Text Generation
Transformers
Safetensors
English
qwen3
mental-health
user-simulation
patient-simulation
psychotherapy
role-play
dpo
conversational
text-generation-inference
Instructions to use ChengLi0228/Angel-Actor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ChengLi0228/Angel-Actor with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ChengLi0228/Angel-Actor") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ChengLi0228/Angel-Actor") model = AutoModelForCausalLM.from_pretrained("ChengLi0228/Angel-Actor", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ChengLi0228/Angel-Actor with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ChengLi0228/Angel-Actor" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ChengLi0228/Angel-Actor", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ChengLi0228/Angel-Actor
- SGLang
How to use ChengLi0228/Angel-Actor with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ChengLi0228/Angel-Actor" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ChengLi0228/Angel-Actor", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ChengLi0228/Angel-Actor" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ChengLi0228/Angel-Actor", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ChengLi0228/Angel-Actor with Docker Model Runner:
docker model run hf.co/ChengLi0228/Angel-Actor
Add link to paper
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,11 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
base_model: Qwen/Qwen3-8B
|
| 4 |
-
base_model_relation: finetune
|
| 5 |
-
library_name: transformers
|
| 6 |
-
pipeline_tag: text-generation
|
| 7 |
language:
|
| 8 |
- en
|
|
|
|
|
|
|
|
|
|
| 9 |
tags:
|
| 10 |
- mental-health
|
| 11 |
- user-simulation
|
|
@@ -14,10 +13,13 @@ tags:
|
|
| 14 |
- role-play
|
| 15 |
- dpo
|
| 16 |
- qwen3
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
# Angel-Actor
|
| 20 |
|
|
|
|
|
|
|
| 21 |
**Angel-Actor** role-plays a **psychotherapy patient** across a multi-turn
|
| 22 |
conversation. You are the therapist; it answers in character, keeps some
|
| 23 |
things back, and opens up gradually. It is stage 2 of **Angel**, a two-stage
|
|
@@ -100,4 +102,4 @@ progress and naturalness. Full recipe:
|
|
| 100 |
|
| 101 |
## Citation
|
| 102 |
|
| 103 |
-
Coming soon.
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: Qwen/Qwen3-8B
|
|
|
|
|
|
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
+
library_name: transformers
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
tags:
|
| 9 |
- mental-health
|
| 10 |
- user-simulation
|
|
|
|
| 13 |
- role-play
|
| 14 |
- dpo
|
| 15 |
- qwen3
|
| 16 |
+
base_model_relation: finetune
|
| 17 |
---
|
| 18 |
|
| 19 |
# Angel-Actor
|
| 20 |
|
| 21 |
+
This model is presented in the paper [SimAI: Mechanistic User Simulation through Psychological Network Models](https://huggingface.co/papers/2611.21808).
|
| 22 |
+
|
| 23 |
**Angel-Actor** role-plays a **psychotherapy patient** across a multi-turn
|
| 24 |
conversation. You are the therapist; it answers in character, keeps some
|
| 25 |
things back, and opens up gradually. It is stage 2 of **Angel**, a two-stage
|
|
|
|
| 102 |
|
| 103 |
## Citation
|
| 104 |
|
| 105 |
+
Coming soon.
|