Instructions to use solidrust/Chupacabra-7B-v2.01-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Chupacabra-7B-v2.01-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/Chupacabra-7B-v2.01-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Chupacabra-7B-v2.01-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Chupacabra-7B-v2.01-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use solidrust/Chupacabra-7B-v2.01-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/Chupacabra-7B-v2.01-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/Chupacabra-7B-v2.01-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/solidrust/Chupacabra-7B-v2.01-AWQ

SGLang

How to use solidrust/Chupacabra-7B-v2.01-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/Chupacabra-7B-v2.01-AWQ" \
    --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": "solidrust/Chupacabra-7B-v2.01-AWQ",
		"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 "solidrust/Chupacabra-7B-v2.01-AWQ" \
        --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": "solidrust/Chupacabra-7B-v2.01-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use solidrust/Chupacabra-7B-v2.01-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Chupacabra-7B-v2.01-AWQ
```

perlthoughts/Chupacabra-7B-v2.01 AWQ

Model creator: perlthoughts
Original model: Chupacabra-7B-v2.01

Model Summary

Dare-ties merge method.

List of all models and merging path is coming soon.

Purpose

Merging the "thick"est model weights from mistral models using amazing training methods like direct preference optimization (dpo) and reinforced learning.

I have spent countless hours studying the latest research papers, attending conferences, and networking with experts in the field. I experimented with different algorithms, tactics, fine-tuned hyperparameters, optimizers, and optimized code until i achieved the best possible results.

Thank you openchat 3.5 for showing me the way.

Here is my contribution.

Prompt Template

Replace {system} with your system prompt, and {prompt} with your prompt instruction.

### System:
{system}

### User:
{prompt}

### Assistant:

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

I32

F16

Collection including solidrust/Chupacabra-7B-v2.01-AWQ

7B AWQ

Collection

These models are selected for their compatibility with small 12GB memory GPUs. • 203 items • Updated Mar 2 • 2

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

68.860
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

86.120
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

63.900
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

63.500
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

80.510
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

59.670