Edit model card

GGUF importance matrix (imatrix) quants for https://huggingface.co/jondurbin/bagel-dpo-20b-v04-llama
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

Layers Context Template
48
32768
[INST] <<SYS>>
{instructions}
<</SYS>>

{prompt} [/INST]
{response}
Downloads last month
127
GGUF
Model size
19.9B params
Architecture
llama

2-bit

3-bit

4-bit

8-bit

16-bit

Inference Examples
Inference API (serverless) is not available, repository is disabled.