Instructions to use nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora")

Transformers

How to use nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora with Transformers:

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

pipe = pipeline("text-generation", model="nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora

SGLang

How to use nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora 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 "nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora" \
    --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": "nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora",
		"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 "nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora" \
        --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": "nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora with Docker Model Runner:
```
docker model run hf.co/nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora
```

Reasoning with Emoji

Why?

Good question. I could carry on about advancing the frontiers of ML, but let's face it I did it for the lulz. I was just curious what would happen. Now I know. OK, I had some questions:

Can an LLM reason with emoji?
Would it be hilarious?

Is it good?

No. I believe my rewards were penalising reasoning length too heavily. It's also possible that reasoning with emojis is just a dumb idea. More research is needed.

Is it interesting?

Sure! It may lend evidence, although doesn't prove, the idea that model reasoning and CoT is actually doing what it appears to be doing, and the words it chooses are semantically relevant.

Future Directions

Further finetuning with rewards that encourage a longer reasoning phase
Different datasets - emoji might be unsuitable for mathematical reasoning

Usage

Use with `transformers`

from transformers import pipeline

pipe = pipeline("text-generation", "nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora")

SYSTEM_PROMPT = """
Respond in the following format:
<💭>
[emojis]
</💭>
<🎯>
[...]
</🎯>
"""

messages = [
  {"role": "system", "content": SYSTEM_PROMPT}
  {"role": "user", "content": "How may r's in Strawberry"}
]

response = pipe(messages)
print(response[0]["generated_text"][-1]["content"])

Development

Developed by: nomadicsynth
License: apache-2.0
Fine-tuning Notebook: Qwen2_5_(3B)_GRPO_emoji_hf.ipynb
Finetuned from model : unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 13

Model tree for nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit

Adapter

(9)

this model

nomadicsynth
/

Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora

Reasoning with Emoji

Why?

Is it good?

Is it interesting?

Future Directions

Usage

Use with `transformers`

Development

Model tree for nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora

Dataset used to train nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora

Reasoning with Emoji

Why?

Is it good?

Is it interesting?

Future Directions

Usage

Use with transformers

Development

Model tree for nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora

Dataset used to train nomadicsynth/Qwen2.5-3B-Instruct-emoji-reasoning-gsm8k-lora

Use with `transformers`