Instructions to use i3-lab/i3-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use i3-lab/i3-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="i3-lab/i3-tiny", trust_remote_code=True)# Load model directly from transformers import i3 model = i3.from_pretrained("i3-lab/i3-tiny", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use i3-lab/i3-tiny with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "i3-lab/i3-tiny" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "i3-lab/i3-tiny", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/i3-lab/i3-tiny
- SGLang
How to use i3-lab/i3-tiny 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 "i3-lab/i3-tiny" \ --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": "i3-lab/i3-tiny", "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 "i3-lab/i3-tiny" \ --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": "i3-lab/i3-tiny", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use i3-lab/i3-tiny with Docker Model Runner:
docker model run hf.co/i3-lab/i3-tiny
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
language:
|
| 4 |
-
- en
|
| 5 |
-
pipeline_tag: text-generation
|
| 6 |
-
library_name: transformers
|
| 7 |
-
tags:
|
| 8 |
-
- i3-architecture
|
| 9 |
-
- custom_code
|
| 10 |
-
---
|
| 11 |
|
| 12 |
# i3-tiny
|
| 13 |
|
|
@@ -77,16 +77,7 @@ These outputs capture the **chaotic creativity** of a character-level model: a m
|
|
| 77 |
## Usage Example
|
| 78 |
|
| 79 |
```python
|
| 80 |
-
|
| 81 |
-
import torch
|
| 82 |
-
|
| 83 |
-
config = i3Config.from_pretrained("i3-hf-model")
|
| 84 |
-
model = i3.from_pretrained("i3-hf-model", config=config)
|
| 85 |
-
|
| 86 |
-
prompt = "Hello"
|
| 87 |
-
input_ids = torch.tensor([[c for c in range(len(prompt))]]) # replace with your dataset encoding
|
| 88 |
-
generated_ids = model.model.generate(input_ids, max_new_tokens=100, temperature=0.8, top_k=20)
|
| 89 |
-
print(generated_ids) # decode using your dataset method
|
| 90 |
````
|
| 91 |
|
| 92 |
---
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
library_name: transformers
|
| 7 |
+
tags:
|
| 8 |
+
- i3-architecture
|
| 9 |
+
- custom_code
|
| 10 |
+
---
|
| 11 |
|
| 12 |
# i3-tiny
|
| 13 |
|
|
|
|
| 77 |
## Usage Example
|
| 78 |
|
| 79 |
```python
|
| 80 |
+
# not available
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
````
|
| 82 |
|
| 83 |
---
|