Draft models
Collection
2 items
•
Updated
DeepSeek-R1-DRAFT-Qwen2.5-0.5B
This model is trained on outputs of deepseek-ai/DeepSeek-R1-Distill-Qwen-32B and is meant to be used only as draft model for speculative decoding.
It's specifically intended for users of 3090/4090, allowing you to run the DeepSeek-R1-Distill-Qwen-32B-Q4_K_M GGUF version with 16k context and speeding up generation without sacrificing more context length or model quality.
Data info
The data consists of code, math, reasoning and general knowledge tasks collected from various datasets. It has been trained for 4 epochs on 5200 unique examples, for a total of 21,600,000 tokens per epoch.
Since data generation was done using spare GPU time, I may publish a further trained version later.
- Downloads last month
- 8
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.