Instructions to use abacusai/Dracarys2-72B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacusai/Dracarys2-72B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="abacusai/Dracarys2-72B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abacusai/Dracarys2-72B-Instruct")
model = AutoModelForCausalLM.from_pretrained("abacusai/Dracarys2-72B-Instruct", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abacusai/Dracarys2-72B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abacusai/Dracarys2-72B-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": "abacusai/Dracarys2-72B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abacusai/Dracarys2-72B-Instruct

SGLang

How to use abacusai/Dracarys2-72B-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 "abacusai/Dracarys2-72B-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": "abacusai/Dracarys2-72B-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 "abacusai/Dracarys2-72B-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": "abacusai/Dracarys2-72B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abacusai/Dracarys2-72B-Instruct with Docker Model Runner:
```
docker model run hf.co/abacusai/Dracarys2-72B-Instruct
```

sreemanti-abacus

osanseviero commited on Oct 31, 2024

Commit

298cb07

verified ·

1 Parent(s): cbaa190

Fix library tag (#4)

Browse files

- Fix library tag (d559defe4982f665d5e465e6d9073d5012f60cd2)

Co-authored-by: Omar Sanseviero <osanseviero@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -7,6 +7,7 @@ tags:
 license_name: tongyi-qianwen
 license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
 pipeline_tag: text-generation
 ---
 # Dracarys2-72B-Instruct
@@ -96,4 +97,4 @@ print(outputs[0]["generated_text"][len(prompt):])
 | Model                     | Easy            | Medium         | Hard                  |
 |---------------------------|-----------------|----------------|-----------------------|
 | **Dracarys2-72B-Instruct**| **79.25**       | **53.76**      | **37.63**             |
-| Qwen2.5-72B-Instruct      |  68.43          |  39.46         |  22.22                |

 license_name: tongyi-qianwen
 license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
 pipeline_tag: text-generation
+library_name: transformers
 ---
 # Dracarys2-72B-Instruct
 | Model                     | Easy            | Medium         | Hard                  |
 |---------------------------|-----------------|----------------|-----------------------|
 | **Dracarys2-72B-Instruct**| **79.25**       | **53.76**      | **37.63**             |
+| Qwen2.5-72B-Instruct      |  68.43          |  39.46         |  22.22                |