Instructions to use ssalvo41/git-base-ohs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ssalvo41/git-base-ohs with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="ssalvo41/git-base-ohs")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("ssalvo41/git-base-ohs") model = AutoModelForImageTextToText.from_pretrained("ssalvo41/git-base-ohs") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ssalvo41/git-base-ohs with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ssalvo41/git-base-ohs" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ssalvo41/git-base-ohs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ssalvo41/git-base-ohs
- SGLang
How to use ssalvo41/git-base-ohs 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 "ssalvo41/git-base-ohs" \ --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": "ssalvo41/git-base-ohs", "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 "ssalvo41/git-base-ohs" \ --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": "ssalvo41/git-base-ohs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ssalvo41/git-base-ohs with Docker Model Runner:
docker model run hf.co/ssalvo41/git-base-ohs
End of training
Browse files- README.md +21 -13
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -5,19 +5,19 @@ base_model: microsoft/git-base
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
-
- name: git-base-isg
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
# git-base-isg
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Wer Score:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -44,20 +44,28 @@ The following hyperparameters were used during training:
|
|
| 44 |
- total_train_batch_size: 32
|
| 45 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
-
- num_epochs:
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
| 52 |
|:-------------:|:-------:|:----:|:---------------:|:---------:|
|
| 53 |
-
| 13.
|
| 54 |
-
|
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
+
- name: git-base-isg-288
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
# git-base-isg-288
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0937
|
| 20 |
+
- Wer Score: 2.7076
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 44 |
- total_train_batch_size: 32
|
| 45 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 100
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
| 52 |
|:-------------:|:-------:|:----:|:---------------:|:---------:|
|
| 53 |
+
| 13.4828 | 5.5882 | 50 | 4.2850 | 16.7473 |
|
| 54 |
+
| 3.9992 | 11.1176 | 100 | 0.3655 | 0.7942 |
|
| 55 |
+
| 0.2368 | 16.7059 | 150 | 0.0692 | 0.6679 |
|
| 56 |
+
| 0.0533 | 22.2353 | 200 | 0.0733 | 0.7004 |
|
| 57 |
+
| 0.0339 | 27.8235 | 250 | 0.0765 | 0.8520 |
|
| 58 |
+
| 0.0249 | 33.3529 | 300 | 0.0795 | 1.8592 |
|
| 59 |
+
| 0.0165 | 38.9412 | 350 | 0.0821 | 2.3827 |
|
| 60 |
+
| 0.0074 | 44.4706 | 400 | 0.0861 | 2.0542 |
|
| 61 |
+
| 0.0034 | 50.0 | 450 | 0.0885 | 3.0361 |
|
| 62 |
+
| 0.0023 | 55.5882 | 500 | 0.0909 | 2.4946 |
|
| 63 |
+
| 0.0018 | 61.1176 | 550 | 0.0920 | 2.6426 |
|
| 64 |
+
| 0.0016 | 66.7059 | 600 | 0.0930 | 2.6354 |
|
| 65 |
+
| 0.0015 | 72.2353 | 650 | 0.0930 | 2.2527 |
|
| 66 |
+
| 0.0013 | 77.8235 | 700 | 0.0935 | 2.6859 |
|
| 67 |
+
| 0.0013 | 83.3529 | 750 | 0.0937 | 2.7726 |
|
| 68 |
+
| 0.0012 | 88.9412 | 800 | 0.0937 | 2.7076 |
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 706516040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fc2dd0c3cfafbae6b063031ae96ad1c2cbbae6ef7aac0cfad4b139fc2742b64
|
| 3 |
size 706516040
|