Text Generation
Transformers
Safetensors
phi-msft
Merge
mergekit
lazymergekit
rhysjones/phi-2-orange
cognitivecomputations/dolphin-2_6-phi-2
Microsoft/Phi-2
custom_code
Instructions to use Venkman42/Phiter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Venkman42/Phiter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Venkman42/Phiter", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Venkman42/Phiter", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Venkman42/Phiter with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Venkman42/Phiter" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Venkman42/Phiter", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Venkman42/Phiter
- SGLang
How to use Venkman42/Phiter 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 "Venkman42/Phiter" \ --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": "Venkman42/Phiter", "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 "Venkman42/Phiter" \ --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": "Venkman42/Phiter", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Venkman42/Phiter with Docker Model Runner:
docker model run hf.co/Venkman42/Phiter
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,7 @@ tags:
|
|
| 9 |
base_model:
|
| 10 |
- rhysjones/phi-2-orange
|
| 11 |
- cognitivecomputations/dolphin-2_6-phi-2
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# Phiter
|
|
@@ -18,7 +19,19 @@ Phiter is a merge of the following models using [LazyMergekit](https://colab.res
|
|
| 18 |
* [rhysjones/phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)
|
| 19 |
* [cognitivecomputations/dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)
|
| 20 |
|
| 21 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
<!-- prompt-template start -->
|
| 24 |
## Prompt template: ChatML
|
|
|
|
| 9 |
base_model:
|
| 10 |
- rhysjones/phi-2-orange
|
| 11 |
- cognitivecomputations/dolphin-2_6-phi-2
|
| 12 |
+
license: mit
|
| 13 |
---
|
| 14 |
|
| 15 |
# Phiter
|
|
|
|
| 19 |
* [rhysjones/phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)
|
| 20 |
* [cognitivecomputations/dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)
|
| 21 |
|
| 22 |
+
Thanks to the great [Maxime Labonne](https://huggingface.co/mlabonne) we have evaluation results on [YALL](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
|
| 23 |
+
|
| 24 |
+
The model tops all other phi-2 finetunes on the leaderboard, even most MoE implementations like Phixtral(Date: 27th February 2024)
|
| 25 |
+
|
| 26 |
+
License: MIT
|
| 27 |
+
|
| 28 |
+
This model wouldn't have been possible without the support of:
|
| 29 |
+
|
| 30 |
+
[Maxime Labonne](https://huggingface.co/mlabonne) - he helped me troubleshoot the merge process
|
| 31 |
+
|
| 32 |
+
[brittlewis12](https://huggingface.co/brittlewis12) - helped me troubleshooting the creation of GGUF files
|
| 33 |
+
|
| 34 |
+
|
| 35 |
|
| 36 |
<!-- prompt-template start -->
|
| 37 |
## Prompt template: ChatML
|