Instructions to use DenisTheDev/Blitz-AI-ULTRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DenisTheDev/Blitz-AI-ULTRA with Transformers:

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

pipe = pipeline("text-generation", model="DenisTheDev/Blitz-AI-ULTRA")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DenisTheDev/Blitz-AI-ULTRA")
model = AutoModelForCausalLM.from_pretrained("DenisTheDev/Blitz-AI-ULTRA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DenisTheDev/Blitz-AI-ULTRA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DenisTheDev/Blitz-AI-ULTRA

SGLang

How to use DenisTheDev/Blitz-AI-ULTRA 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 "DenisTheDev/Blitz-AI-ULTRA" \
    --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": "DenisTheDev/Blitz-AI-ULTRA",
		"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 "DenisTheDev/Blitz-AI-ULTRA" \
        --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": "DenisTheDev/Blitz-AI-ULTRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DenisTheDev/Blitz-AI-ULTRA with Docker Model Runner:
```
docker model run hf.co/DenisTheDev/Blitz-AI-ULTRA
```

DenisTheDev commited on Mar 26, 2024

Commit

3cd980b

verified ·

1 Parent(s): 3443cd7

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -18

README.md CHANGED Viewed

@@ -4,25 +4,8 @@ tags:
 - merge
 - mergekit
 - lazymergekit
-- davidkim205/Rhea-72b-v0.5
 ---
 # Blitz-AI-ULTRA
-Blitz-AI-ULTRA is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
-* [davidkim205/Rhea-72b-v0.5](https://huggingface.co/davidkim205/Rhea-72b-v0.5)
-* [davidkim205/Rhea-72b-v0.5](https://huggingface.co/davidkim205/Rhea-72b-v0.5)
-## 🧩 Configuration
-```yaml
-slices:
-  - sources:
-    - model: davidkim205/Rhea-72b-v0.5
-      layer_range: [0, 72]
-  - sources:
-    - model: davidkim205/Rhea-72b-v0.5
-      layer_range: [8, 80]
-merge_method: passthrough
-dtype: bfloat16
-```

 - merge
 - mergekit
 - lazymergekit
 ---
 # Blitz-AI-ULTRA
+Our current largest model and so far the strongest.