Instructions to use solidrust/Falkor-7b-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Falkor-7b-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/Falkor-7b-AWQ")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Falkor-7b-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Falkor-7b-AWQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use solidrust/Falkor-7b-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/Falkor-7b-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/Falkor-7b-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/solidrust/Falkor-7b-AWQ

SGLang

How to use solidrust/Falkor-7b-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/Falkor-7b-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/Falkor-7b-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/Falkor-7b-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/Falkor-7b-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use solidrust/Falkor-7b-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Falkor-7b-AWQ
```

Configuration Parsing Warning:In config.json: "quantization_config.modules_to_not_convert" must be an array

perlthoughts/Falkor-7b AWQ

Model creator: perlthoughts
Original model: Falkor-7b

Model summary

dragon-mistral-7b-v0 part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Mistral-7B base model.

DRAGON models have been fine-tuned with the specific objective of fact-based question-answering over complex business and legal documents with an emphasis on reducing hallucinations and providing short, clear answers for workflow automation.

Downloads last month: 17

Safetensors

Model size

7B params

Tensor type

I32

F16

Collection including solidrust/Falkor-7b-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

68.260
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

85.840
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

63.980
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

63.080
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

80.350
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

60.500