Downloads · 30 days
6
19% of all-time downloads
jetson-assistant-stage1-adapter
mohith-das/jetson-assistant-stage1-adapter
jetson-assistant-stage1-adapter is a text generation model from mohith-das. Use it when you need the model to write or continue text. It is set up for peft.
Stage 1 ("cognitive distillation") LoRA adapter from the llmdistillery project — a personal-assistant training pipeline run entirely on a Jetson Orin Nano Super (8GB unified memory), start to finish.
All-time downloads
31
Public
Repo size
81.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors70.4 MB · 86%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Jul 24, 2026
- Updated
- Jul 25, 2026
- SHA
- 7ca765ef
Try a prompt
Base models
Model card
From the Hugging Face model README
jetson-assistant-stage1-adapter
Stage 1 ("cognitive distillation") LoRA adapter from the llm_distillery project — a personal-assistant training pipeline run entirely on a Jetson Orin Nano Super (8GB unified memory), start to finish.
Qwen2.5-0.5B imitates small, high-signal slices of three teacher-grade datasets to pick up reasoning, coding, and multi-turn conversational structure:
| Source | Rows | Teaches |
|---|---|---|
a-m-team/AM-DeepSeek-R1-Distilled-1.4M | 5,000 | step-by-step reasoning traces (chain-of-thought) |
nvidia/OpenCodeInstruct (shard 0) | 2,000 | Python code Q&A, unit-test-validated |
HuggingFaceM4/FineVision (text configs) | 1,000 | multi-turn conversational structure |
Training: LoRA r=32/alpha=64 on all linear projections (q/k/v/o/gate/up/down proj), lr=2e-4, 1 epoch (~500 steps), effective batch 16 (batch_size=1 x grad_accum=16), max_length=1024, FP16.
This is the standalone Stage 1 adapter. Stage 2
(jetson-assistant-stage2-adapter)
was trained on top of this adapter merged into the base, not stacked
alongside it — see
jetson-assistant-0.5b
for the final deployable merge of both stages.
- Task
- Text Generation
- Library
- peft
- Created
- Jul 24, 2026
- Updated
- Jul 25, 2026