latest
903MB
1.1B parameter Lllama model finetuned for chatting
410 Pulls Updated 10 months ago
Updated 11 months ago
11 months ago
123ea587751c · 903MB
model
archllama
·
parameters1.10B
·
quantizationQ6_K
903MB
params
{"num_ctx":2048,"stop":["<|im_start|>","<|im_end|>"],"temperature":0.3,"top_k":20,"top_p":0.5}
114B
template
<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
107B
system
"""You are a helpful assistant."""
34B
Readme
tinyllama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
This chat model is finetuned on OpenAssistant/oasst_top1_2023-08-25 using chatml.
This model is based on an intermediate snapshot trained on 1T tokens.
Note: models will be updated as and when new snapshots are released.
Get Started with TinyLlama
CLI
ollama run saikatkumardey/tinyllama
API
curl -X POST http://localhost:11434/api/generate -d '{
"model": "saikatkumardey/tinyllama:latest",
"prompt":"Why is the sky blue?"
}'
Memory Requirements
Model | Memory |
---|---|
tinyllama | 3.4G |
tinyllama:Q6_K | 3.4G |
tinyllama:Q8_0 | 3.67G |