Text Generation
Transformers
Safetensors
phi-msft
Merge
mergekit
lazymergekit
rhysjones/phi-2-orange
cognitivecomputations/dolphin-2_6-phi-2
mrm8488/phi-2-coder
custom_code
Instructions to use Isotonic/phizzle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Isotonic/phizzle with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Isotonic/phizzle", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Isotonic/phizzle", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Isotonic/phizzle with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Isotonic/phizzle" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Isotonic/phizzle", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Isotonic/phizzle
- SGLang
How to use Isotonic/phizzle 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 "Isotonic/phizzle" \ --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": "Isotonic/phizzle", "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 "Isotonic/phizzle" \ --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": "Isotonic/phizzle", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Isotonic/phizzle with Docker Model Runner:
docker model run hf.co/Isotonic/phizzle
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,9 @@ phi-2-ties is a merge of the following models using [LazyMergekit](https://colab
|
|
| 21 |
```yaml
|
| 22 |
models:
|
| 23 |
- model: rhysjones/phi-2-orange
|
|
|
|
|
|
|
|
|
|
| 24 |
- model: cognitivecomputations/dolphin-2_6-phi-2
|
| 25 |
parameters:
|
| 26 |
density: 0.5
|
|
|
|
| 21 |
```yaml
|
| 22 |
models:
|
| 23 |
- model: rhysjones/phi-2-orange
|
| 24 |
+
parameters:
|
| 25 |
+
density: 0.5
|
| 26 |
+
weight: 0.4
|
| 27 |
- model: cognitivecomputations/dolphin-2_6-phi-2
|
| 28 |
parameters:
|
| 29 |
density: 0.5
|