gpt-oss-psychologist

Delete that section and replace it with your custom Unsloth code.

---

4. Add your Unsloth inference code

Here’s a formatted example you can copy directly:

## 🧠 Example: Inference with Unsloth FastLanguageModel

You can run this model using [Unsloth](https://github.com/unslothai/unsloth) for optimized 4-bit inference:



# Uploaded  model

- **Developed by:** gbalachandhiran
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gpt-oss-20b-unsloth-bnb-4bit

This gpt_oss model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

```python
from unsloth import FastLanguageModel
from transformers import TextStreamer
from huggingface_hub import login

# Optional: login if your model is private
# login("YOUR_HF_TOKEN")

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "gbalachandhiran/oss_psychologist_merged_model_4bit",
    max_seq_length = 2048,
    dtype = None,
    load_in_4bit = True,
)

FastLanguageModel.for_inference(model)  # Enable inference mode

messages = [
    {
        "role": "user",
        "content": "Can you help me with insomnia?"
    }
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=False,
    return_tensors="pt",
    return_dict=True,
    reasoning_effort="medium"
).to("cuda")

text_streamer = TextStreamer(tokenizer, skip_prompt=True)

print("Psychologist AI:")
outputs = model.generate(
    **inputs,
    max_new_tokens=150,
    temperature=0.9,
    top_p=0.99,
    streamer=text_streamer,
    do_sample=False,
)