Instructions to use YingxuHe/git-base-test4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YingxuHe/git-base-test4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="YingxuHe/git-base-test4")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("YingxuHe/git-base-test4") model = AutoModelForImageTextToText.from_pretrained("YingxuHe/git-base-test4") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use YingxuHe/git-base-test4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "YingxuHe/git-base-test4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "YingxuHe/git-base-test4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/YingxuHe/git-base-test4
- SGLang
How to use YingxuHe/git-base-test4 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 "YingxuHe/git-base-test4" \ --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": "YingxuHe/git-base-test4", "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 "YingxuHe/git-base-test4" \ --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": "YingxuHe/git-base-test4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use YingxuHe/git-base-test4 with Docker Model Runner:
docker model run hf.co/YingxuHe/git-base-test4
update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,15 +14,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- eval_loss: 0.
|
| 18 |
-
- eval_wer_score:
|
| 19 |
-
- eval_rouge_score: 0.
|
| 20 |
-
- eval_bert_score: 0.
|
| 21 |
-
- eval_runtime:
|
| 22 |
-
- eval_samples_per_second: 3.
|
| 23 |
-
- eval_steps_per_second: 0.
|
| 24 |
-
- epoch:
|
| 25 |
-
- step:
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- eval_loss: 0.0380
|
| 18 |
+
- eval_wer_score: 18.3045
|
| 19 |
+
- eval_rouge_score: 0.0639
|
| 20 |
+
- eval_bert_score: 0.7613
|
| 21 |
+
- eval_runtime: 33.2248
|
| 22 |
+
- eval_samples_per_second: 3.431
|
| 23 |
+
- eval_steps_per_second: 0.451
|
| 24 |
+
- epoch: 28.71
|
| 25 |
+
- step: 3000
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|