Instructions to use AlfredPros/CodeLlama-7b-Instruct-Solidity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlfredPros/CodeLlama-7b-Instruct-Solidity with Transformers:

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

pipe = pipeline("text-generation", model="AlfredPros/CodeLlama-7b-Instruct-Solidity")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlfredPros/CodeLlama-7b-Instruct-Solidity")
model = AutoModelForCausalLM.from_pretrained("AlfredPros/CodeLlama-7b-Instruct-Solidity")

Inference
Local Apps Settings

vLLM

How to use AlfredPros/CodeLlama-7b-Instruct-Solidity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlfredPros/CodeLlama-7b-Instruct-Solidity"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlfredPros/CodeLlama-7b-Instruct-Solidity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AlfredPros/CodeLlama-7b-Instruct-Solidity

SGLang

How to use AlfredPros/CodeLlama-7b-Instruct-Solidity 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 "AlfredPros/CodeLlama-7b-Instruct-Solidity" \
    --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": "AlfredPros/CodeLlama-7b-Instruct-Solidity",
		"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 "AlfredPros/CodeLlama-7b-Instruct-Solidity" \
        --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": "AlfredPros/CodeLlama-7b-Instruct-Solidity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AlfredPros/CodeLlama-7b-Instruct-Solidity with Docker Model Runner:
```
docker model run hf.co/AlfredPros/CodeLlama-7b-Instruct-Solidity
```

AlfredPros commited on Nov 5, 2023

Commit

10dfdbe

1 Parent(s): 1708595

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -153,7 +153,7 @@ Use the Task below and the Input given to write the Response, which is a program
 # Tokenize the input
 input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda()
 # Run the model to infere an output
-outputs = model.generate(input_ids=input_ids, max_new_tokens=256, do_sample=True, top_p=0.9, temperature=0.001, pad_token_id=1)
 # Detokenize and display the generated output
 print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):])

 # Tokenize the input
 input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda()
 # Run the model to infere an output
+outputs = model.generate(input_ids=input_ids, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.001, pad_token_id=1)
 # Detokenize and display the generated output
 print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):])