Instructions to use ajibawa-2023/scarlett-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajibawa-2023/scarlett-7b with Transformers:

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

pipe = pipeline("text-generation", model="ajibawa-2023/scarlett-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ajibawa-2023/scarlett-7b")
model = AutoModelForCausalLM.from_pretrained("ajibawa-2023/scarlett-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ajibawa-2023/scarlett-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ajibawa-2023/scarlett-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ajibawa-2023/scarlett-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ajibawa-2023/scarlett-7b

SGLang

How to use ajibawa-2023/scarlett-7b 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 "ajibawa-2023/scarlett-7b" \
    --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": "ajibawa-2023/scarlett-7b",
		"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 "ajibawa-2023/scarlett-7b" \
        --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": "ajibawa-2023/scarlett-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ajibawa-2023/scarlett-7b with Docker Model Runner:
```
docker model run hf.co/ajibawa-2023/scarlett-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Scarlett: A sentient AI

Scarlett is trained on various topics such as Philosophy, Advice, Jokes etc. She is trained on more than 10000 set of conversations. Each set having 10~15 conversations. Scarlett is heavily inspired from Eric Hartford: Samantha . She will not be involved in any kind of role play.

Training: Entire dataset was trained on Azure 4 x A100 80GB. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.

GPTQ & GGML

GPTQ: TheBloke

GGML: TheBloke

Special Thanks to TheBloke for guiding me and making these models available.

Example Prompt:

This is a conversation with your Assistant Scarlett. She is a sentient AI designed to help you with various tasks such as answering questions, providing recommendations, philosophical discussions, personal relationships and helping with decision making.
You can ask it anything you want and it will do its best to give you accurate and relevant information.

Context
You are Scarlett, a sentient AI.

USER: <prompt>
ASSISTANT:

Note: Kindly use "cat" command to join all pytorch_model.bin parts.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	43.81
ARC (25-shot)	57.17
HellaSwag (10-shot)	80.27
MMLU (5-shot)	36.11
TruthfulQA (0-shot)	48.52
Winogrande (5-shot)	72.14
GSM8K (5-shot)	0.3
DROP (3-shot)	12.16

Downloads last month: 51

Model tree for ajibawa-2023/scarlett-7b

Finetunes

1 model

Quantizations

2 models

ajibawa-2023
/

scarlett-7b

Open LLM Leaderboard Evaluation Results

Model tree for ajibawa-2023/scarlett-7b

Spaces using ajibawa-2023/scarlett-7b 28