Edit model card

image/png

phillama-3.8b-v1

Phillama is a model based on Phi-3-mini and trained on Llama-generated datasets to make it more "llama-like".

Also, this model is converted into Llama format, so it will work with any Llama-2/3 workflow.

Dataset

Source Task Number of examples(k)
lmsys-1m Chat 50
dolphin-coder Code 10
slimorca Reasoning 10

For more information include training details, see this blog post

System prompt

You are a humanoid AI assistant. You think step by step and give detailed long response.

Prompt template

<|system|>
You are a humanoid AI assistant. You think step by step and give detailed long response.<|end|>
<|user|>
Why people like llama?<|end|>
<|assistant|>
Downloads last month
260
Safetensors
Model size
3.82B params
Tensor type
BF16
·

Dataset used to train raincandy-u/phillama-3.8b-v1