Instructions to use ArchiveAI/Thespis-CurtainCall-8x7b-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArchiveAI/Thespis-CurtainCall-8x7b-v0.3 with Transformers:

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

pipe = pipeline("text-generation", model="ArchiveAI/Thespis-CurtainCall-8x7b-v0.3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArchiveAI/Thespis-CurtainCall-8x7b-v0.3")
model = AutoModelForCausalLM.from_pretrained("ArchiveAI/Thespis-CurtainCall-8x7b-v0.3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArchiveAI/Thespis-CurtainCall-8x7b-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArchiveAI/Thespis-CurtainCall-8x7b-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchiveAI/Thespis-CurtainCall-8x7b-v0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArchiveAI/Thespis-CurtainCall-8x7b-v0.3

SGLang

How to use ArchiveAI/Thespis-CurtainCall-8x7b-v0.3 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 "ArchiveAI/Thespis-CurtainCall-8x7b-v0.3" \
    --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": "ArchiveAI/Thespis-CurtainCall-8x7b-v0.3",
		"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 "ArchiveAI/Thespis-CurtainCall-8x7b-v0.3" \
        --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": "ArchiveAI/Thespis-CurtainCall-8x7b-v0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArchiveAI/Thespis-CurtainCall-8x7b-v0.3 with Docker Model Runner:
```
docker model run hf.co/ArchiveAI/Thespis-CurtainCall-8x7b-v0.3
```

A bigger badder Thespis and my first pass at Mixtral.

Datasets Used:

Dolphin
Ultrachat
Capybara
Augmental
ToxicQA
Magiccoder-Evol-Instruct-110k
Yahoo Answers
OpenOrca
Airoboros 3.1
grimulkan/physical-reasoning and theory-of-mind

Prompt Format: Chat ( The default Ooba template and Silly Tavern Template )

{System Prompt}

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

Mixtral seems to require higher temperatures overall compared to Mistral 7b, please mess with your samplers until you find a setting you like.

Duplicated from cgato/Thespis-CurtainCall-8x7b-v0.3

ArchiveAI
/

Thespis-CurtainCall-8x7b-v0.3

Prompt Format: Chat ( The default Ooba template and Silly Tavern Template )

Recommended Sampler Setting Ranges

Presets ( For the lazy!~ )

Recommended Silly Tavern Preset -> Universal-Creative

Recommended Kobold Horde Preset -> MinP