39 lines
2.2 KiB
Markdown
39 lines
2.2 KiB
Markdown
---
|
|
license: mit
|
|
base_model:
|
|
- Qwen/Qwen3-8B-Base
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
tags:
|
|
- human-simulation
|
|
- user-simulation
|
|
- behavioral-modeling
|
|
- social-simulation
|
|
---
|
|
|
|
# OSim-8B-Mid
|
|
|
|
**OSim-8B-Mid** is the *midtrained* checkpoint of **OSim** (OdysSim), a foundation model for **human behavior simulation** — trained to imitate the *human / user* side of interactions rather than to behave as a helpful assistant.
|
|
|
|
It is [`Qwen/Qwen3-8B-Base`](https://huggingface.co/Qwen/Qwen3-8B-Base) **midtrained** on the OdysSim corpus: 62 public behavioral datasets unified into a common conversational format (~21.4M interactions, ~10B tokens), organized along the five **Soul** capability axes — `CONV` (discourse/interaction), `SS` (social skills), `COG` (cognitive / mental-state reasoning), `ROLE` (persona, roleplay, pedagogy), and `EVAL` (judgment / preference). Midtraining shifts the base model's prior toward the human-side distribution, avoiding the verbose, agreeable "assistant register" induced by helpfulness post-training.
|
|
|
|
This is the **mid** stage only (no task-specific RL or expert distillation). For the post-trained instruct model, see [`sunweiwei/OSim-Inst-8B`](https://huggingface.co/sunweiwei/OSim-Inst-8B).
|
|
|
|
## Intended use
|
|
|
|
Simulating the human/user side of conversations — user simulation for agent evaluation, social simulation, and persona / role-play. The model is conditioned on a *social-context* system prompt describing who is speaking (role, goal, background, conversational style); given the other party's turns it generates the next human turn.
|
|
|
|
## Results (from the paper)
|
|
|
|
On the held-out OdysSim evaluation, OSim-8B-Mid attains **PPL 4.95 / BLEU 26.72** — the lowest perplexity among 8B behavioral-simulation baselines (UserLM-8B 8.38, CoSER-8B 8.77, Llama-3.1-8B 10.04).
|
|
|
|
## Training
|
|
|
|
- **Base:** Qwen3-8B-Base
|
|
- **Stage:** midtraining (SFT on the OdysSim corpus, ~10B tokens / 4,500 steps)
|
|
- **Optimizer:** AdamW, peak LR 1e-5, 16K-input / 8K-response context, global batch 1,024, bf16, FSDP-2.
|
|
|
|
## Citation
|
|
|
|
If you use this model, please cite the OdysSim paper (*Building Foundation Models for Human Behavior Simulation*). Code: https://github.com/sunnweiwei/OdysSim
|