Text Generation
Transformers
Safetensors
Chinese
qwen2
counseltraj
counseltrajlm
counseling
conversational
merged
text-generation-inference
Instructions to use UEC-InabaLab/CounselTrajLM-Qwen2.5-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UEC-InabaLab/CounselTrajLM-Qwen2.5-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="UEC-InabaLab/CounselTrajLM-Qwen2.5-7B") 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("UEC-InabaLab/CounselTrajLM-Qwen2.5-7B") model = AutoModelForCausalLM.from_pretrained("UEC-InabaLab/CounselTrajLM-Qwen2.5-7B", 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 UEC-InabaLab/CounselTrajLM-Qwen2.5-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "UEC-InabaLab/CounselTrajLM-Qwen2.5-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "UEC-InabaLab/CounselTrajLM-Qwen2.5-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/UEC-InabaLab/CounselTrajLM-Qwen2.5-7B
- SGLang
How to use UEC-InabaLab/CounselTrajLM-Qwen2.5-7B 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 "UEC-InabaLab/CounselTrajLM-Qwen2.5-7B" \ --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": "UEC-InabaLab/CounselTrajLM-Qwen2.5-7B", "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 "UEC-InabaLab/CounselTrajLM-Qwen2.5-7B" \ --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": "UEC-InabaLab/CounselTrajLM-Qwen2.5-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use UEC-InabaLab/CounselTrajLM-Qwen2.5-7B with Docker Model Runner:
docker model run hf.co/UEC-InabaLab/CounselTrajLM-Qwen2.5-7B
File size: 3,023 Bytes
d34e5bd | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | """Generate the next counselor response with the merged CounselTrajLM model."""
import argparse
import json
from pathlib import Path
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
SYSTEM_PROMPT = (
"你是一名专业、温和、自然的线上心理咨询师。"
"请根据对话历史生成下一句咨询师回复。"
"回复只写咨询师要说的话,不要写说话人名称,不要写对话标签。"
)
def load_messages(path):
messages = json.loads(Path(path).read_text(encoding="utf-8"))
if not isinstance(messages, list) or not messages:
raise ValueError("Provide a non-empty JSON list of chat messages.")
for i, message in enumerate(messages):
if not isinstance(message, dict):
raise ValueError("Each message must be a JSON object.")
if message.get("role") not in {"system", "user", "assistant"}:
raise ValueError("Message roles must be system, user, or assistant.")
if message["role"] == "system" and i != 0:
raise ValueError("A system message may appear only at the beginning.")
if not isinstance(message.get("content"), str) or not message["content"].strip():
raise ValueError("Each message must have non-empty text content.")
if messages[-1]["role"] != "user":
raise ValueError("The dialogue must end with a client (user) message.")
if messages[0]["role"] != "system":
messages.insert(0, {"role": "system", "content": SYSTEM_PROMPT})
return messages
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--model", default="UEC-InabaLab/CounselTrajLM-Qwen2.5-7B")
parser.add_argument("--messages", type=Path, default=Path(__file__).parent / "examples/history.json")
parser.add_argument("--max-new-tokens", type=int, default=160)
parser.add_argument("--greedy", action="store_true")
args = parser.parse_args()
messages = load_messages(args.messages)
tokenizer = AutoTokenizer.from_pretrained(args.model)
model = AutoModelForCausalLM.from_pretrained(
args.model, dtype=torch.bfloat16, device_map="auto"
).eval()
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
if inputs.input_ids.shape[-1] + args.max_new_tokens > model.config.max_position_embeddings:
raise ValueError("The input plus requested output exceeds the model context window.")
generation = {
"max_new_tokens": args.max_new_tokens,
"do_sample": not args.greedy,
"repetition_penalty": 1.05,
}
if not args.greedy:
generation.update(temperature=0.7, top_p=0.8, top_k=20)
with torch.inference_mode():
outputs = model.generate(**inputs, **generation)
reply = tokenizer.decode(outputs[0, inputs.input_ids.shape[-1]:], skip_special_tokens=True)
print(reply.strip())
if __name__ == "__main__":
main()
|