Instructions to use razy101/emojify-300m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use razy101/emojify-300m with Transformers:

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

pipe = pipeline("text-generation", model="razy101/emojify-300m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("razy101/emojify-300m")
model = AutoModelForCausalLM.from_pretrained("razy101/emojify-300m", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use razy101/emojify-300m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "razy101/emojify-300m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "razy101/emojify-300m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/razy101/emojify-300m

SGLang

How to use razy101/emojify-300m 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 "razy101/emojify-300m" \
    --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": "razy101/emojify-300m",
		"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 "razy101/emojify-300m" \
        --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": "razy101/emojify-300m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use razy101/emojify-300m with Docker Model Runner:
```
docker model run hf.co/razy101/emojify-300m
```

license: apache-2.0 base_model: google/gemma-3-270m-it library_name: transformers tags: - unsloth - gemma-3 - emoji - translation - multilingual - gguf - edge-ai datasets: - custom-curated-emoji-distillation

🚀 Emojify-300M (Gemma-3-270M Fine-tuned)

Emojify-300M is a hyper-compact, specialized Large Language Model (LLM) designed for semantic text-to-emoji distillation. Based on the Gemma-3-270M-IT architecture, this model is optimized for edge computing and ultra-low latency applications.

🛠 Technical Specifications

Architecture: Gemma-3 (270M parameters)
Fine-tuning Method: LoRA (Low-Rank Adaptation) via Unsloth
Context Window: 2048 tokens
Language Support: Native Multilingual

📈 Performance & Benchmarks (Local CPU)

Tested on consumer-grade hardware (e.g., laptop CPU):

Prompt Evaluation: ~210 tokens/s
Token Generation (Eval): ~48 tokens/s
Total Latency: < 500ms (near-instant response)

🎯 Key Features

Zero-Shot Cross-Lingual Transfer: Leveraging Gemma 3's robust base weights, the model accurately processes languages not explicitly present in the fine-tuning set.
Noise Suppression: Specifically trained to inhibit conversational filler and "hallucinated" text, focusing strictly on relevant emoji output.
EOS Stability: Fine-tuned to respect End-of-Sequence (EOS) tokens, preventing the common "looping" behavior seen in smaller models.

Downloads last month: 17

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for razy101/emojify-300m

Base model

google/gemma-3-270m

Finetuned

google/gemma-3-270m-it

Finetuned

unsloth/gemma-3-270m-it

Finetuned

(422)

this model