1.1B parameter Lllama model finetuned for chatting

Updated 1 year ago

1 year ago

1f8f12e9b667 · 1.2GB

archllama

parameters1.1B

quantizationQ8_0

1.2GB

"""You are a helpful assistant."""

34B

<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assi

107B

{ "stop": [ "<|im_start|>", "<|im_end|>" ], "temperature": 0.7 }

76B

Readme

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

This model is based on an intermediate snapshot trained on 1T tokens.

Note: models will be updated as and when new snapshots are released.

ollama run saikatkumardey/tinyllama

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "saikatkumardey/tinyllama:latest",
  "prompt":"Why is the sky blue?"
 }'