Yarn extension of context to 160k since 40k for coding these days is pretty obsolete.
| Quant | Perplexity |
|---|---|
| Q8_0 | PPL = 5.6355 +/- 0.13322 |
| Q6_K_M | PPL = 5.6169 +/- 0.13250 |
| Q5_K_M | PPL = 5.6270 +/- 0.13270 |
| Q4_K_M | PPL = 5.6435 +/- 0.13298 |
| IQ4_NL | PPL = 5.6717 +/- 0.13443 |
| IQ3_XS | PPL = 5.8865 +/- 0.13868 |
- Downloads last month
- 1,196
Hardware compatibility
Log In
to view the estimation
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support