model_family stringclasses 7
values | chat_format stringclasses 3
values | example stringclasses 3
values |
|---|---|---|
SmolLM2 | llama-3 | <|im_start|>user\n{msg}<|im_end|>\n<|im_start|>assistant\n |
Llama-3.2 | llama-3 | <|begin_of_text|><|start_header_id|>user<|end_header_id|>\n{msg}<|eot_id|> |
Qwen2.5 | chatml | <|im_start|>user\n{msg}<|im_end|>\n<|im_start|>assistant\n |
Gemma-2 | gemma | <start_of_turn>user\n{msg}<end_of_turn>\n<start_of_turn>model\n |
Phi-3.5 | chatml | <|im_start|>user\n{msg}<|im_end|>\n<|im_start|>assistant\n |
TinyLlama | chatml | <|im_start|>user\n{msg}<|im_end|>\n<|im_start|>assistant\n |
MiniCPM | chatml | <|im_start|>user\n{msg}<|im_end|>\n<|im_start|>assistant\n |
Chat Format Reference
Correct chat formats for dispatchAI GGUF models. Use with llama-cpp-python's chat_format parameter.
Usage
from llama_cpp import Llama
llm = Llama(model_path='model.gguf', chat_format='llama-3') # For SmolLM2/Llama-3.2
馃殌 dispatchAI
- Downloads last month
- 7