Instructions to use cgato/TheSpice-7b-FT-ExperimentalOrca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cgato/TheSpice-7b-FT-ExperimentalOrca with Transformers:

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

pipe = pipeline("text-generation", model="cgato/TheSpice-7b-FT-ExperimentalOrca")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cgato/TheSpice-7b-FT-ExperimentalOrca")
model = AutoModelForCausalLM.from_pretrained("cgato/TheSpice-7b-FT-ExperimentalOrca")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cgato/TheSpice-7b-FT-ExperimentalOrca with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/cgato/TheSpice-7b-FT-ExperimentalOrca

SGLang

How to use cgato/TheSpice-7b-FT-ExperimentalOrca 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 "cgato/TheSpice-7b-FT-ExperimentalOrca" \
    --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": "cgato/TheSpice-7b-FT-ExperimentalOrca",
		"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 "cgato/TheSpice-7b-FT-ExperimentalOrca" \
        --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": "cgato/TheSpice-7b-FT-ExperimentalOrca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cgato/TheSpice-7b-FT-ExperimentalOrca with Docker Model Runner:
```
docker model run hf.co/cgato/TheSpice-7b-FT-ExperimentalOrca
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A smort model made using the cleaned Orca data.

{System Prompt}

Username: {Input}
BotName: {Response}
Username: {Input}
BotName: {Response}

Seriously, I have to add more due to HF Leaderboard requirements. so basically, this model uses a cleaned version of Orca along with my typical RP data package. It was intended as a test to see if the models RP evals would be affected by an overwhelming amount of instruct tokens.

Downloads last month: 66

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for cgato/TheSpice-7b-FT-ExperimentalOrca

Quantizations

2 models