Instructions to use CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412 with Transformers:

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

pipe = pipeline("text-generation", model="CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412")
model = AutoModelForMultimodalLM.from_pretrained("CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412")
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 CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412

SGLang

How to use CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412 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 "CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412" \
    --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": "CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412",
		"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 "CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412" \
        --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": "CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412 with Docker Model Runner:
```
docker model run hf.co/CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Vicuna Model Card

Model Details

Minecraft-Vicuna is a chat assistant trained by fine-tuning Vicuna v1.5 on conversations collected from CraftJarvis.

Developed by: CraftJarvis
Model type: An auto-regressive language model based on the transformer architecture
License: Llama 2 Community License Agreement
Finetuned from model: Vicuna 1.5

Model Sources

Paper: OmniJARVIS, https://arxiv.org/abs/2407.00114

Uses

The primary use of Minecraft-Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.

How to Get Started with the Model

Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api

Training Details

TODO.

Evaluation

TODO.

Downloads last month: -

Safetensors

Model size

7B params

Tensor type

F32

Model tree for CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412

Base model

lmsys/vicuna-7b-v1.5

Finetuned

(65)

this model

Paper for CraftJarvis/Minecraft-Vicuna-v1.5-7B-2412

OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents

Paper • 2407.00114 • Published Jun 27, 2024 • 13