license, base_model, pipeline_tag, tags
| license | base_model | pipeline_tag | tags | |||
|---|---|---|---|---|---|---|
| apache-2.0 | HuggingFaceTB/SmolLM2-135M-Instruct | text-generation |
|
Wyzer 2.0 (SmolLM2-135M fine-tune)
The conversational companion inside the BackOnTrack study app.
LoRA fine-tune of SmolLM2-135M-Instruct, merged to native Transformers
format (safetensors) — this is the deployment artifact served by the
Wyzer FastAPI Space. An optional wyzer-2.0-q4_k_m.gguf is included for
local llama.cpp inference. The 135M size was chosen deliberately: it
trains on a laptop CPU and responds fast on Hugging Face's free 2-vCPU
tier.
Trained behaviours:
- Grounded answers: user metrics arrive in a
[CONTEXT]...[/CONTEXT]block; the model quotes numbers only from there. - Refusal to fabricate: missing data → says so instead of guessing.
- Action honesty: recommends, never claims to execute; the app's deterministic engine performs approved actions.
- Mentor persona across study, tech, career, fitness, wellbeing (English + Hinglish).
Trained offline with a synthetic instruction dataset (~900 examples, 2 epochs, LoRA r=16). Not a general-purpose assistant; expect app-domain behaviour.