Instructions to use momergul/git_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use momergul/git_test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="momergul/git_test", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("momergul/git_test", trust_remote_code=True) model = AutoModelForImageTextToText.from_pretrained("momergul/git_test", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use momergul/git_test with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "momergul/git_test" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "momergul/git_test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/momergul/git_test
- SGLang
How to use momergul/git_test 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 "momergul/git_test" \ --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": "momergul/git_test", "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 "momergul/git_test" \ --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": "momergul/git_test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use momergul/git_test with Docker Model Runner:
docker model run hf.co/momergul/git_test
Upload processor
Browse files- special_tokens_map.json +8 -1
- tokenizer_config.json +2 -1
special_tokens_map.json
CHANGED
|
@@ -15,8 +15,15 @@
|
|
| 15 |
"single_word": false
|
| 16 |
}
|
| 17 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
"pad_token": {
|
| 19 |
-
"content": "<
|
| 20 |
"lstrip": false,
|
| 21 |
"normalized": false,
|
| 22 |
"rstrip": false,
|
|
|
|
| 15 |
"single_word": false
|
| 16 |
}
|
| 17 |
],
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "</s>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
"pad_token": {
|
| 26 |
+
"content": "</s>",
|
| 27 |
"lstrip": false,
|
| 28 |
"normalized": false,
|
| 29 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -54,9 +54,10 @@
|
|
| 54 |
"<PERSON>"
|
| 55 |
],
|
| 56 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 57 |
"extra_special_tokens": {},
|
| 58 |
"model_max_length": 1000000000000000019884624838656,
|
| 59 |
-
"pad_token": "<
|
| 60 |
"processor_class": "GITProcessor",
|
| 61 |
"tokenizer_class": "PreTrainedTokenizer"
|
| 62 |
}
|
|
|
|
| 54 |
"<PERSON>"
|
| 55 |
],
|
| 56 |
"clean_up_tokenization_spaces": false,
|
| 57 |
+
"eos_token": "</s>",
|
| 58 |
"extra_special_tokens": {},
|
| 59 |
"model_max_length": 1000000000000000019884624838656,
|
| 60 |
+
"pad_token": "</s>",
|
| 61 |
"processor_class": "GITProcessor",
|
| 62 |
"tokenizer_class": "PreTrainedTokenizer"
|
| 63 |
}
|