Instructions to use kth8/LFM2.5-230M-OpenCode-Title-Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kth8/LFM2.5-230M-OpenCode-Title-Generator with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kth8/LFM2.5-230M-OpenCode-Title-Generator")
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("kth8/LFM2.5-230M-OpenCode-Title-Generator")
model = AutoModelForCausalLM.from_pretrained("kth8/LFM2.5-230M-OpenCode-Title-Generator", 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 kth8/LFM2.5-230M-OpenCode-Title-Generator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kth8/LFM2.5-230M-OpenCode-Title-Generator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kth8/LFM2.5-230M-OpenCode-Title-Generator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kth8/LFM2.5-230M-OpenCode-Title-Generator

SGLang

How to use kth8/LFM2.5-230M-OpenCode-Title-Generator 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 "kth8/LFM2.5-230M-OpenCode-Title-Generator" \
    --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": "kth8/LFM2.5-230M-OpenCode-Title-Generator",
		"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 "kth8/LFM2.5-230M-OpenCode-Title-Generator" \
        --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": "kth8/LFM2.5-230M-OpenCode-Title-Generator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use kth8/LFM2.5-230M-OpenCode-Title-Generator with Docker Model Runner:
```
docker model run hf.co/kth8/LFM2.5-230M-OpenCode-Title-Generator
```

LFM2.5-230M-OpenCode-Title-Generator / README.md

kth8

Update README.md

8962065 verified about 1 month ago

preview code

Raw History Blame Contribute Delete

2.45 kB

---
license: other
license_name: lfm1.0
language:
- en
base_model: unsloth/LFM2.5-230M
datasets:
- kth8/title-generation-10000x
pipeline_tag: text-generation
library_name: transformers
tags:
- sft
- trl
- unsloth
- liquid
- lfm2.5
---
![logo](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png)

A supervised fine-tune of [unsloth/LFM2.5-230M](https://huggingface.co/unsloth/LFM2.5-230M) on the [kth8/title-generation-10000x](https://huggingface.co/datasets/kth8/title-generation-10000x) dataset. Supports all 10 languages by the base model: English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish.

Trained with the system prompt used by OpenCode's [title agent](https://raw.githubusercontent.com/anomalyco/opencode/refs/heads/dev/packages/opencode/src/agent/prompt/title.txt). OpenCode generate thread title based on the first user message. OpenCode UI can show title up to 100 characters long before being truncated.

## Usage example

Point to this model with [small_model](https://opencode.ai/docs/config/#models) key in `opencode.jsonc` config file.

```json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "title": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "http://127.0.0.1:8080/v1",
        "apiKey": "not-needed"
      },
      "models": {
        "generator": {}
      }
    }
  },
  "small_model": "title/generator"
}
```

**User prompt**
```
Troy's home is 75 meters away from school while Emily's home is 98 meters away from school. Troy and Emily walk to school and back home every day. How much farther does Emily walk to school and back in five days?
```
**Title response**
```
Troy vs Emily five-day school walk distance difference
```

## Training Settings

### PEFT
- Rank: 16
- LoRA alpha: 16
- Modules: ["q_proj", "k_proj", "v_proj", "out_proj", "in_proj", "w1", "w2", "w3"]
- Gradient checkpointing: unsloth
### SFT
- Epoch: 1
- Batch size: 4
- Gradient Accumulation steps: 4
- Learning rate: 0.0002
- Optimizer: adamw_torch_fused
- Learning rate scheduler: cosine
- Warmup steps: 10
- Weight decay: 0.01
### Framework versions
- Unsloth: 2026.9.4
- TRL: 0.23.1
- Transformers: 5.5.0
- Pytorch: 2.10.0+cu128
- Datasets: 4.3.0
- Tokenizers: 0.22.2
## License
This model is released under [LFM Open License v1.0](https://huggingface.co/LiquidAI/LFM2.5-230M/raw/main/LICENSE).

	---
	license: other
	license_name: lfm1.0
	language:
	- en
	base_model: unsloth/LFM2.5-230M
	datasets:
	- kth8/title-generation-10000x
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- sft
	- trl
	- unsloth
	- liquid
	- lfm2.5
	---

	![logo](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png)

	A supervised fine-tune of [unsloth/LFM2.5-230M](https://huggingface.co/unsloth/LFM2.5-230M) on the [kth8/title-generation-10000x](https://huggingface.co/datasets/kth8/title-generation-10000x) dataset. Supports all 10 languages by the base model: English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish.

	Trained with the system prompt used by OpenCode's [title agent](https://raw.githubusercontent.com/anomalyco/opencode/refs/heads/dev/packages/opencode/src/agent/prompt/title.txt). OpenCode generate thread title based on the first user message. OpenCode UI can show title up to 100 characters long before being truncated.

	## Usage example

	Point to this model with [small_model](https://opencode.ai/docs/config/#models) key in `opencode.jsonc` config file.

	```json
	{
	"$schema": "https://opencode.ai/config.json",
	"provider": {
	"title": {
	"npm": "@ai-sdk/openai-compatible",
	"options": {
	"baseURL": "http://127.0.0.1:8080/v1",
	"apiKey": "not-needed"
	},
	"models": {
	"generator": {}
	}
	}
	},
	"small_model": "title/generator"
	}
	```

	User prompt
	```
	Troy's home is 75 meters away from school while Emily's home is 98 meters away from school. Troy and Emily walk to school and back home every day. How much farther does Emily walk to school and back in five days?
	```
	Title response
	```
	Troy vs Emily five-day school walk distance difference
	```

	## Training Settings

	### PEFT
	- Rank: 16
	- LoRA alpha: 16
	- Modules: ["q_proj", "k_proj", "v_proj", "out_proj", "in_proj", "w1", "w2", "w3"]
	- Gradient checkpointing: unsloth

	### SFT
	- Epoch: 1
	- Batch size: 4
	- Gradient Accumulation steps: 4
	- Learning rate: 0.0002
	- Optimizer: adamw_torch_fused
	- Learning rate scheduler: cosine
	- Warmup steps: 10
	- Weight decay: 0.01

	### Framework versions

	- Unsloth: 2026.9.4
	- TRL: 0.23.1
	- Transformers: 5.5.0
	- Pytorch: 2.10.0+cu128
	- Datasets: 4.3.0
	- Tokenizers: 0.22.2

	## License

	This model is released under [LFM Open License v1.0](https://huggingface.co/LiquidAI/LFM2.5-230M/raw/main/LICENSE).