Instructions to use Azazelle/Tippy-Toppy-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Azazelle/Tippy-Toppy-7b with Transformers:

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

pipe = pipeline("text-generation", model="Azazelle/Tippy-Toppy-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Azazelle/Tippy-Toppy-7b")
model = AutoModelForCausalLM.from_pretrained("Azazelle/Tippy-Toppy-7b", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Azazelle/Tippy-Toppy-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Azazelle/Tippy-Toppy-7b

SGLang

How to use Azazelle/Tippy-Toppy-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 "Azazelle/Tippy-Toppy-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": "Azazelle/Tippy-Toppy-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 "Azazelle/Tippy-Toppy-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": "Azazelle/Tippy-Toppy-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Model Card for Tippy-Toppy-7b

DARE merge intended to be build on Toppy-M-7b.

.yaml file for mergekit

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: Undi95/Toppy-M-7B #175
    parameters:
      weight: 0.54
      density: 0.81
  - model: PistachioAlt/Noromaid-Bagel-7B-Slerp #75
    parameters:
      weight: 0.23
      density: 0.61
  - model: OpenPipe/mistral-ft-optimized-1227 #100
    parameters:
      weight: 0.31
      density: 0.68
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16

Downloads last month: 52

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Azazelle/Tippy-Toppy-7b

Merges

1 model

Quantizations

1 model