Downloads · 30 days
23
9% of all-time downloads
qwen-8b-dialog-v1
milwright/qwen-8b-dialog-v1
qwen-8b-dialog-v1 is a text generation model from milwright. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as gpl-3.0.
Snapshot: On‑policy pedagogical variant of Qwen‑3‑8B tuned to lead with conversational inquiry, multi‑turn scaffolding, and question-asking dialogue. The model prioritizes question‑asking, co‑investigation, and adapti…
All-time downloads
258
Public
Repo size
5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- llama.cpp
- License
- gpl-3.0
- Access
- Public
- Created
- Feb 8, 2026
- Updated
- Feb 15, 2026
- SHA
- 3004c0f6
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
qwen-8b-dialog-v1
Snapshot: On‑policy pedagogical variant of Qwen‑3‑8B tuned to lead with conversational inquiry, multi‑turn scaffolding, and question-asking dialogue. The model prioritizes question‑asking, co‑investigation, and adaptive depth over direct instruction. It is intended to be tunable across dialogic and pedagogical contexts (e.g., ESL, academic writing, exam prep, K‑12, conversation practice) via prompting or downstream adapters.
- HuggingFaceH4/ultrachat_200k (train_sft; pilot run)
LoRA / continued pre‑training specs
- Method: Low‑Rank Adaptation (LoRA) via Tinker SDK
- Base model: Qwen/Qwen3‑8B
- Rank (r): 16
- Alpha: 32
- Target modules: all linear layers (all‑linear)
Format
This release is provided as a GGUF model for llama.cpp/Ollama workflows.
Intended use
- Dialogue‑forward tutoring
- Socratic, inquiry‑led teaching
- Scaffolding reasoning and language in multi‑turn conversations
Example (Ollama)
# Modelfile
FROM ./qwen3-stage1.q4_k_m.gguf
ollama create qwen-8b-dialog-v1 -f Modelfile
ollama run qwen-8b-dialog-v1
- Task
- Text Generation
- Library
- llama.cpp
- License
- gpl-3.0
- Languages
- en
- Created
- Feb 8, 2026
- Updated
- Feb 15, 2026