Instructions to use aiplanet/effi-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aiplanet/effi-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="aiplanet/effi-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("aiplanet/effi-7b") model = AutoModelForCausalLM.from_pretrained("aiplanet/effi-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use aiplanet/effi-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "aiplanet/effi-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "aiplanet/effi-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/aiplanet/effi-7b
- SGLang
How to use aiplanet/effi-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 "aiplanet/effi-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": "aiplanet/effi-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 "aiplanet/effi-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": "aiplanet/effi-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use aiplanet/effi-7b with Docker Model Runner:
docker model run hf.co/aiplanet/effi-7b
Librarian Bot: Add base_model information to model
Browse filesThis pull request aims to enrich the metadata of your model by adding [`huggyllama/llama-7b`](https://huggingface.co/huggyllama/llama-7b) as a `base_model` field, situated in the `YAML` block of your model's `README.md`.
How did we find this information? We extracted this infromation from the `adapter_config.json` file of your model.
**Why add this?** Enhancing your model's metadata in this way:
- **Boosts Discoverability** - It becomes straightforward to trace the relationships between various models on the Hugging Face Hub.
- **Highlights Impact** - It showcases the contributions and influences different models have within the community.
For a hands-on example of how such metadata can play a pivotal role in mapping model connections, take a look at [librarian-bots/base_model_explorer](https://huggingface.co/spaces/librarian-bots/base_model_explorer).
This PR comes courtesy of [Librarian Bot](https://huggingface.co/librarian-bot). If you have any feedback, queries, or need assistance, please don't hesitate to reach out to [@davanstrien](https://huggingface.co/davanstrien).
If you want to automatically add `base_model` metadata to more of your modes you can use the [Librarian Bot](https://huggingface.co/librarian-bot) [Metadata Request Service](https://huggingface.co/spaces/librarian-bots/metadata_request_service)!
|
@@ -1,9 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
library_name: peft
|
| 3 |
license: apache-2.0
|
|
|
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
| 6 |
pipeline_tag: text-generation
|
|
|
|
| 7 |
---
|
| 8 |
effi 7b is a 7 billion parameter model built by AI Planet. Inspired by llama, we've built fine-tuned version of llama7b with qlora. The training procedure and framework versions are provided below along with model weighths.
|
| 9 |
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
+
base_model: huggyllama/llama-7b
|
| 8 |
---
|
| 9 |
effi 7b is a 7 billion parameter model built by AI Planet. Inspired by llama, we've built fine-tuned version of llama7b with qlora. The training procedure and framework versions are provided below along with model weighths.
|
| 10 |
|