Instructions to use mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds with Transformers:

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

pipe = pipeline("text-generation", model="mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds")
model = AutoModelForCausalLM.from_pretrained("mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds

SGLang

How to use mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds 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 "mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds" \
    --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": "mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds",
		"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 "mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds" \
        --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": "mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds with Docker Model Runner:
```
docker model run hf.co/mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds
```

mgoin commited on Nov 7, 2023

Commit

dd8d5d2

1 Parent(s): 53fd54d

Create README.md

Browse files

Files changed (1) hide show

README.md +38 -0

README.md ADDED Viewed

	@@ -0,0 +1,38 @@

+---
+tags:
+- deepsparse
+---
+## DeepSparse One-Shot and Export of https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct
+Prompt Template:
+```python
+prompt = f"### Instruction:{input}### Response:"
+```
+## Usage
+```python
+from deepsparse import TextGeneration
+model = TextGeneration(model="hf:mgoin/deepseek-coder-1.3b-instruct-pruned50-quant-ds")
+print(model("#write a quick sort algorithm in python", max_new_tokens=200).generations[0].text)
+"""
+def quick_sort(arr):
+    if len(arr) == 0:
+        return arr
+    else:
+        pivot = arr[0]
+        left = []
+        right = []
+        for i in range(1, len(arr)):
+            if arr[i] < pivot:
+                left.append(arr[i])
+            else:
+                right.append(arr[i])
+        return quick_sort(left) + [pivot] + quick_sort(right)
+print(quick_sort([3, 9, 2, 5, 4, 7, 1]))
+print(quick_sort([1, 2, 3, 4, 5, 6]))
+print(quick_sort([6, 5, 4, 3, 2, 1]))
+"""
+```