago
5393d4f5f262 · 4.1GB
model
archllama
·
parameters7.24B
·
quantizationQ4_0
4.1GB
template
<|prompter|>{{ .System }} {{ .Prompt }}</s><|assistant|>
57B
params
{"num_ctx":32768,"stop":["\u003c|prompter|\u003e","\u003c|assistant|\u003e","\u003c/s\u003e"]}
94B
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.