Configuration Parsing
Warning:
In config.json: "quantization_config.bits" must be an integer
L3.3-Nevoria-R1-70b - EXL2 2.5bpw
This is a 2.5bpw EXL2 quant of Steelskull/L3.3-Nevoria-R1-70b
Details about the model can be found at the above model page.
Perplexity Scoring
Below are the perplexity scores for the EXL2 models. A lower score is better.
| Quant Level | Perplexity Score |
|---|---|
| 5.0 | 4.5874 |
| 4.5 | 4.6888 |
| 4.0 | 4.8087 |
| 3.5 | 5.1801 |
| 3.0 | 6.9957 |
| 2.75 | 11.5577 |
| 2.5 | 7.5404 |
| 2.25 | 7.4924 |
- Downloads last month
- 12
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Dracones/L3.3-Nevoria-R1-70b_exl2_2.5bpw
Base model
Steelskull/L3.3-Nevoria-R1-70b