Instructions to use braindao/iq-code-evmind-v3-granite-8b-instruct-all with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use braindao/iq-code-evmind-v3-granite-8b-instruct-all with Transformers:

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

pipe = pipeline("text-generation", model="braindao/iq-code-evmind-v3-granite-8b-instruct-all")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("braindao/iq-code-evmind-v3-granite-8b-instruct-all")
model = AutoModelForCausalLM.from_pretrained("braindao/iq-code-evmind-v3-granite-8b-instruct-all", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use braindao/iq-code-evmind-v3-granite-8b-instruct-all with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "braindao/iq-code-evmind-v3-granite-8b-instruct-all"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "braindao/iq-code-evmind-v3-granite-8b-instruct-all",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/braindao/iq-code-evmind-v3-granite-8b-instruct-all

SGLang

How to use braindao/iq-code-evmind-v3-granite-8b-instruct-all 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 "braindao/iq-code-evmind-v3-granite-8b-instruct-all" \
    --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": "braindao/iq-code-evmind-v3-granite-8b-instruct-all",
		"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 "braindao/iq-code-evmind-v3-granite-8b-instruct-all" \
        --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": "braindao/iq-code-evmind-v3-granite-8b-instruct-all",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use braindao/iq-code-evmind-v3-granite-8b-instruct-all with Docker Model Runner:
```
docker model run hf.co/braindao/iq-code-evmind-v3-granite-8b-instruct-all
```

This LLM, named braindao/iq-code-evmind-v3-granite-8b-instruct-all, is a specialized model for generating Solidity code.

It is based on ibm-granite/granite-8b-code-instruct and has been fine-tuned using the braindao/Solidity-Dataset.

The model focuses on the "average", "beginner", and "content" columns of the dataset, likely to provide code examples suitable for different skill levels.

This LLM is designed to assist with Solidity programming tasks, particularly for blockchain and smart contract development on Ethereum-compatible platforms.

Downloads last month: 25

Safetensors

Model size

8B params

Tensor type

F16

braindao
/

iq-code-evmind-v3-granite-8b-instruct-all

Dataset used to train braindao/iq-code-evmind-v3-granite-8b-instruct-all