Text Generation
Transformers
Safetensors
Chinese
qwen3
counseltraj
counseltrajlm
counseling
conversational
merged
text-generation-inference
Instructions to use UEC-InabaLab/CounselTrajLM-Qwen3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UEC-InabaLab/CounselTrajLM-Qwen3-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="UEC-InabaLab/CounselTrajLM-Qwen3-8B") 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-Qwen3-8B") model = AutoModelForCausalLM.from_pretrained("UEC-InabaLab/CounselTrajLM-Qwen3-8B", 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-Qwen3-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "UEC-InabaLab/CounselTrajLM-Qwen3-8B" # 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-Qwen3-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/UEC-InabaLab/CounselTrajLM-Qwen3-8B
- SGLang
How to use UEC-InabaLab/CounselTrajLM-Qwen3-8B 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-Qwen3-8B" \ --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-Qwen3-8B", "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-Qwen3-8B" \ --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-Qwen3-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use UEC-InabaLab/CounselTrajLM-Qwen3-8B with Docker Model Runner:
docker model run hf.co/UEC-InabaLab/CounselTrajLM-Qwen3-8B
Download training_summary.json from UEC-InabaLab/CounselTrajLM-Qwen3-8B: direct link, hf CLI and curl.
- Browser
- Download file 876 Bytes
-
https://huggingface.co/UEC-InabaLab/CounselTrajLM-Qwen3-8B/resolve/main/training_summary.json
- Command line
-
hf download hf://UEC-InabaLab/CounselTrajLM-Qwen3-8B/training_summary.json
-
curl -L -o training_summary.json https://huggingface.co/UEC-InabaLab/CounselTrajLM-Qwen3-8B/resolve/main/training_summary.json
876 Bytes
| { | |
| "model": "CounselTrajLM-Qwen3-8B", | |
| "base_model": "Qwen/Qwen3-8B", | |
| "base_revision": "b968826d9c46dd6066d109eabc6255188de91218", | |
| "training_dataset": "CounselTrajD", | |
| "split": "dialogue-disjoint 90/10 train/validation", | |
| "train_examples": 425679, | |
| "validation_examples": 47528, | |
| "fine_tuning_method": "QLoRA", | |
| "release_format": "adapter merged into unquantized BF16 base weights", | |
| "learning_rate": 0.0002, | |
| "epochs": 3, | |
| "checkpoint_policy": "final_epoch", | |
| "validation_role": "monitoring", | |
| "lr_scheduler": "cosine", | |
| "warmup_ratio": 0.06, | |
| "effective_batch_size": 16, | |
| "max_sequence_length": 2048, | |
| "max_history_characters": 1800, | |
| "seed": 20260704, | |
| "global_step": 79815, | |
| "thinking_enabled": false, | |
| "lora": { | |
| "rank": 32, | |
| "alpha": 64, | |
| "dropout": 0.05 | |
| }, | |
| "train_loss": 1.3573430852992174, | |
| "validation_loss": 1.513865351676941 | |
| } | |