GGUF importance matrix (imatrix) quants for https://huggingface.co/abacusai/Smaug-34B-v0.1
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

Layers Context Template
60
200000
[INST] <<SYS>>
{instructions}
<</SYS>>

{prompt} [/INST]
{response}
Downloads last month
22
GGUF
Model size
34B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support