mistrallite:7b-v0.1-q4_K

mistrallite:7b-v0.1-q4_K_S

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-q4_K_S

curl http://localhost:11434/api/chat \
  -d '{
    "model": "mistrallite:7b-v0.1-q4_K_S",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='mistrallite:7b-v0.1-q4_K_S',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'mistrallite:7b-v0.1-q4_K_S',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

81a8a1744387 · 4.1GB ·

model

archllama

parameters7.24B

quantizationQ4_K_S

4.1GB

template

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

57B

params

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

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.

Reference

Hugging Face