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

Libraries

How to use rishiraj/zephyr-math with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rishiraj/zephyr-math")
model = AutoModelForCausalLM.from_pretrained("rishiraj/zephyr-math")
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 rishiraj/zephyr-math with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rishiraj/zephyr-math

SGLang

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

Docker Model Runner
How to use rishiraj/zephyr-math with Docker Model Runner:
```
docker model run hf.co/rishiraj/zephyr-math
```

zephyr-math / training_params.json

rishiraj

Upload folder using huggingface_hub

c3a18e8 over 2 years ago

Raw

History Blame Contribute Delete

956 Bytes

{"model": "HuggingFaceH4/zephyr-7b-alpha", "data_path": "data/", "project_name": "zephyr-math", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 2e-05, "epochs": 3, "batch_size": 4, "warmup_ratio": 0.03, "gradient_accumulation": 4, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": 10, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "rishiraj/zephyr-math", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": true, "username": null, "use_flash_attention_2": false, "log": "wandb", "disable_gradient_checkpointing": false}