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
```

kth8 commited on Sep 12

Commit

4da61ae

verified ·

1 Parent(s): ae379e5

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ language:
 - en
 base_model: unsloth/LFM2.5-230M
 datasets:
-- kth8/title-generation-10000x-english
 pipeline_tag: text-generation
 library_name: transformers
 tags:
@@ -18,7 +18,7 @@ tags:
 ![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.
 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.

 - en
 base_model: unsloth/LFM2.5-230M
 datasets:
+- kth8/title-generation-10000x
 pipeline_tag: text-generation
 library_name: transformers
 tags:
 ![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.