Instructions to use solidrust/Copus-2x8B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Copus-2x8B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/Copus-2x8B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Copus-2x8B-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Copus-2x8B-AWQ")
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

vLLM

How to use solidrust/Copus-2x8B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/Copus-2x8B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/Copus-2x8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/Copus-2x8B-AWQ

SGLang

How to use solidrust/Copus-2x8B-AWQ 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 "solidrust/Copus-2x8B-AWQ" \
    --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": "solidrust/Copus-2x8B-AWQ",
		"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 "solidrust/Copus-2x8B-AWQ" \
        --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": "solidrust/Copus-2x8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/Copus-2x8B-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Copus-2x8B-AWQ
```

Copus-2x8B-AWQ

Commit History

Added base_model tag in README.md

a132267
verified

Suparious commited on Sep 3, 2024

Update README.md

2260e70
verified

Suparious commited on Apr 24, 2024

adding initial model card

82e3f07

Ubuntu commited on Apr 23, 2024

adding quant config

969f7db

Ubuntu commited on Apr 23, 2024

adding AWQ model

c5fb3ee

Ubuntu commited on Apr 23, 2024

add processing notice

f9d3e49

Ubuntu commited on Apr 23, 2024

initial commit

90acf3a
verified

Suparious commited on Apr 23, 2024

Commit History

Added base_model tag in README.md a132267 verified

Update README.md 2260e70 verified

adding initial model card 82e3f07

adding quant config 969f7db

adding AWQ model c5fb3ee

add processing notice f9d3e49

initial commit 90acf3a verified

Added base_model tag in README.md

a132267
verified

Update README.md

2260e70
verified

adding initial model card

82e3f07

adding quant config

969f7db

adding AWQ model

c5fb3ee

add processing notice

f9d3e49

initial commit

90acf3a
verified