Instructions to use thomasjvu/lisper-gemma4-e2b-audio-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thomasjvu/lisper-gemma4-e2b-audio-full with Transformers:

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

pipe = pipeline("image-text-to-text", model="thomasjvu/lisper-gemma4-e2b-audio-full")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("thomasjvu/lisper-gemma4-e2b-audio-full")
model = AutoModelForImageTextToText.from_pretrained("thomasjvu/lisper-gemma4-e2b-audio-full")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use thomasjvu/lisper-gemma4-e2b-audio-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thomasjvu/lisper-gemma4-e2b-audio-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thomasjvu/lisper-gemma4-e2b-audio-full",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/thomasjvu/lisper-gemma4-e2b-audio-full

SGLang

How to use thomasjvu/lisper-gemma4-e2b-audio-full 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 "thomasjvu/lisper-gemma4-e2b-audio-full" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thomasjvu/lisper-gemma4-e2b-audio-full",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "thomasjvu/lisper-gemma4-e2b-audio-full" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thomasjvu/lisper-gemma4-e2b-audio-full",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use thomasjvu/lisper-gemma4-e2b-audio-full with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for thomasjvu/lisper-gemma4-e2b-audio-full to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for thomasjvu/lisper-gemma4-e2b-audio-full to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for thomasjvu/lisper-gemma4-e2b-audio-full to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="thomasjvu/lisper-gemma4-e2b-audio-full",
    max_seq_length=2048,
)

Docker Model Runner
How to use thomasjvu/lisper-gemma4-e2b-audio-full with Docker Model Runner:
```
docker model run hf.co/thomasjvu/lisper-gemma4-e2b-audio-full
```

thomasjvu commited on 14 days ago

Commit

9cb59fc

verified ·

1 Parent(s): 879ed7a

Publish v18 hybrid eval summary

Browse files

Files changed (1) hide show

eval_summary.json +37 -0

eval_summary.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "evaluation_name": "v18_hybrid_acoustic_gemma_heldout",
+  "status": "pass",
+  "count": 2000,
+  "success_count": 2000,
+  "effective_success_count": 2000,
+  "error_count": 0,
+  "hard_error_count": 0,
+  "hard_error_ids": [],
+  "truncated_count": 225,
+  "in_memory_retry_count": 75,
+  "acoustic_hint_count": 2000,
+  "acoustic_hint_match": 0.976,
+  "response_repaired_count": 2000,
+  "generation_fallback_count": 75,
+  "class_match": 0.976,
+  "class_match_successful_only": 0.976,
+  "clear_match": 0.989,
+  "clear_match_successful_only": 0.989,
+  "has_reason": 1.0,
+  "has_reason_successful_only": 1.0,
+  "has_corrective_cue": 1.0,
+  "has_corrective_cue_successful_only": 1.0,
+  "has_encouragement": 1.0,
+  "has_encouragement_successful_only": 1.0,
+  "format_exact": 1.0,
+  "format_exact_successful_only": 1.0,
+  "format_four_lines": 1.0,
+  "format_four_lines_successful_only": 1.0,
+  "detected_class_in_schema": 1.0,
+  "detected_class_in_schema_successful_only": 1.0,
+  "notes": [
+    "This is the v18 hybrid acoustic+Gemma held-out evaluation.",
+    "The lisp-class hint comes from acoustic features; Gemma generates the structured coaching response.",
+    "Do not interpret these metrics as a pure direct-Gemma raw-audio classification result."
+  ]
+}