robertgshaw2 / zephyr family / text-generation
zephyr-7b-beta-channelwise-gptq
robertgshaw2/zephyr-7b-beta-channelwise-gptq
Benchmarks
Where it scores.
General Provisional —
Coding Provisional —
Math Provisional —
Reasoning Provisional —
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| FP16 / smallest | SAFETENSORS | 4.0 GB | — | model.safetensors |
Sizes are file sizes, not peak runtime memory.
From the Hugging Face model card
About this model.
From the Hugging Face model card