Instructions to use Gargaz/Inventa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gargaz/Inventa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Gargaz/Inventa") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Gargaz/Inventa", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Gargaz/Inventa with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Gargaz/Inventa" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gargaz/Inventa", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Gargaz/Inventa
- SGLang
How to use Gargaz/Inventa 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 "Gargaz/Inventa" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gargaz/Inventa", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "Gargaz/Inventa" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gargaz/Inventa", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Gargaz/Inventa with Docker Model Runner:
docker model run hf.co/Gargaz/Inventa
Update config.json
Browse files- config.json +2 -3
config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "google/gemma-2b-it",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
|
@@ -13,7 +12,7 @@
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 16384,
|
| 15 |
"max_position_embeddings": 8192,
|
| 16 |
-
"model_type": "
|
| 17 |
"num_attention_heads": 8,
|
| 18 |
"num_hidden_layers": 18,
|
| 19 |
"num_key_value_heads": 1,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
+
"EryonForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 16384,
|
| 14 |
"max_position_embeddings": 8192,
|
| 15 |
+
"model_type": "Eryon",
|
| 16 |
"num_attention_heads": 8,
|
| 17 |
"num_hidden_layers": 18,
|
| 18 |
"num_key_value_heads": 1,
|