---
base_model: Qwen/Qwen3-0.6B
tags:
- text-generation-inference
- transformers
- qwen3
- trl
- sft
- unsloth
license: apache-2.0
language:
- en
datasets:
- boltuix/emotions-dataset
---

## Goal:
Detection emotional from natural lanugage.

## Usage:
```python
messages = [
    {"role" : "user", "content" : "I want to play this game"}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize = False,
    add_generation_prompt = True
    enable_thinking = False, # you can set this to True but it won't get thinking!
)

from transformers import TextStreamer
_ = model.generate(
    **tokenizer(text, return_tensors = "pt").to("cuda"),
    streamer = TextStreamer(tokenizer, skip_prompt = True),
)
#neutral
```


Base model: Qwen3-0.6B