Instructions to use Deci/DeciLM-7B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Deci/DeciLM-7B-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Deci/DeciLM-7B-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Deci/DeciLM-7B-instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Deci/DeciLM-7B-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Deci/DeciLM-7B-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Deci/DeciLM-7B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Deci/DeciLM-7B-instruct

SGLang

How to use Deci/DeciLM-7B-instruct 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 "Deci/DeciLM-7B-instruct" \
    --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": "Deci/DeciLM-7B-instruct",
		"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 "Deci/DeciLM-7B-instruct" \
        --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": "Deci/DeciLM-7B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Deci/DeciLM-7B-instruct with Docker Model Runner:
```
docker model run hf.co/Deci/DeciLM-7B-instruct
```

harpreetsahota commited on Dec 12, 2023

Commit

1fb44f8

1 Parent(s): b0b6c53

Update README.md

Browse files

Files changed (1) hide show

README.md +29 -7

README.md CHANGED Viewed

@@ -43,19 +43,41 @@ The model is intended for commercial and research use in English.
 Use the code below to get started with the model.
-```bibtex
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
 model_name = "Deci/DeciLM-7B-instruct"
 device = "cuda" # for GPU usage or "cpu" for CPU usage
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True).to(device)
-inputs = tokenizer.encode("In a shocking finding, scientists discovered a herd of unicorns living in", return_tensors="pt").to(device)
-outputs = model.generate(inputs, max_new_tokens=100, do_sample=True, top_p=0.95)
-print(tokenizer.decode(outputs[0]))
 ```
 ## Evaluation

 Use the code below to get started with the model.
+```python
 import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, pipeline
 model_name = "Deci/DeciLM-7B-instruct"
 device = "cuda" # for GPU usage or "cpu" for CPU usage
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit = True,
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    trust_remote_code=True,
+    quantization_config=bnb_config
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+tokenizer.pad_token = tokenizer.eos_token
+deci_generator = pipeline("text-generation",
+                          model=model,
+                          tokenizer=tokenizer,
+                          temperature=0.1,
+                          device_map="auto",
+                          max_length=4096,
+                          return_full_text=False
+)
+prompt = "How do I make the most delicious pancakes the world has ever tasted?"
+response = deci_generator(prompt)[0]['generated_text']
+print(response)
 ```
 ## Evaluation