Instructions to use abacusai/Fewshot-Metamath-OrcaVicuna-Mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacusai/Fewshot-Metamath-OrcaVicuna-Mistral with Transformers:

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

pipe = pipeline("text-generation", model="abacusai/Fewshot-Metamath-OrcaVicuna-Mistral")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abacusai/Fewshot-Metamath-OrcaVicuna-Mistral")
model = AutoModelForCausalLM.from_pretrained("abacusai/Fewshot-Metamath-OrcaVicuna-Mistral")
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 abacusai/Fewshot-Metamath-OrcaVicuna-Mistral with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abacusai/Fewshot-Metamath-OrcaVicuna-Mistral

SGLang

How to use abacusai/Fewshot-Metamath-OrcaVicuna-Mistral 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 "abacusai/Fewshot-Metamath-OrcaVicuna-Mistral" \
    --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": "abacusai/Fewshot-Metamath-OrcaVicuna-Mistral",
		"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 "abacusai/Fewshot-Metamath-OrcaVicuna-Mistral" \
        --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": "abacusai/Fewshot-Metamath-OrcaVicuna-Mistral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abacusai/Fewshot-Metamath-OrcaVicuna-Mistral with Docker Model Runner:
```
docker model run hf.co/abacusai/Fewshot-Metamath-OrcaVicuna-Mistral
```

This model was trained on our MetamathFewshot dataset, as well as the Vicuna dataset and the OrcaChat dataset.

It has been finetuned from base Mistral 7B

Usage

This model uses a specific prompt format which is encoded as a chat template. To apply this, you can use the tokenizer.apply_chat_template() method of the attached tokenizer:

messages = [
    {"role": "user", "content": "What is the capital of Spain?"},
    {"role": "assistant", "content": "The capital of Spain is Madrid."}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)

Evaluation Results

HuggingFace Leaderboard

Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
67.33	59.64	81.82	61.69	53.23	78.45	69.14

For comparison the GSM8K score for the original metamath/MetaMath-Mistral-7B was 68.84 and average score was 65.78.

MT-Bench

Turn 1	Turn 2	Average
6.90	6.52	6.71

Training Details

Instruction tuned with the following parameters:

LORA, Rank 8, Alpha 16, Dropout 0.05, all modules (QKV and MLP)
3 epochs
Micro Batch Size 32 over 4xH100, gradient accumulation steps = 1
AdamW with learning rate 5e-5

Bias, Risks, and Limitations

The model has not been evaluated for safety and is only intended for research and experiments.

Downloads last month: 14

Safetensors

Model size

7B params

Tensor type

F16

Model tree for abacusai/Fewshot-Metamath-OrcaVicuna-Mistral

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(927)

this model

abacusai
/

Fewshot-Metamath-OrcaVicuna-Mistral