Instructions to use robertthecreator/deepseek-coder-secure-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use robertthecreator/deepseek-coder-secure-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-1.3b-base")
model = PeftModel.from_pretrained(base_model, "robertthecreator/deepseek-coder-secure-lora")

Transformers

How to use robertthecreator/deepseek-coder-secure-lora with Transformers:

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

pipe = pipeline("text-generation", model="robertthecreator/deepseek-coder-secure-lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("robertthecreator/deepseek-coder-secure-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use robertthecreator/deepseek-coder-secure-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/robertthecreator/deepseek-coder-secure-lora

SGLang

How to use robertthecreator/deepseek-coder-secure-lora 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 "robertthecreator/deepseek-coder-secure-lora" \
    --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": "robertthecreator/deepseek-coder-secure-lora",
		"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 "robertthecreator/deepseek-coder-secure-lora" \
        --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": "robertthecreator/deepseek-coder-secure-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use robertthecreator/deepseek-coder-secure-lora with Docker Model Runner:
```
docker model run hf.co/robertthecreator/deepseek-coder-secure-lora
```

deepseek-coder-secure-lora

File size: 1,159 Bytes

99b4b36

{
  "best_metric": 1.6711045503616333,
  "best_model_checkpoint": "./best_model/checkpoint-524",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 524,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9541984732824428,
      "grad_norm": 0.08830071985721588,
      "learning_rate": 8.091603053435115e-06,
      "loss": 1.9773,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6711045503616333,
      "eval_runtime": 48.1017,
      "eval_samples_per_second": 9.688,
      "eval_steps_per_second": 1.227,
      "step": 524
    }
  ],
  "logging_steps": 500,
  "max_steps": 2620,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.680497543479296e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}