Instructions to use Azazelle/Dumb-Maidlet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Azazelle/Dumb-Maidlet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Azazelle/Dumb-Maidlet")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Azazelle/Dumb-Maidlet") model = AutoModelForMultimodalLM.from_pretrained("Azazelle/Dumb-Maidlet") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Azazelle/Dumb-Maidlet with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Azazelle/Dumb-Maidlet" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Azazelle/Dumb-Maidlet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Azazelle/Dumb-Maidlet
- SGLang
How to use Azazelle/Dumb-Maidlet 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/Dumb-Maidlet" \ --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/Dumb-Maidlet", "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/Dumb-Maidlet" \ --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/Dumb-Maidlet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Azazelle/Dumb-Maidlet with Docker Model Runner:
docker model run hf.co/Azazelle/Dumb-Maidlet
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,30 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: cc-by-4.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
tags:
|
| 4 |
+
- mistral
|
| 5 |
+
- merge
|
| 6 |
license: cc-by-4.0
|
| 7 |
---
|
| 8 |
+
# Model Card for Dumb-Maidlet
|
| 9 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 10 |
+
Slerp merge of Noromaid-7b-v0.2, NSFW_DPO_Noromaid-7b, go-bruins-v2, and smol-7b.
|
| 11 |
+
|
| 12 |
+
.yaml file for mergekit
|
| 13 |
+
```.yaml:
|
| 14 |
+
slices:
|
| 15 |
+
- sources:
|
| 16 |
+
- model: Azazelle/Half-NSFW_Noromaid-7b
|
| 17 |
+
layer_range: [0, 32]
|
| 18 |
+
- model: Azazelle/smol_bruin-7b
|
| 19 |
+
layer_range: [0, 32]
|
| 20 |
+
merge_method: slerp
|
| 21 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 22 |
+
parameters:
|
| 23 |
+
t:
|
| 24 |
+
- filter: self_attn
|
| 25 |
+
value: [0.22, 0.61, 0.46, 0.77, 1]
|
| 26 |
+
- filter: mlp
|
| 27 |
+
value: [0.78, 0.39, 0.54, 0.23, 0]
|
| 28 |
+
- value: 0.5 # fallback for rest of tensors
|
| 29 |
+
dtype: float16
|
| 30 |
+
```
|