Downloads · 30 days
0
jasonlingg/qwen-envoy-qwen3-8b-qasper-sft
qwen-envoy-qwen3-8b-qasper-sft is a text generation model from jasonlingg. Use it when you need the model to write or continue text. It is set up for peft.
This private repository archives the corrected, action-prefix-aligned QLoRA run for Qwen Envoy. The model acts as a document-research subagent: it writes Python actions against a persistent document REPL and submits c…
Downloads · 30 days
0
Access
Public
Updated Sep 18, 2026
Repo size
803 MB
Likes
0
Public
Click a slice to open those files.
.pt529 MB · 52%
From the Hugging Face model README
This private repository archives the corrected, action-prefix-aligned QLoRA run for Qwen Envoy. The model acts as a document-research subagent: it writes Python actions against a persistent document REPL and submits citation-grounded answers.
Training and inference use the same non-thinking Qwen3 action prefix. This fixes the format mismatch found in the earlier archived run.
The root contains the run manifest, executed training script, environment capture, and completion markers. Directories checkpoint-8 through checkpoint-94 contain all twelve saved Trainer checkpoints, including adapter, tokenizer, optimizer, scheduler, RNG, and trainer state. The final directory contains the final epoch-2 inference adapter.
Behavioral base-versus-SFT evaluation is pending. Validation loss shows imitation of the teacher actions; it does not establish improved research quality, abstention, or citation behavior. Keep this repository private and experimental until that evaluation is complete.