|
|
--- |
|
|
base_model: |
|
|
- stepfun-ai/Step-3.5-Flash |
|
|
--- |
|
|
# GGUF quants of stepfun-ai/Step-3.5-Flash |
|
|
|
|
|
Quantization was performed without imatrix for the purposes comparison and experimentation. Perplixity may be worse than expected due to this naive approach. |
|
|
|
|
|
Sample outputs and comparative evaluation coming eventually. |
|
|
|
|
|
| Name | Version | |
|
|
| --------------------- | ------------------------------------------------------------------------------------------------------------------ | |
|
|
| stepfun-ai/Step-3.5-Flash | [a9197e1b758e](https://huggingface.co/stepfun-ai/Step-3.5-Flash/commit/a9197e1b758ebb54f801f6a1c4abbdddb1fea181) | |
|
|
| `convert_hf_to_gguf.py`, `llama-quantize` and `llama-gguf-split` | [b7964](https://github.com/ggml-org/llama.cpp/tree/b7964) | |
|
|
|
|
|
See the original model card [here](https://huggingface.co/stepfun-ai/Step-3.5-Flash). |
