Instructions to use braindao/iq-code-evmind-v2-llama3-code-8b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use braindao/iq-code-evmind-v2-llama3-code-8b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="braindao/iq-code-evmind-v2-llama3-code-8b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("braindao/iq-code-evmind-v2-llama3-code-8b-instruct")
model = AutoModelForCausalLM.from_pretrained("braindao/iq-code-evmind-v2-llama3-code-8b-instruct")
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]:]))

Inference
Local Apps Settings

vLLM

How to use braindao/iq-code-evmind-v2-llama3-code-8b-instruct 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-v2-llama3-code-8b-instruct"
# 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-v2-llama3-code-8b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/braindao/iq-code-evmind-v2-llama3-code-8b-instruct

SGLang

How to use braindao/iq-code-evmind-v2-llama3-code-8b-instruct 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-v2-llama3-code-8b-instruct" \
    --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-v2-llama3-code-8b-instruct",
		"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-v2-llama3-code-8b-instruct" \
        --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-v2-llama3-code-8b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use braindao/iq-code-evmind-v2-llama3-code-8b-instruct with Docker Model Runner:
```
docker model run hf.co/braindao/iq-code-evmind-v2-llama3-code-8b-instruct
```

brunneis commited on May 31, 2024

Commit

f734035

verified ·

1 Parent(s): 576d28b

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -5

README.md CHANGED Viewed

@@ -9,11 +9,11 @@ language:
 tags:
 - solidity
 - code
-- braindao/iq-code-evmind-v1-llama3-coder-8b-instruct
 ---
-The iq-code-evmind-v1-code-llama3-8b-instruct-pro model is a finely-tuned version specifically designed to generate and resolve queries related to the Solidity programming language. This model has been developed from the robust foundation provided by ajibawa-2023/Code-Llama-3-8B and has undergone specialized fine-tuning to optimize its performance in tasks associated with Solidity, the primary language used for developing smart contracts on the Ethereum blockchain.
-Key Features:
 Solidity Code Generation: The model can generate Solidity code snippets, offering quick and accurate solutions for various development needs.
 Query Resolution: It answers technical and conceptual questions about Solidity, covering basic concepts to advanced topics, facilitating learning and problem-solving.
@@ -27,13 +27,13 @@ Base Model:
 This model is based on ajibawa-2023/Code-Llama-3-8B, known for its advanced code generation capabilities and deep understanding of programming languages.
-How to Use:
 You can integrate this model into your projects via the Hugging Face platform, utilizing the provided APIs and tools to facilitate its implementation and use in various applications.
 Example Usage:
-python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 model_name = "your-username/iq-code-evmind-v1-code-llama3-8b-instruct-pro"
@@ -44,4 +44,6 @@ input_text = "How can I define a basic contract structure in Solidity?"
 inputs = tokenizer(input_text, return_tensors="pt")
 outputs = model.generate(**inputs)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 With iq-code-evmind-v1-code-llama3-8b-instruct-pro, you will have a powerful and specialized tool to handle everything related to Solidity development, from code generation to technical query resolution.

 tags:
 - solidity
 - code
+- ajibawa-2023/Code-Llama-3-8B
 ---
+This model is a finely-tuned version specifically designed to generate and resolve queries related to the Solidity programming language. This model has been developed from the robust foundation provided by `ajibawa-2023/Code-Llama-3-8B` and has undergone specialized fine-tuning to optimize its performance in tasks associated with Solidity, the primary language used for developing smart contracts on the Ethereum blockchain.
+## Key Features:
 Solidity Code Generation: The model can generate Solidity code snippets, offering quick and accurate solutions for various development needs.
 Query Resolution: It answers technical and conceptual questions about Solidity, covering basic concepts to advanced topics, facilitating learning and problem-solving.
 This model is based on ajibawa-2023/Code-Llama-3-8B, known for its advanced code generation capabilities and deep understanding of programming languages.
+## How to Use:
 You can integrate this model into your projects via the Hugging Face platform, utilizing the provided APIs and tools to facilitate its implementation and use in various applications.
 Example Usage:
+```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 model_name = "your-username/iq-code-evmind-v1-code-llama3-8b-instruct-pro"
 inputs = tokenizer(input_text, return_tensors="pt")
 outputs = model.generate(**inputs)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 With iq-code-evmind-v1-code-llama3-8b-instruct-pro, you will have a powerful and specialized tool to handle everything related to Solidity development, from code generation to technical query resolution.