Instructions to use titan087/OpenLlama13B-Guanaco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use titan087/OpenLlama13B-Guanaco with Transformers:

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

pipe = pipeline("text-generation", model="titan087/OpenLlama13B-Guanaco")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("titan087/OpenLlama13B-Guanaco")
model = AutoModelForCausalLM.from_pretrained("titan087/OpenLlama13B-Guanaco", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use titan087/OpenLlama13B-Guanaco with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "titan087/OpenLlama13B-Guanaco"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "titan087/OpenLlama13B-Guanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/titan087/OpenLlama13B-Guanaco

SGLang

How to use titan087/OpenLlama13B-Guanaco 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 "titan087/OpenLlama13B-Guanaco" \
    --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": "titan087/OpenLlama13B-Guanaco",
		"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 "titan087/OpenLlama13B-Guanaco" \
        --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": "titan087/OpenLlama13B-Guanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use titan087/OpenLlama13B-Guanaco with Docker Model Runner:
```
docker model run hf.co/titan087/OpenLlama13B-Guanaco
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Open Llama 13b Finetuned using Qlora on the Guanaco dataset

datasets: - timdettmers/openassistant-guanaco

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	41.32
ARC (25-shot)	51.19
HellaSwag (10-shot)	75.24
MMLU (5-shot)	43.76
TruthfulQA (0-shot)	38.4
Winogrande (5-shot)	71.74
GSM8K (5-shot)	2.96
DROP (3-shot)	5.96

Downloads last month: 46

Safetensors

Model size

13B params

Tensor type

F32

F16

Model tree for titan087/OpenLlama13B-Guanaco

Quantizations

2 models

titan087
/

OpenLlama13B-Guanaco

datasets: - timdettmers/openassistant-guanaco

Open LLM Leaderboard Evaluation Results

Model tree for titan087/OpenLlama13B-Guanaco

Spaces using titan087/OpenLlama13B-Guanaco 28