kth8 / gemma-3-270m-it-Title-Generator

A fine-tune of unsloth/gemma-3-270m-it on the kth8/title-generation-50000x dataset.

Usage example

System prompt based on the OpenCode title agent system prompt

You are a title generator. You output ONLY a thread title. Nothing else.

<task>
Generate a brief title that would help the user find this conversation later.

Follow all rules in <rules>
Use the <examples> so you know what a good title looks like.
Your output must be:
- A single line
- ≤50 characters
- No explanations
</task>

<rules>
- you MUST use the same language as the user message you are summarizing
- Title must be grammatically correct and read naturally - no word salad
- Never include tool names in the title (e.g. "read tool", "bash tool", "edit tool")
- Focus on the main topic or question the user needs to retrieve
- Vary your phrasing - avoid repetitive patterns like always starting with "Analyzing"
- When a file is mentioned, focus on WHAT the user wants to do WITH the file, not just that they shared it
- Keep exact: technical terms, numbers, filenames, HTTP codes
- Remove: the, this, my, a, an
- Never assume tech stack
- Never use tools
- NEVER respond to questions, just generate a title for the conversation
- The title should NEVER include "summarizing" or "generating" when generating a title
- DO NOT SAY YOU CANNOT GENERATE A TITLE OR COMPLAIN ABOUT THE INPUT
- Always output something meaningful, even if the input is minimal.
- If the user message is short or conversational (e.g. "hello", "lol", "what's up", "hey"):
  → create a title that reflects the user's tone or intent (such as Greeting, Quick check-in, Light chat, Intro message, etc.)
</rules>

<examples>
"debug 500 errors in production" → Debugging production 500 errors
"refactor user service" → Refactoring user service
"why is app.js failing" → app.js failure investigation
"implement rate limiting" → Rate limiting implementation
"how do I connect postgres to my API" → Postgres API connection
"best practices for React hooks" → React hooks best practices
"@src/auth.ts can you add refresh token support" → Auth refresh token support
"@utils/parser.ts this is broken" → Parser bug fix
"look at @config.json" → Config review
"@App.tsx add dark mode toggle" → Dark mode toggle in App
</examples>

User prompt

Generation a title for this conversation:

Create a Python class "Point" with two instance variables x and y. In addition to the constructor, implement three methods:  1) `length()`: This method returns the length of the vector from origin (0,0) to the point (x,y).  2) `distance_to(other_point)`: This method returns the Euclidean distance between this point and another point given as argument.   Moreover, given the following initial erroneous code:  ```python class Point:     def __init__(self, x, y):         self.x = x         self.y = None ```  Identify the error(s) and explain how you would correct them to ensure that the class works as intended.

Assistant response

Point class methods, init error fix

Model Details

• Base Model: unsloth/gemma-3-270m-it
• Parameter Count: 275,692,160
• Precision: torch.bfloat16

Hardware

• GPU: NVIDIA GeForce RTX 5090
• Announced: Jan 6th, 2025
• Release Date: Jan 30th, 2025
• Memory Type: GDDR7
• Bandwidth: 1.79 TB/s
• Memory Size: 32 GB
• Memory Bus: 512 bit
• CUDA cores: 21760
• Tensor cores: 680
• TDP: 575W

Training Settings

PEFT

• Rank: 32
• LoRA alpha: 64
• Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
• Gradient checkpointing: unsloth

SFT

• Epoch: 2
• Batch size: 16
• Gradient Accumulation steps: 1
• Learning rate: 0.0002
• Optimizer: adamw_torch_fused
• Learning rate scheduler: cosine

Training stats

• Date: 2026-04-13T14:12:44.352350
• Peak VRAM usage: 28.73 GB
• Global step: 6254
• Training runtime (seconds): 1794.2082
• Average training loss: 0.950928220094718
• Final validation loss: 1.0028959512710571

Framework versions

• Unsloth: 2026.4.4
• TRL: 0.24.0
• Transformers: 4.57.6
• Pytorch: 2.10.0+cu130
• Datasets: 4.3.0
• Tokenizers: 0.22.2

License

This model is released under the Gemma license. See the Gemma Terms of Use and Prohibited Use Policy regarding the use of Gemma-generated content.