Text Generation
Transformers
Safetensors
Chinese
qwen3_5_text
qwen3_5
merged
psychological-counseling
counselor-response-generation
conversational
Instructions to use UEC-InabaLab/CounselTrajLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UEC-InabaLab/CounselTrajLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="UEC-InabaLab/CounselTrajLM") 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") model = AutoModelForCausalLM.from_pretrained("UEC-InabaLab/CounselTrajLM", 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 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "UEC-InabaLab/CounselTrajLM" # 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", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/UEC-InabaLab/CounselTrajLM
- SGLang
How to use UEC-InabaLab/CounselTrajLM 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" \ --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", "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" \ --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", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use UEC-InabaLab/CounselTrajLM with Docker Model Runner:
docker model run hf.co/UEC-InabaLab/CounselTrajLM
Download model_details.json from UEC-InabaLab/CounselTrajLM: direct link, hf CLI and curl.
- Browser
- Download file 1.32 kB
-
https://huggingface.co/UEC-InabaLab/CounselTrajLM/resolve/main/model_details.json
- Command line
-
hf download hf://UEC-InabaLab/CounselTrajLM/model_details.json
-
curl -L -o model_details.json https://huggingface.co/UEC-InabaLab/CounselTrajLM/resolve/main/model_details.json
1.32 kB
| { | |
| "base_model": "Qwen/Qwen3.5-9B", | |
| "base_revision": "c202236235762e1c871ad0ccb60c8ee5ba337b9a", | |
| "rank": 32, | |
| "alpha": 64, | |
| "dropout": 0.05, | |
| "adapter_parameters": 58195968, | |
| "selection": "Final checkpoint after three epochs; no best-validation checkpoint reload.", | |
| "epoch": 3.0, | |
| "global_step": 79815, | |
| "train_samples": 425679, | |
| "validation_samples": 47528, | |
| "validation_loss": 1.5481888055801392, | |
| "training_hyperparameters": { | |
| "max_seq_length": 2048, | |
| "max_history_chars": 1800, | |
| "learning_rate": 0.0002, | |
| "warmup_ratio": 0.06, | |
| "optim": "paged_adamw_8bit", | |
| "lr_scheduler_type": "cosine", | |
| "per_device_train_batch_size": 2, | |
| "gradient_accumulation_steps": 1, | |
| "num_train_epochs": 3.0, | |
| "attn_implementation": "eager", | |
| "seed": 20260704 | |
| }, | |
| "release_changes": [ | |
| "Replace the internal base-model path with its official Hub ID and pin the exact base revision.", | |
| "Merge the published final adapter into the unquantized pinned base text language model." | |
| ], | |
| "training_adapter_type": "LoRA", | |
| "training_checkpoint": "final_adapter", | |
| "release_format": "merged BF16 text language model", | |
| "source_adapter_sha256": "c4d89ce3b6cfdb53dba2927683331e2182c8767f3380527a78f0533b0f31e5bd", | |
| "source_adapter_hf_revision": "341e9b198c985ee75c982a43376015d806b15522" | |
| } | |