Instructions to use athirdpath/Orca-2-13b-Alpaca-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athirdpath/Orca-2-13b-Alpaca-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="athirdpath/Orca-2-13b-Alpaca-Uncensored")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("athirdpath/Orca-2-13b-Alpaca-Uncensored")
model = AutoModelForCausalLM.from_pretrained("athirdpath/Orca-2-13b-Alpaca-Uncensored")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use athirdpath/Orca-2-13b-Alpaca-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "athirdpath/Orca-2-13b-Alpaca-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "athirdpath/Orca-2-13b-Alpaca-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/athirdpath/Orca-2-13b-Alpaca-Uncensored

SGLang

How to use athirdpath/Orca-2-13b-Alpaca-Uncensored 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 "athirdpath/Orca-2-13b-Alpaca-Uncensored" \
    --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": "athirdpath/Orca-2-13b-Alpaca-Uncensored",
		"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 "athirdpath/Orca-2-13b-Alpaca-Uncensored" \
        --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": "athirdpath/Orca-2-13b-Alpaca-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use athirdpath/Orca-2-13b-Alpaca-Uncensored with Docker Model Runner:
```
docker model run hf.co/athirdpath/Orca-2-13b-Alpaca-Uncensored
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model is a fine-tuned version of microsoft/Orca-2-13b on a subset of the Vezora/Mini_Orca_Uncencored_Alpaca dataset, adjusted to demonstrate the relationship between instruction and input, with some particularly spicy prompts added to reduce the risk of rejections.

Only the q_proj and k_proj modules were targeted and a low rank (8) was used, in hopes of containing the adjustments to the prompt format and alignment. This is promising on paper, with the training's per-step loss averaging <0.9 for the last third of the run.

Reasoning stayed solid (for a 13b model) and I consider this a success. Performance is slighty worse than OG Orca-2 in Ooba's chat mode, comparable in Alpaca chat-instruct mode to the OG in ChatLM chat-instruct mode.

May still reject some shocking prompts, but can easily be overcome with author's note or character card.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	61.63
AI2 Reasoning Challenge (25-Shot)	61.09
HellaSwag (10-Shot)	79.27
MMLU (5-Shot)	60.13
TruthfulQA (0-shot)	53.59
Winogrande (5-shot)	77.43
GSM8k (5-shot)	38.29

Downloads last month: 865

Model tree for athirdpath/Orca-2-13b-Alpaca-Uncensored

Merges

2 models

Quantizations

2 models

Evaluation results

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

61.090
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

79.270
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

60.130
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

53.590
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

77.430
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

38.290