Instructions to use gretelai/text2table with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gretelai/text2table with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="gretelai/text2table")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("gretelai/text2table") model = AutoModelForCausalLM.from_pretrained("gretelai/text2table") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use gretelai/text2table with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gretelai/text2table" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gretelai/text2table", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/gretelai/text2table
- SGLang
How to use gretelai/text2table 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 "gretelai/text2table" \ --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": "gretelai/text2table", "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 "gretelai/text2table" \ --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": "gretelai/text2table", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use gretelai/text2table with Docker Model Runner:
docker model run hf.co/gretelai/text2table
Commit ·
b9388e3
1
Parent(s): 8580e6d
Update config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"rotary_emb_base": 10000,
|
| 19 |
"rotary_pct": 1.0,
|
| 20 |
"tie_word_embeddings": false,
|
| 21 |
-
"torch_dtype": "
|
| 22 |
"transformers_version": "4.29.0.dev0",
|
| 23 |
"use_cache": true,
|
| 24 |
"use_parallel_residual": false,
|
|
|
|
| 18 |
"rotary_emb_base": 10000,
|
| 19 |
"rotary_pct": 1.0,
|
| 20 |
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.29.0.dev0",
|
| 23 |
"use_cache": true,
|
| 24 |
"use_parallel_residual": false,
|