Instructions to use jawk5/GJMiii with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jawk5/GJMiii with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jawk5/GJMiii")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jawk5/GJMiii", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use jawk5/GJMiii with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jawk5/GJMiii" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jawk5/GJMiii", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jawk5/GJMiii
- SGLang
How to use jawk5/GJMiii 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 "jawk5/GJMiii" \ --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": "jawk5/GJMiii", "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 "jawk5/GJMiii" \ --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": "jawk5/GJMiii", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jawk5/GJMiii with Docker Model Runner:
docker model run hf.co/jawk5/GJMiii
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,8 +10,6 @@ datasets:
|
|
| 10 |
- fka/awesome-chatgpt-prompts
|
| 11 |
- HumanLLMs/Human-Like-DPO-Dataset
|
| 12 |
- NovaSky-AI/Sky-T1_data_17k
|
| 13 |
-
- agibot-world/AgiBotWorld-Alpha
|
| 14 |
-
- DAMO-NLP-SG/multimodal_textbook
|
| 15 |
metrics:
|
| 16 |
- accuracy
|
| 17 |
- perplexity
|
|
@@ -19,20 +17,21 @@ metrics:
|
|
| 19 |
library_name: transformers
|
| 20 |
license: mit
|
| 21 |
widget:
|
| 22 |
-
- text: "Introduce yourself."
|
| 23 |
- text: "What is quantum entanglement?"
|
|
|
|
| 24 |
---
|
| 25 |
-
# GJMiii: AI Assistant Powered by OLMo
|
| 26 |
|
| 27 |
-
|
|
|
|
|
|
|
| 28 |
|
| 29 |
## Features
|
| 30 |
|
| 31 |
- **Text Generation**: Create human-like responses to various prompts.
|
| 32 |
-
- **Scientific Knowledge**:
|
| 33 |
-
- **Task Management**: Manage and recall
|
| 34 |
-
- **Command Execution**:
|
| 35 |
-
- **Math Solver**: Evaluate complex mathematical expressions.
|
| 36 |
|
| 37 |
---
|
| 38 |
|
|
@@ -42,3 +41,58 @@ GJMiii is a versatile AI assistant built on the OLMo model from AllenAI. It is d
|
|
| 42 |
```bash
|
| 43 |
git clone https://huggingface.co/jawk5/GJMiii
|
| 44 |
cd GJMiii
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
- fka/awesome-chatgpt-prompts
|
| 11 |
- HumanLLMs/Human-Like-DPO-Dataset
|
| 12 |
- NovaSky-AI/Sky-T1_data_17k
|
|
|
|
|
|
|
| 13 |
metrics:
|
| 14 |
- accuracy
|
| 15 |
- perplexity
|
|
|
|
| 17 |
library_name: transformers
|
| 18 |
license: mit
|
| 19 |
widget:
|
|
|
|
| 20 |
- text: "What is quantum entanglement?"
|
| 21 |
+
- text: "Write a summary of the theory of relativity."
|
| 22 |
---
|
|
|
|
| 23 |
|
| 24 |
+
# Lilith: AI Assistant Powered by OLMo
|
| 25 |
+
|
| 26 |
+
Lilith is a versatile and powerful AI assistant designed to perform a wide range of tasks, including text generation, answering scientific queries, solving mathematical problems, and more. Built using the OLMo model from AllenAI, Lilith is ideal for researchers, developers, and AI enthusiasts.
|
| 27 |
|
| 28 |
## Features
|
| 29 |
|
| 30 |
- **Text Generation**: Create human-like responses to various prompts.
|
| 31 |
+
- **Scientific Knowledge**: Provide detailed explanations for scientific and technical topics.
|
| 32 |
+
- **Task Management**: Manage tasks with add, list, and recall commands.
|
| 33 |
+
- **Command Execution**: Run system-level commands directly from the interface.
|
| 34 |
+
- **Math Solver**: Evaluate and compute complex mathematical expressions.
|
| 35 |
|
| 36 |
---
|
| 37 |
|
|
|
|
| 41 |
```bash
|
| 42 |
git clone https://huggingface.co/jawk5/GJMiii
|
| 43 |
cd GJMiii
|
| 44 |
+
```
|
| 45 |
+
|
| 46 |
+
2. **Set Up the Virtual Environment**:
|
| 47 |
+
```bash
|
| 48 |
+
python3 -m venv venv
|
| 49 |
+
source venv/bin/activate # On Windows: venv\\Scripts\\activate
|
| 50 |
+
```
|
| 51 |
+
|
| 52 |
+
3. **Install Dependencies**:
|
| 53 |
+
```bash
|
| 54 |
+
pip install transformers
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
4. **Run Lilith**:
|
| 58 |
+
```bash
|
| 59 |
+
python lilith.py
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
---
|
| 63 |
+
|
| 64 |
+
## Example Commands
|
| 65 |
+
|
| 66 |
+
### Task Management
|
| 67 |
+
```plaintext
|
| 68 |
+
Lilith> add_task Complete project documentation
|
| 69 |
+
Task 'Complete project documentation' added.
|
| 70 |
+
|
| 71 |
+
Lilith> list_tasks
|
| 72 |
+
- Complete project documentation
|
| 73 |
+
```
|
| 74 |
+
|
| 75 |
+
### Scientific Inquiry
|
| 76 |
+
```plaintext
|
| 77 |
+
Lilith> science Explain quantum mechanics.
|
| 78 |
+
Lilith: Quantum mechanics is a fundamental theory in physics that describes...
|
| 79 |
+
```
|
| 80 |
+
|
| 81 |
+
### Chat Interaction
|
| 82 |
+
```plaintext
|
| 83 |
+
Lilith> chat Hi, who are you?
|
| 84 |
+
Lilith: I am Lilith, your AI assistant. How can I help you today?
|
| 85 |
+
```
|
| 86 |
+
|
| 87 |
+
---
|
| 88 |
+
|
| 89 |
+
## Dependencies
|
| 90 |
+
|
| 91 |
+
- [Transformers](https://huggingface.co/docs/transformers/)
|
| 92 |
+
- Python 3.7 or higher
|
| 93 |
+
|
| 94 |
+
---
|
| 95 |
+
|
| 96 |
+
## License
|
| 97 |
+
|
| 98 |
+
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
|