Instructions to use nvmthanhhcmus/LORAV-DeepSeek-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvmthanhhcmus/LORAV-DeepSeek-Coder with Transformers:

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

pipe = pipeline("text-generation", model="nvmthanhhcmus/LORAV-DeepSeek-Coder")
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("nvmthanhhcmus/LORAV-DeepSeek-Coder")
model = AutoModelForCausalLM.from_pretrained("nvmthanhhcmus/LORAV-DeepSeek-Coder", 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 nvmthanhhcmus/LORAV-DeepSeek-Coder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nvmthanhhcmus/LORAV-DeepSeek-Coder

SGLang

How to use nvmthanhhcmus/LORAV-DeepSeek-Coder 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 "nvmthanhhcmus/LORAV-DeepSeek-Coder" \
    --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": "nvmthanhhcmus/LORAV-DeepSeek-Coder",
		"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 "nvmthanhhcmus/LORAV-DeepSeek-Coder" \
        --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": "nvmthanhhcmus/LORAV-DeepSeek-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use nvmthanhhcmus/LORAV-DeepSeek-Coder with Docker Model Runner:
```
docker model run hf.co/nvmthanhhcmus/LORAV-DeepSeek-Coder
```

Uploaded finetuned model

Developed by: nvmthanhhcmus
License: apache-2.0
Finetuned from model : nvmthanhhcmus/LORAV-DeepSeek-Coder

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Source Code

We will soon publish our source code.

We are currently reconstructing the source code by removing sensitive information of private HuggingFace token and SSH keys.

Downloads last month: 21

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for nvmthanhhcmus/LORAV-DeepSeek-Coder

Unable to build the model tree, the base model loops to the model itself. Learn more.