mistrallite:7b-v0.1-q2

mistrallite:7b-v0.1-q2_K

158K Downloads Updated 2 years ago

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

ollama run mistrallite:7b-v0.1-q2_K

curl http://localhost:11434/api/chat \
  -d '{
    "model": "mistrallite:7b-v0.1-q2_K",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='mistrallite:7b-v0.1-q2_K',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'mistrallite:7b-v0.1-q2_K',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

32164f7b30a5 · 3.1GB ·

model

archllama

parameters7.24B

quantizationQ2_K

3.1GB

params

{ "num_ctx": 32768, "stop": [ "<|prompter|>", "<|assistant|>", "</s>

94B

template

<|prompter|>{{ .System }} {{ .Prompt }}</s><|assistant|>

57B

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