Instructions to use llm-agents/tora-code-34b-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llm-agents/tora-code-34b-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="llm-agents/tora-code-34b-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llm-agents/tora-code-34b-v1.0")
model = AutoModelForCausalLM.from_pretrained("llm-agents/tora-code-34b-v1.0")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use llm-agents/tora-code-34b-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llm-agents/tora-code-34b-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llm-agents/tora-code-34b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/llm-agents/tora-code-34b-v1.0

SGLang

How to use llm-agents/tora-code-34b-v1.0 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 "llm-agents/tora-code-34b-v1.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llm-agents/tora-code-34b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "llm-agents/tora-code-34b-v1.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llm-agents/tora-code-34b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use llm-agents/tora-code-34b-v1.0 with Docker Model Runner:
```
docker model run hf.co/llm-agents/tora-code-34b-v1.0
```

Chat template for this model?

by lewtun - opened May 26, 2024

Discussion

lewtun

May 26, 2024

Hello, thanks for open sourcing this very nice math LLM! Can you share how one should run inference with this model and what type of chat template should be used?

Thanks!

Elchamaa

Nov 7, 2025

coming a little late, any updates on the model.
You’ve shown ToRA can reason through complex math by using external tools — how far do you see that architecture extending beyond math? Could ToRA become a general reasoning layer for other domains?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment