# DeepSeek Coder

{% hint style="info" %}
**Newer versions available!** [**DeepSeek-R1**](https://docs.clore.ai/guides/language-models/deepseek-r1) (reasoning + coding) and [**DeepSeek-V3**](https://docs.clore.ai/guides/language-models/deepseek-v3) (general purpose) are significantly more capable. Also see [**Qwen2.5-Coder**](https://docs.clore.ai/guides/language-models/qwen25) for a strong coding alternative.
{% endhint %}

Best-in-class code generation with DeepSeek Coder models.

{% hint style="success" %}
All examples can be run on GPU servers rented through [CLORE.AI Marketplace](https://clore.ai/marketplace).
{% endhint %}

## Renting on CLORE.AI

1. Visit [CLORE.AI Marketplace](https://clore.ai/marketplace)
2. Filter by GPU type, VRAM, and price
3. Choose **On-Demand** (fixed rate) or **Spot** (bid price)
4. Configure your order:
   * Select Docker image
   * Set ports (TCP for SSH, HTTP for web UIs)
   * Add environment variables if needed
   * Enter startup command
5. Select payment: **CLORE**, **BTC**, or **USDT/USDC**
6. Create order and wait for deployment

### Access Your Server

* Find connection details in **My Orders**
* Web interfaces: Use the HTTP port URL
* SSH: `ssh -p <port> root@<proxy-address>`

## What is DeepSeek Coder?

DeepSeek Coder offers:

* State-of-the-art code generation
* 338 programming languages
* Fill-in-the-middle support
* Repository-level understanding

## Model Variants

| Model               | Parameters | VRAM  | Context |
| ------------------- | ---------- | ----- | ------- |
| DeepSeek-Coder-1.3B | 1.3B       | 3GB   | 16K     |
| DeepSeek-Coder-6.7B | 6.7B       | 8GB   | 16K     |
| DeepSeek-Coder-33B  | 33B        | 40GB  | 16K     |
| DeepSeek-Coder-V2   | 16B/236B   | 20GB+ | 128K    |

## Quick Deploy

**Docker Image:**

```
pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime
```

**Ports:**

```
22/tcp
8000/http
```

**Command:**

```bash
pip install vllm && \
vllm serve deepseek-ai/deepseek-coder-6.7b-instruct --port 8000
```

## Accessing Your Service

After deployment, find your `http_pub` URL in **My Orders**:

1. Go to **My Orders** page
2. Click on your order
3. Find the `http_pub` URL (e.g., `abc123.clorecloud.net`)

Use `https://YOUR_HTTP_PUB_URL` instead of `localhost` in examples below.

## Using Ollama

```bash

# Run DeepSeek Coder
ollama run deepseek-coder

# Specific sizes
ollama run deepseek-coder:1.3b
ollama run deepseek-coder:6.7b
ollama run deepseek-coder:33b

# V2 (latest)
ollama run deepseek-coder-v2
```

## Installation

```bash
pip install transformers accelerate torch
```

## Code Generation

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "deepseek-ai/deepseek-coder-6.7b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {"role": "user", "content": """
Write a Python class for a REST API client with:
- Authentication support
- Retry logic with exponential backoff
- Request/response logging
"""}
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to("cuda")

outputs = model.generate(
    inputs,
    max_new_tokens=1024,
    temperature=0.2,
    do_sample=True
)

print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
```

## Fill-in-the-Middle (FIM)

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "deepseek-ai/deepseek-coder-6.7b-base"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

# Fill-in-the-middle format
prefix = """def calculate_statistics(data):
    \"\"\"Calculate mean, median, and std of a list.\"\"\"
    import statistics

    mean = statistics.mean(data)
"""

suffix = """
    return {
        'mean': mean,
        'median': median,
        'std': std
    }
"""

# FIM tokens
prompt = f"<｜fim▁begin｜>{prefix}<｜fim▁hole｜>{suffix}<｜fim▁end｜>"

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=128)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## DeepSeek-Coder-V2

Latest and most powerful:

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {"role": "user", "content": "Implement a thread-safe LRU cache in Python"}
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.2)
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
```

## vLLM Server

```bash
vllm serve deepseek-ai/deepseek-coder-6.7b-instruct \
    --port 8000 \
    --dtype bfloat16 \
    --max-model-len 16384 \
    --trust-remote-code
```

### API Usage

```python
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="x")

response = client.chat.completions.create(
    model="deepseek-ai/deepseek-coder-6.7b-instruct",
    messages=[
        {"role": "system", "content": "You are an expert programmer."},
        {"role": "user", "content": "Write a FastAPI websocket server"}
    ],
    temperature=0.2,
    max_tokens=1500
)

print(response.choices[0].message.content)
```

## Code Review

````python
code_to_review = """
def process_data(data):
    result = []
    for i in range(len(data)):
        if data[i] > 0:
            result.append(data[i] * 2)
    return result
"""

messages = [
    {"role": "user", "content": f"""
Review this code and suggest improvements:

```python
{code_to_review}
````

Focus on:

1. Performance
2. Readability
3. Best practices """} ]

````

## Bug Fixing

```python
buggy_code = """
def merge_sorted_lists(list1, list2):
    result = []
    i = j = 0
    while i < len(list1) and j < len(list2):
        if list1[i] < list2[j]:
            result.append(list1[i])
            i += 1
        else:
            result.append(list2[j])
    return result
"""

messages = [
    {"role": "user", "content": f"""
Find and fix the bug in this code:

```python
{buggy_code}
````

"""} ]

````

## Gradio Interface

```python
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "deepseek-ai/deepseek-coder-6.7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
)

def generate_code(prompt, temperature, max_tokens):
    messages = [{"role": "user", "content": prompt}]
    inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
    outputs = model.generate(inputs, max_new_tokens=max_tokens, temperature=temperature, do_sample=True)
    return tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)

demo = gr.Interface(
    fn=generate_code,
    inputs=[
        gr.Textbox(label="Prompt", lines=5, placeholder="Describe the code you need..."),
        gr.Slider(0.1, 1.0, value=0.2, label="Temperature"),
        gr.Slider(256, 2048, value=1024, step=128, label="Max Tokens")
    ],
    outputs=gr.Code(language="python", label="Generated Code"),
    title="DeepSeek Coder"
)

demo.launch(server_name="0.0.0.0", server_port=7860)
````

## Performance

| Model            | GPU      | Tokens/sec |
| ---------------- | -------- | ---------- |
| DeepSeek-1.3B    | RTX 3060 | \~120      |
| DeepSeek-6.7B    | RTX 3090 | \~70       |
| DeepSeek-6.7B    | RTX 4090 | \~100      |
| DeepSeek-33B     | A100     | \~40       |
| DeepSeek-V2-Lite | RTX 4090 | \~50       |

## Comparison

| Model              | HumanEval | Code Quality |
| ------------------ | --------- | ------------ |
| DeepSeek-Coder-33B | 79.3%     | Excellent    |
| CodeLlama-34B      | 53.7%     | Good         |
| GPT-3.5-Turbo      | 72.6%     | Good         |

## Troubleshooting

### Code completion not working

* Ensure correct prompt format with `<|fim_prefix|>`, `<|fim_suffix|>`, `<|fim_middle|>`
* Set appropriate `max_new_tokens` for code generation

### Model outputs garbage

* Check model is fully downloaded
* Verify CUDA is being used: `model.device`
* Try lower temperature (0.2-0.5 for code)

### Slow inference

* Use vLLM for 5-10x speedup
* Enable `torch.compile()` for transformers
* Use quantized model for large variants

### Import errors

* Install dependencies: `pip install transformers accelerate`
* Update PyTorch to 2.0+

## Cost Estimate

Typical CLORE.AI marketplace rates (as of 2024):

| GPU       | Hourly Rate | Daily Rate | 4-Hour Session |
| --------- | ----------- | ---------- | -------------- |
| RTX 3060  | \~$0.03     | \~$0.70    | \~$0.12        |
| RTX 3090  | \~$0.06     | \~$1.50    | \~$0.25        |
| RTX 4090  | \~$0.10     | \~$2.30    | \~$0.40        |
| A100 40GB | \~$0.17     | \~$4.00    | \~$0.70        |
| A100 80GB | \~$0.25     | \~$6.00    | \~$1.00        |

*Prices vary by provider and demand. Check* [*CLORE.AI Marketplace*](https://clore.ai/marketplace) *for current rates.*

**Save money:**

* Use **Spot** market for flexible workloads (often 30-50% cheaper)
* Pay with **CLORE** tokens
* Compare prices across different providers

## Next Steps

* [DeepSeek-V3](https://docs.clore.ai/guides/language-models/deepseek-v3) - Latest DeepSeek flagship model
* [CodeLlama](https://docs.clore.ai/guides/language-models/codellama) - Alternative code model
* [Qwen2.5-Coder](https://docs.clore.ai/guides/language-models/qwen25) - Alibaba's code model
* [vLLM](https://docs.clore.ai/guides/language-models/vllm) - Production deployment