许可证：apache-2.0 数据集：

• WizardLM/WizardLM_evol_instruct_V2_196k
• icybee/share_gpt_90k_v1 语言：
• en 小部件：
  • 示例标题："示例1" 文本："如何安全地将电视安装在干墙上？" 输出： 文本："安全地将电视安装在干墙上对于确保电视和墙体的长期使用至关重要。以下是安全操作的逐步指南：\n1. 选择合适的支架：选择与您的电视和墙体兼容的支架。确保支架适用于干墙，而不仅仅是木材或混凝土。\n2. 准备墙面：在安装电视之前，确保墙面清洁，无任何碎片或油漆。使用墙柱探测器定位墙内的立柱。\n3. 安装支架：按照制造商的说明将支架安装到墙上。使用适当的硬件和工具将支架固定在墙上。\n4. 调平电视：使用水平仪或支架制造商提供的调平套件，在支架上调平电视。\n5. 将电视固定在支架上：使用适当的硬件和工具将电视固定在支架上。拧紧螺栓和螺丝，确保电视牢固固定。\n6. 连接电缆：将电视电缆连接到电视背面和支架上的相应端口。\n7. 测试支架：测试支架以确保其稳固。根据需要调整支架，确保电视水平且稳固。\n安全地将电视安装在干墙上对于避免损坏墙体或电视至关重要。仔细遵循这些步骤，并使用适当的工具和硬件，以确保安装牢固且稳定。"
  • 示例标题："示例2" 文本："快乐之于悲伤，如同平静之于_。" 输出： 文本："可以用来描述平静反义词的形容词是“焦虑”或“压力”。因此，从快乐到悲伤，我们可以说快乐之于悲伤，如同平静之于焦虑或压力。" 库名称：transformers 管道标签：文本生成 标签：
• nlp
• llm

AmberChat

我们推出了AmberChat，这是一个基于LLM360/Amber微调的指令跟随模型。AmberChat是LLM360的Pebble模型系列的一部分。

评估

模型描述

• 模型类型： 与LLaMA-7B架构相同的语言模型
• 语言（NLP）： 英语
• 许可证： Apache 2.0
• 更多信息资源：
  • 指标
  • 完全处理的Amber预训练数据
  • 微调代码

加载AmberChat

import torch
from transformers import LlamaTokenizer, LlamaForCausalLM

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

#模板改编自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，您可以使用FastChat：

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

AmberChat微调详情

数据混合

超参数