最後更新: 2024-05-11

目錄

• Llama3
• Code Llama
• Llama2-Chinese
• Qwen

Llama3

@2024-05 只有 7b 及 70b 版本公開了

ollama pull llama3               # 取得 7b 版本

Code Llama

Web

• https://github.com/meta-llama/codellama
• https://ollama.com/library/codellama

Code Llama is a code-specialized version of Llama 2
  that was created by further training Llama 2
  on its code-specific datasets, sampling more data from that same dataset for longer.

Size

• 70B     131GB
• 34B     63GB
• 13B     24GB
• 7B       ~12.55GB

分支

i.e.

• 7b-instruct    # natural language
• 7b-code        # Base model for code completion
• 7b-python     # fine-tuned on 100B tokens of Python code

Example prompts

• Instruct(default)
• Code completion
• Python

Instruct

# It trained to output human-like answers to questions(closest to ChatGPT)

ollama run codellama "Where is the bug in this code? $(cat fib.py)"

ollama run codellama "write a unit test for this function: $(cat fib.py)"

ollama run codellama 'You are an expert programmer that writes simple,
concise code and explanations. Write a python function to generate the nth fibonacci number.'

Code completion

Generate by comment

# generate subsequent tokens based on the provided prompt

ollama run codellama:7b-code '# A simple python function to remove whitespace from a string:'

Fill-in-the-middle (FIM)

# model can complete code between two already written code blocks.

Format: <PRE> {prefix} <SUF>{suffix} <MID>

ie.

def compute_gcd(x, y):
    <FILL>
    return result

相當於

ollama run codellama:7b-code '<PRE> def compute_gcd(x, y): <SUF>return result <MID>'

Python

fine-tuned on 100B additional Python tokens

Llama2-Chinese

Web

• https://ollama.com/library/llama2-chinese

Qwen

通义千问

Web

• https://github.com/QwenLM/Qwen1.5
• https://ollama.com/library/qwen

By Alibaba Cloud

Qwen 1.5

6 model sizes, including 0.5B, 1.8B, 4B (default), 7B, 14B, 32B (new) and 72B