Instructions to use deepseek-ai/deepseek-coder-6.7b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/deepseek-coder-6.7b-base with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/deepseek-coder-6.7b-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-6.7b-base")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/deepseek-coder-6.7b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/deepseek-coder-6.7b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-coder-6.7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-coder-6.7b-base

SGLang

How to use deepseek-ai/deepseek-coder-6.7b-base 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 "deepseek-ai/deepseek-coder-6.7b-base" \
    --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": "deepseek-ai/deepseek-coder-6.7b-base",
		"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 "deepseek-ai/deepseek-coder-6.7b-base" \
        --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": "deepseek-ai/deepseek-coder-6.7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepseek-ai/deepseek-coder-6.7b-base with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/deepseek-coder-6.7b-base
```

trained on old code

by fawogin598 - opened Jan 5, 2024

Discussion

fawogin598

Jan 5, 2024

Unfortunately, it was trained on data dating before 2023.
"prompt":"write sveltekit code for a todo app"
"response": "Sure, below is a basic example of a Todo application in SvelteKit. This includes creating and deleting todos:\n\n1. Firstly, install SvelteKit if you haven't done so yet:\nbash\nnpx degit sveltejs/svelte-kit my-app\ncd my-app\nnpm install\n\n2. Create a new file src/routes/index.svelte for the todo app:\n\nsvelte\n<script>\n let todos = [];\n let inputValue = \"\";\n \n function addTodo() {\n if (inputValue !== \"\") {\n todos = [...todos, inputValue];\n inputValue = \"\";\n }\n }\n\n function deleteTodo(index) {\n todos = todos.filter((_, i) => i !== index);\n }\n</script>\n\n<input bind:value={inputValue} type=\"text\">\n<button on:click={addTodo}>Add Todo</button>\n\n<ul>\n {#each todos as todo, index (index)}\n <li>\n {todo} \n <button on:click={() => deleteTodo(index)}>Delete</button>\n </li>\n {/each}\n</ul>\n\n3. Run the application by using npm run dev command in your terminal and then opening localhost:5000 in your browser to view the result.\n\nThis is a very basic example, you may want to persist data (like saving todos to a database) or handle errors/edge cases based on your needs. For that, SvelteKit provides several features like actions and stores which can be used as per requirements.\n",
This is not recent sveltekit (routes/+page.svelte, ...).
So sad, it's a pretty fast model.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment