Instructions to use i04n4/math-solver-llama3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use i04n4/math-solver-llama3 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "i04n4/math-solver-llama3")

Transformers

How to use i04n4/math-solver-llama3 with Transformers:

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

pipe = pipeline("text-generation", model="i04n4/math-solver-llama3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("i04n4/math-solver-llama3", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use i04n4/math-solver-llama3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "i04n4/math-solver-llama3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "i04n4/math-solver-llama3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/i04n4/math-solver-llama3

SGLang

How to use i04n4/math-solver-llama3 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 "i04n4/math-solver-llama3" \
    --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": "i04n4/math-solver-llama3",
		"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 "i04n4/math-solver-llama3" \
        --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": "i04n4/math-solver-llama3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use i04n4/math-solver-llama3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for i04n4/math-solver-llama3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for i04n4/math-solver-llama3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for i04n4/math-solver-llama3 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="i04n4/math-solver-llama3",
    max_seq_length=2048,
)

Docker Model Runner
How to use i04n4/math-solver-llama3 with Docker Model Runner:
```
docker model run hf.co/i04n4/math-solver-llama3
```

Model Card for Model ID

Model Description

Answers simple math problems, being capable of reasoning and Chain-of-Thought

Developed by: Super Awesome Team Name
Model type: LLM
Language(s) (NLP): English
License:
Finetuned from model [optional]: unsloth/Llama3-8B-Instruct

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Downloads last month: -

Model tree for i04n4/math-solver-llama3

Base model

unsloth/llama-3-8b-Instruct-bnb-4bit

Adapter

(157)

this model

Adapters

1 model