Instructions to use EricChan1122/florence2-parasitic-egg-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EricChan1122/florence2-parasitic-egg-detection with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large")
model = PeftModel.from_pretrained(base_model, "EricChan1122/florence2-parasitic-egg-detection")

Transformers

How to use EricChan1122/florence2-parasitic-egg-detection with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EricChan1122/florence2-parasitic-egg-detection")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("EricChan1122/florence2-parasitic-egg-detection", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use EricChan1122/florence2-parasitic-egg-detection with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EricChan1122/florence2-parasitic-egg-detection"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EricChan1122/florence2-parasitic-egg-detection",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EricChan1122/florence2-parasitic-egg-detection

SGLang

How to use EricChan1122/florence2-parasitic-egg-detection 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 "EricChan1122/florence2-parasitic-egg-detection" \
    --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": "EricChan1122/florence2-parasitic-egg-detection",
		"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 "EricChan1122/florence2-parasitic-egg-detection" \
        --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": "EricChan1122/florence2-parasitic-egg-detection",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EricChan1122/florence2-parasitic-egg-detection with Docker Model Runner:
```
docker model run hf.co/EricChan1122/florence2-parasitic-egg-detection
```

EricChan1122 commited on Feb 9

Commit

7c46d41

verified ·

1 Parent(s): e0d7e14

End of training

Browse files

Files changed (4) hide show

README.md +68 -0
adapter_config.json +47 -0
adapter_model.safetensors +3 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,68 @@

+---
+library_name: peft
+license: mit
+base_model: microsoft/Florence-2-large
+tags:
+- base_model:adapter:microsoft/Florence-2-large
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: florence2-parasitic-egg-detection
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# florence2-parasitic-egg-detection
+This model is a fine-tuned version of [microsoft/Florence-2-large](https://huggingface.co/microsoft/Florence-2-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9388
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+### Training results
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8297        | 0.2424 | 200  | 0.9942          |
+| 0.8781        | 0.4848 | 400  | 0.9599          |
+| 0.7837        | 0.7273 | 600  | 0.9458          |
+| 0.7298        | 0.9697 | 800  | 0.9388          |
+### Framework versions
+- PEFT 0.18.1
+- Transformers 4.45.2
+- Pytorch 2.6.0+cu124
+- Datasets 4.5.0
+- Tokenizers 0.20.3

adapter_config.json ADDED Viewed

	@@ -0,0 +1,47 @@

+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Florence-2-large",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "fc2",
+    "Conv2d",
+    "linear",
+    "k_proj",
+    "o_proj",
+    "lm_head",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7a19ba01299904c2aa4b5978132653189c10450b8dcf2c8ac2a3e3e7582e3e1e
+size 16582384

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0a0699d32de7e3ea4b84260e6c661846e09e4f1f3fd9722191e18a0a46ab8a
+size 5240