Instructions to use i3-lab/i3-GPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use i3-lab/i3-GPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="i3-lab/i3-GPT")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("i3-lab/i3-GPT") model = AutoModelForCausalLM.from_pretrained("i3-lab/i3-GPT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use i3-lab/i3-GPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "i3-lab/i3-GPT" # 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-GPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/i3-lab/i3-GPT
- SGLang
How to use i3-lab/i3-GPT 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-GPT" \ --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-GPT", "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-GPT" \ --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-GPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use i3-lab/i3-GPT with Docker Model Runner:
docker model run hf.co/i3-lab/i3-GPT
Upload folder using huggingface_hub
Browse files- config.json +3 -3
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -12,10 +12,10 @@
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 1024,
|
| 15 |
-
"n_embd":
|
| 16 |
-
"n_head":
|
| 17 |
"n_inner": null,
|
| 18 |
-
"n_layer":
|
| 19 |
"n_positions": 1024,
|
| 20 |
"pad_token_id": 50256,
|
| 21 |
"reorder_and_upcast_attn": false,
|
|
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 384,
|
| 16 |
+
"n_head": 6,
|
| 17 |
"n_inner": null,
|
| 18 |
+
"n_layer": 6,
|
| 19 |
"n_positions": 1024,
|
| 20 |
"pad_token_id": 50256,
|
| 21 |
"reorder_and_upcast_attn": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91a805e92443d17c079ab7787315f81149260617150c6a6a2faa1537cb22c3df
|
| 3 |
+
size 121365368
|