Instructions to use cplonski/cope-a-9b-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cplonski/cope-a-9b-merged with Transformers:

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

pipe = pipeline("text-generation", model="cplonski/cope-a-9b-merged")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cplonski/cope-a-9b-merged")
model = AutoModelForCausalLM.from_pretrained("cplonski/cope-a-9b-merged")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cplonski/cope-a-9b-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cplonski/cope-a-9b-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cplonski/cope-a-9b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cplonski/cope-a-9b-merged

SGLang

How to use cplonski/cope-a-9b-merged 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 "cplonski/cope-a-9b-merged" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cplonski/cope-a-9b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "cplonski/cope-a-9b-merged" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cplonski/cope-a-9b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cplonski/cope-a-9b-merged with Docker Model Runner:
```
docker model run hf.co/cplonski/cope-a-9b-merged
```

Cope-A-9B Merged Model

This model is a merged version of the Gemma-2-9B base model with the zentropi-ai/cope-a-9b LoRA adapter.

Base Model

Base Model: google/gemma-2-9b
LoRA Adapter: zentropi-ai/cope-a-9b

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("cplonski/cope-a-9b-merged")
tokenizer = AutoTokenizer.from_pretrained("cplonski/cope-a-9b-merged")

# Generate text
inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Model Details

Model Type: Causal Language Model
Architecture: Gemma-2
Parameters: ~9B
Merged from: Base model + LoRA adapter weights

Downloads last month: 6

Safetensors

Model size

9B params

Tensor type

F32

Model tree for cplonski/cope-a-9b-merged

Base model

google/gemma-2-9b

Adapter

(61)

this model

Adapters

1 model