Text Generation
Transformers
PyTorch
Safetensors
English
rwkv-hybrid
i3-architecture
hybrid-model
rwkv-mamba
custom_code
Instructions to use i3-lab/i3-200m-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use i3-lab/i3-200m-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="i3-lab/i3-200m-v2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("i3-lab/i3-200m-v2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use i3-lab/i3-200m-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "i3-lab/i3-200m-v2" # 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/i3-200m-v2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/i3-lab/i3-200m-v2
- SGLang
How to use i3-lab/i3-200m-v2 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/i3-200m-v2" \ --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/i3-200m-v2", "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/i3-200m-v2" \ --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/i3-200m-v2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use i3-lab/i3-200m-v2 with Docker Model Runner:
docker model run hf.co/i3-lab/i3-200m-v2
Upload folder using huggingface_hub
Browse files- config.json +11 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"i3HybridModel"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "rwkv-hybrid",
|
| 6 |
+
"d_model": 768,
|
| 7 |
+
"n_layers": 16,
|
| 8 |
+
"rwkv_layers": 12,
|
| 9 |
+
"attn_layers": 4,
|
| 10 |
+
"vocab_size": 32000
|
| 11 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74b0eb02913bf3232b10c2edf08742b76e344e281b37c994ac17e7c914d9e8f0
|
| 3 |
+
size 679484674
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|