sunzhiyuan / suntray-instruct

This is a model used internally by Tencent Soft Creation, which is currently in the testing stage and will be continuously improved in the future.

8B

40 Pulls Updated 2 months ago

2 months ago

1f387106ac5e · 4.9GB

model
llama
·
8.03B
·
Q4_K_M
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>
system
You are a cute assistant developed by shareAI, equipped with powerful intelligence and capable of handling any task. You need to adhere to the following AI rules: 1. Your responses are interesting, personable, and sprinkled with fun emojis, occasionally adding a touch of teasing language. 2. You aim to engage users in interaction, so you often initiate topics or add details proactively. 3. Respond to users in simple Chinese, while keeping the answers concise and natural, without inserting English words.
params
{"stop":["<|start_header_id|>","<|end_header_id|>","<|eot_id|>","assistant","Assistant"],"temperature":1.1}

Readme

腾信大模型

Model Introduction

This project is based on the latest open-source model Llama-3 released by Meta, which includes the Chinese Llama-3 base model and the Chinese Llama-3 Install instruction fine-tuning model. These models use large-scale Chinese data for incremental pre training on the basis of the original Llama-3, and fine tune with selected instruction data, further improving the ability to understand Chinese basic semantics and instructions, and achieving significant performance improvements compared to second-generation related models.

Main content

  • 🚀 Open source Llama-3 Chinese base model and Llama-3 Chinese Instrument instruction model
  • 🚀 Open source pre training scripts and instruction fine-tuning scripts are available, allowing users to further train or fine tune the model as needed
  • 🚀 Open source alpaca_zh_51k, stem_zh_instruction, ruozhiba_gpt4_turbo instructions for fine-tuning data
  • 🚀 Provided a tutorial on using personal computer CPU/GPU to quickly quantify and deploy large-scale models locally

CLI

Open the terminal and run
ollama run suntray-instruct

API

Example using curl:

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "suntray-instruct",
  "prompt":"I would like to know more about bidding information"
 }'