Amberchat

🚀 AmberChat

AmberChat是一個基於指令跟隨的模型，它是在LLM360/Amber的基礎上進行微調得到的。AmberChat屬於LLM360的Pebble模型系列，能夠為用戶提供準確且詳細的回答。

🚀 快速開始

你可以按照以下步驟加載和使用AmberChat模型：

import torch
from transformers import LlamaTokenizer, LlamaForCausalLM

tokenizer = LlamaTokenizer.from_pretrained("LLM360/AmberChat")
model = LlamaForCausalLM.from_pretrained("LLM360/AmberChat")

#template adapated from fastchat
template= "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: Got any creative ideas for a 10 year old’s birthday?\n### Assistant: Of course! Here are some creative ideas for a 10-year-old's birthday party:\n1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.\n2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.\n3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.\n4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.\n5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.\n6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.\n7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.\n8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.\nRemember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!\n### Human: {prompt}\n### Assistant:"

prompt = "How do I mount a tv to drywall safely?"

input_str = template.format(prompt=prompt)
input_ids = tokenizer(input_str, return_tensors="pt").input_ids
outputs = model.generate(input_ids, max_length=1000)
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())

或者，你也可以使用FastChat：

python3 -m fastchat.serve.cli --model-path LLM360/AmberChat

✨ 主要特性

• 指令跟隨能力：能夠準確理解用戶的指令，並給出詳細且有幫助的回答。
• 多場景應用：可用於多種自然語言處理任務，如問答、文本生成等。

💻 使用示例

基礎用法

以下是使用AmberChat進行文本生成的示例：

import torch
from transformers import LlamaTokenizer, LlamaForCausalLM

tokenizer = LlamaTokenizer.from_pretrained("LLM360/AmberChat")
model = LlamaForCausalLM.from_pretrained("LLM360/AmberChat")

template= "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: {prompt}\n### Assistant:"
prompt = "How do I mount a tv to drywall safely?"
input_str = template.format(prompt=prompt)
input_ids = tokenizer(input_str, return_tensors="pt").input_ids
outputs = model.generate(input_ids, max_length=1000)
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())

高級用法

你可以使用FastChat來更方便地使用AmberChat：

python3 -m fastchat.serve.cli --model-path LLM360/AmberChat

📚 詳細文檔

評估結果

模型描述

微調細節

數據混合

超參數

訓練超參數

使用Ollama運行量化模型

你可以按照以下步驟在個人電腦或筆記本上使用AmberChat的量化版本：

1. 首先，按照此處的說明安裝Ollama。然後，從TheBloke/AmberChat - GGUF下載一個量化模型檢查點（例如8位版本的amberchat.Q8_0.gguf）。使用以下模板在本地創建一個Ollama Modelfile：

FROM amberchat.Q8_0.gguf

TEMPLATE """{{ .System }}
USER: {{ .Prompt }}
ASSISTANT:
"""
SYSTEM """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
"""
PARAMETER stop "USER:"
PARAMETER stop "ASSISTANT:"
PARAMETER repeat_last_n   0
PARAMETER num_ctx         2048
PARAMETER seed            0
PARAMETER num_predict    -1

確保FROM指令指向下載的檢查點文件。 2. 運行以下命令來構建模型：

ollama create amberchat -f Modelfile

3. 從命令行運行模型：

ollama run amberchat

你只需要構建一次模型，之後就可以直接運行它。

📄 許可證

AmberChat使用Apache 2.0許可證。

📖 引用

如果你使用了AmberChat，請引用以下論文：

@misc{liu2023llm360,
      title={LLM360: Towards Fully Transparent Open-Source LLMs}, 
      author={Zhengzhong Liu and Aurick Qiao and Willie Neiswanger and Hongyi Wang and Bowen Tan and Tianhua Tao and Junbo Li and Yuqi Wang and Suqi Sun and Omkar Pangarkar and Richard Fan and Yi Gu and Victor Miller and Yonghao Zhuang and Guowei He and Haonan Li and Fajri Koto and Liping Tang and Nikhil Ranjan and Zhiqiang Shen and Xuguang Ren and Roberto Iriondo and Cun Mu and Zhiting Hu and Mark Schulze and Preslav Nakov and Tim Baldwin and Eric P. Xing},
      year={2023},
      eprint={2312.06550},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}