Instructions to use botbotrobotics/cabra13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use botbotrobotics/cabra13b with Transformers:

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

pipe = pipeline("text-generation", model="botbotrobotics/cabra13b")

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

tokenizer = AutoTokenizer.from_pretrained("botbotrobotics/cabra13b")
model = AutoModelForCausalLM.from_pretrained("botbotrobotics/cabra13b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use botbotrobotics/cabra13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "botbotrobotics/cabra13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "botbotrobotics/cabra13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/botbotrobotics/cabra13b

SGLang

How to use botbotrobotics/cabra13b 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 "botbotrobotics/cabra13b" \
    --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": "botbotrobotics/cabra13b",
		"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 "botbotrobotics/cabra13b" \
        --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": "botbotrobotics/cabra13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use botbotrobotics/cabra13b with Docker Model Runner:
```
docker model run hf.co/botbotrobotics/cabra13b
```

cabra13b

Commit History

May 24, 2025

14:57
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
19f181c

Mar 31, 2024

03:38
Update README.md

nicolasdec

Verified signature
86c4ccc

Feb 27, 2024

15:01
Update README.md

nicolasdec

Verified signature
ee0a4e7

Feb 22, 2024

17:36
Update README.md

nicolasdec

Verified signature
9e6f721

Feb 17, 2024

22:04
Update README.md

nicolasdec

Verified signature
2fbcb8c
22:04
Update README.md

nicolasdec

Verified signature
38f23de
22:03
Update README.md

nicolasdec

Verified signature
2f9caa3

Aug 17, 2023

20:01
Create README.md

nicolasdec

c147386

Aug 9, 2023

19:14
Upload tokenizer

nicolasdec

4afd04a
19:13
Upload LlamaForCausalLM

nicolasdec

5d3e494
18:29
initial commit

nicolasdec

9a85a71

Commit History

May 24, 2025

Adding `safetensors` variant of this model⁠

Mar 31, 2024

Update README.md

Feb 27, 2024

Update README.md

Feb 22, 2024

Update README.md

Feb 17, 2024

Update README.md

Update README.md

Update README.md

Aug 17, 2023

Create README.md

Aug 9, 2023

Upload tokenizer

Upload LlamaForCausalLM

initial commit