Instructions to use BlacqTangent/medgemma-4b-it-sft-lora-diff with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BlacqTangent/medgemma-4b-it-sft-lora-diff with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/medgemma-4b-it-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "BlacqTangent/medgemma-4b-it-sft-lora-diff")

Transformers

How to use BlacqTangent/medgemma-4b-it-sft-lora-diff with Transformers:

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

pipe = pipeline("text-generation", model="BlacqTangent/medgemma-4b-it-sft-lora-diff")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BlacqTangent/medgemma-4b-it-sft-lora-diff", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BlacqTangent/medgemma-4b-it-sft-lora-diff with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BlacqTangent/medgemma-4b-it-sft-lora-diff"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BlacqTangent/medgemma-4b-it-sft-lora-diff",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BlacqTangent/medgemma-4b-it-sft-lora-diff

SGLang

How to use BlacqTangent/medgemma-4b-it-sft-lora-diff 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 "BlacqTangent/medgemma-4b-it-sft-lora-diff" \
    --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": "BlacqTangent/medgemma-4b-it-sft-lora-diff",
		"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 "BlacqTangent/medgemma-4b-it-sft-lora-diff" \
        --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": "BlacqTangent/medgemma-4b-it-sft-lora-diff",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use BlacqTangent/medgemma-4b-it-sft-lora-diff with Docker Model Runner:
```
docker model run hf.co/BlacqTangent/medgemma-4b-it-sft-lora-diff
```

BlacqTangent commited on Nov 11, 2025

Commit

137c2f8

verified ·

1 Parent(s): 5b4b4af

Model save

Browse files

Files changed (1) hide show

README.md +21 -10

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [unsloth/medgemma-4b-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/medgemma-4b-it-unsloth-bnb-4bit) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.9605
 ## Model description
@@ -45,24 +45,35 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4163        | 0.16  | 2    | 5.8335          |
-| 0.3497        | 0.32  | 4    | 5.1265          |
-| 0.31          | 0.48  | 6    | 4.6419          |
-| 0.2826        | 0.64  | 8    | 4.3103          |
-| 0.2648        | 0.8   | 10   | 4.0871          |
-| 0.2507        | 0.96  | 12   | 3.9605          |
 ### Framework versions

 This model is a fine-tuned version of [unsloth/medgemma-4b-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/medgemma-4b-it-unsloth-bnb-4bit) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.1324
 ## Model description
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 0.2086        | 0.32  | 2    | 6.1580          |
+| 0.1811        | 0.64  | 4    | 5.1228          |
+| 0.1542        | 0.96  | 6    | 4.5230          |
+| 0.3444        | 1.16  | 8    | 4.0204          |
+| 0.1211        | 1.48  | 10   | 3.5760          |
+| 0.1076        | 1.8   | 12   | 3.1542          |
+| 0.2279        | 2.0   | 14   | 2.7274          |
+| 0.0812        | 2.32  | 16   | 2.3581          |
+| 0.0707        | 2.64  | 18   | 2.0595          |
+| 0.0613        | 2.96  | 20   | 1.8119          |
+| 0.1386        | 3.16  | 22   | 1.6140          |
+| 0.0481        | 3.48  | 24   | 1.4556          |
+| 0.0439        | 3.8   | 26   | 1.3301          |
+| 0.1025        | 4.0   | 28   | 1.2408          |
+| 0.0376        | 4.32  | 30   | 1.1838          |
+| 0.036         | 4.64  | 32   | 1.1499          |
+| 0.0354        | 4.96  | 34   | 1.1324          |
 ### Framework versions