Instructions to use abacusai/Liberated-Qwen1.5-72B-c1000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacusai/Liberated-Qwen1.5-72B-c1000 with Transformers:

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

pipe = pipeline("text-generation", model="abacusai/Liberated-Qwen1.5-72B-c1000")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abacusai/Liberated-Qwen1.5-72B-c1000")
model = AutoModelForCausalLM.from_pretrained("abacusai/Liberated-Qwen1.5-72B-c1000")
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 abacusai/Liberated-Qwen1.5-72B-c1000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abacusai/Liberated-Qwen1.5-72B-c1000"
# 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/Liberated-Qwen1.5-72B-c1000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abacusai/Liberated-Qwen1.5-72B-c1000

SGLang

How to use abacusai/Liberated-Qwen1.5-72B-c1000 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/Liberated-Qwen1.5-72B-c1000" \
    --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/Liberated-Qwen1.5-72B-c1000",
		"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/Liberated-Qwen1.5-72B-c1000" \
        --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/Liberated-Qwen1.5-72B-c1000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abacusai/Liberated-Qwen1.5-72B-c1000 with Docker Model Runner:
```
docker model run hf.co/abacusai/Liberated-Qwen1.5-72B-c1000
```

Liberated-Qwen1.5-72B Checkpoint 1000

Please see (Liberated-Qwen1.5-72B)[https://huggingface.co/abacusai/Liberated-Qwen1.5-72B] for complete details on this model.

This is the same model at checkpoint 1000 which was evaluated on MT Bench. The results of the evaluation are in the model card for the main model.

Downloads last month: 6

Safetensors

Model size

72B params

Tensor type

F32

abacusai
/

Liberated-Qwen1.5-72B-c1000

Liberated-Qwen1.5-72B Checkpoint 1000

Datasets used to train abacusai/Liberated-Qwen1.5-72B-c1000