ChatML as always. Full-precision this time. Quants will come later.
An experiment to make causal models more conversational. Many of them can already chat, but suffer from problems like occasional dullness, incoherence and verbatim repetition. This model DOES NOT follow assistant-style instructions and IS NOT INTENDED TO.
- Downloads last month
- 65
Hardware compatibility
Log In
to view the estimation
4-bit
8-bit
16-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.
Model tree for toasterai/Qwen2.5-7B-SambaV1DialogTesting-001-GGUF
Base model
Qwen/Qwen2.5-7B