Upload 9 files
Browse files- README.md +8 -50
- app.py +80 -22
- clients/client_test.py +9 -0
- requirements.txt +0 -5
README.md
CHANGED
|
@@ -1,62 +1,20 @@
|
|
| 1 |
---
|
| 2 |
-
title: veureu-
|
| 3 |
emoji: 🦎
|
| 4 |
colorFrom: purple
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: "4.44.
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
-
# 🦎 veureu-
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
-
|
| 17 |
-
Funciona tanto desde la **interfaz web (Gradio)** como desde **clientes externos** (por ejemplo, otro Space con Streamlit o una app Python local).
|
| 18 |
|
| 19 |
-
---
|
| 20 |
-
|
| 21 |
-
## 🚀 Características
|
| 22 |
-
|
| 23 |
-
- **ZeroGPU**: utiliza GPU bajo demanda, sin necesidad de hardware dedicado.
|
| 24 |
-
- **Entrada multimodal**: imagen + texto.
|
| 25 |
-
- **Salida**: texto descriptivo (en catalán o español).
|
| 26 |
-
- **API REST directa** (`/api/describe_raw`) + **API Gradio** (`/api/predict/describe`).
|
| 27 |
-
- Compatible con clientes HTTP (`requests`) o `gradio_client`.
|
| 28 |
-
|
| 29 |
-
---
|
| 30 |
-
|
| 31 |
-
## 🧠 Modelo
|
| 32 |
-
|
| 33 |
-
- **Modelo:** `BSC-LT/salamandra-7b-vision`
|
| 34 |
-
- **Arquitectura:** LLaVA-OneVision 7B
|
| 35 |
-
- **Framework:** PyTorch + Transformers
|
| 36 |
-
- **Capa de entrada:** `AutoProcessor`
|
| 37 |
-
- **Generación:** `LlavaOnevisionForConditionalGeneration`
|
| 38 |
-
|
| 39 |
-
El modelo combina visión y lenguaje para generar texto a partir de imágenes, siguiendo el esquema de conversación (“chat template”) oficial de OneVision.
|
| 40 |
-
|
| 41 |
-
---
|
| 42 |
-
|
| 43 |
-
## ⚙️ Configuración del Space
|
| 44 |
-
|
| 45 |
-
**Hardware:** ZeroGPU
|
| 46 |
-
**SDK:** Gradio
|
| 47 |
-
**Archivo principal:** `app.py`
|
| 48 |
-
**Requisitos:** `requirements.txt`
|
| 49 |
-
|
| 50 |
-
Ejemplo del bloque de configuración YAML (este ya está en la cabecera del README):
|
| 51 |
-
|
| 52 |
-
```yaml
|
| 53 |
-
---
|
| 54 |
-
title: Salamandra-Vision 7B · ZeroGPU
|
| 55 |
-
emoji: 🦎
|
| 56 |
-
colorFrom: purple
|
| 57 |
-
colorTo: indigo
|
| 58 |
-
sdk: gradio
|
| 59 |
-
sdk_version: "4.44.0"
|
| 60 |
-
app_file: app.py
|
| 61 |
-
pinned: false
|
| 62 |
-
---
|
|
|
|
| 1 |
---
|
| 2 |
+
title: veureu-svision
|
| 3 |
emoji: 🦎
|
| 4 |
colorFrom: purple
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: "4.44.1"
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# 🦎 veureu-svision (Salamandra-Vision 7B · ZeroGPU)
|
| 13 |
|
| 14 |
+
## Endpoints
|
| 15 |
+
- **`/api/predict`** (Gradio): **batch** — entrada `[[<file1>, <file2>, ...], "{...context_json...}", 256, 0.7]` → salida `["desc1", "desc2", ...]`.
|
| 16 |
+
- **`/api/describe_raw`** (multipart): `image`, `text`, `max_new_tokens`, `temperature` → `{"text": "..."}`.
|
| 17 |
+
- **`/api/describe`** (Gradio UI single).
|
| 18 |
|
| 19 |
+
Compatibilidad con el `engine`: el `VisionClient` del engine llama a **`api_name="/predict"`** con *lista de imágenes* y **`context_json`**.
|
|
|
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
app.py
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
-
# app.py
|
| 2 |
import os
|
| 3 |
-
|
|
|
|
|
|
|
| 4 |
import gradio as gr
|
| 5 |
import spaces
|
| 6 |
import torch
|
|
@@ -8,13 +10,14 @@ from PIL import Image
|
|
| 8 |
from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration
|
| 9 |
|
| 10 |
MODEL_ID = os.environ.get("MODEL_ID", "BSC-LT/salamandra-7b-vision")
|
| 11 |
-
DTYPE = torch.float16
|
| 12 |
-
DEVICE = "cuda"
|
| 13 |
|
| 14 |
_model = None
|
| 15 |
_processor = None
|
| 16 |
|
| 17 |
-
|
|
|
|
| 18 |
global _model, _processor
|
| 19 |
if _model is None or _processor is None:
|
| 20 |
_processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
|
|
@@ -26,32 +29,67 @@ def _lazy_load():
|
|
| 26 |
use_safetensors=True,
|
| 27 |
device_map=None,
|
| 28 |
)
|
|
|
|
| 29 |
return _model, _processor
|
| 30 |
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
return convo
|
| 35 |
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
| 38 |
model, processor = _lazy_load()
|
| 39 |
-
prompt = processor.apply_chat_template(_compose_prompt(text), add_generation_prompt=True)
|
| 40 |
-
|
| 41 |
-
inputs = processor(images=image, text=prompt, return_tensors="pt").to(DEVICE, DTYPE)
|
| 42 |
with torch.inference_mode():
|
| 43 |
out = model.generate(**inputs, max_new_tokens=int(max_new_tokens), temperature=float(temperature))
|
| 44 |
return processor.decode(out[0], skip_special_tokens=True).strip()
|
| 45 |
|
| 46 |
|
| 47 |
-
#
|
|
|
|
| 48 |
def describe_raw(image: Image.Image, text: str = "Describe la imagen con detalle.",
|
| 49 |
max_new_tokens: int = 256, temperature: float = 0.7) -> Dict[str, str]:
|
| 50 |
-
result =
|
| 51 |
return {"text": result}
|
| 52 |
|
| 53 |
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
with gr.Blocks(title="Salamandra Vision 7B · ZeroGPU") as demo:
|
| 56 |
gr.Markdown("## Salamandra-Vision 7B · ZeroGPU\nImagen + texto → descripción.")
|
| 57 |
with gr.Row():
|
|
@@ -64,12 +102,32 @@ with gr.Blocks(title="Salamandra Vision 7B · ZeroGPU") as demo:
|
|
| 64 |
with gr.Column():
|
| 65 |
out = gr.Textbox(label="Descripción", lines=18)
|
| 66 |
|
| 67 |
-
#
|
| 68 |
-
btn.click(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
-
#
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
|
| 75 |
demo.queue(concurrency_count=1, max_size=16).launch()
|
|
|
|
|
|
| 1 |
+
# app.py — veureu/svision (Salamandra Vision 7B · ZeroGPU) — compatible con ENGINE
|
| 2 |
import os
|
| 3 |
+
import json
|
| 4 |
+
from typing import Dict, List, Optional, Tuple, Union
|
| 5 |
+
|
| 6 |
import gradio as gr
|
| 7 |
import spaces
|
| 8 |
import torch
|
|
|
|
| 10 |
from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration
|
| 11 |
|
| 12 |
MODEL_ID = os.environ.get("MODEL_ID", "BSC-LT/salamandra-7b-vision")
|
| 13 |
+
DTYPE = torch.float16 if torch.cuda.is_available() else torch.float32
|
| 14 |
+
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
|
| 15 |
|
| 16 |
_model = None
|
| 17 |
_processor = None
|
| 18 |
|
| 19 |
+
|
| 20 |
+
def _lazy_load() -> Tuple[LlavaOnevisionForConditionalGeneration, AutoProcessor]:
|
| 21 |
global _model, _processor
|
| 22 |
if _model is None or _processor is None:
|
| 23 |
_processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
|
|
|
|
| 29 |
use_safetensors=True,
|
| 30 |
device_map=None,
|
| 31 |
)
|
| 32 |
+
_model.to(DEVICE)
|
| 33 |
return _model, _processor
|
| 34 |
|
| 35 |
+
|
| 36 |
+
def _compose_prompt(user_text: str, context: Optional[Dict] = None) -> List[Dict]:
|
| 37 |
+
"""Construye el chat template con imagen + texto + contexto opcional."""
|
| 38 |
+
ctx_txt = ""
|
| 39 |
+
if context:
|
| 40 |
+
try:
|
| 41 |
+
# breve, sin ruido
|
| 42 |
+
ctx_txt = "\n\nContexto adicional:\n" + json.dumps(context, ensure_ascii=False)[:2000]
|
| 43 |
+
except Exception:
|
| 44 |
+
pass
|
| 45 |
+
user_txt = (user_text or "Describe la imagen con detalle.") + ctx_txt
|
| 46 |
+
convo = [
|
| 47 |
+
{
|
| 48 |
+
"role": "user",
|
| 49 |
+
"content": [
|
| 50 |
+
{"type": "image"},
|
| 51 |
+
{"type": "text", "text": user_txt},
|
| 52 |
+
],
|
| 53 |
+
}
|
| 54 |
+
]
|
| 55 |
return convo
|
| 56 |
|
| 57 |
+
|
| 58 |
+
@spaces.GPU # en HF Spaces usará GPU cuando haya disponibilidad (ZeroGPU)
|
| 59 |
+
def _infer_one(image: Image.Image, text: str, max_new_tokens: int = 256, temperature: float = 0.7,
|
| 60 |
+
context: Optional[Dict] = None) -> str:
|
| 61 |
model, processor = _lazy_load()
|
| 62 |
+
prompt = processor.apply_chat_template(_compose_prompt(text, context), add_generation_prompt=True)
|
| 63 |
+
inputs = processor(images=image, text=prompt, return_tensors="pt").to(DEVICE, dtype=DTYPE)
|
|
|
|
| 64 |
with torch.inference_mode():
|
| 65 |
out = model.generate(**inputs, max_new_tokens=int(max_new_tokens), temperature=float(temperature))
|
| 66 |
return processor.decode(out[0], skip_special_tokens=True).strip()
|
| 67 |
|
| 68 |
|
| 69 |
+
# ----------------------------- API helpers -----------------------------------
|
| 70 |
+
|
| 71 |
def describe_raw(image: Image.Image, text: str = "Describe la imagen con detalle.",
|
| 72 |
max_new_tokens: int = 256, temperature: float = 0.7) -> Dict[str, str]:
|
| 73 |
+
result = _infer_one(image, text, max_new_tokens, temperature, context=None)
|
| 74 |
return {"text": result}
|
| 75 |
|
| 76 |
|
| 77 |
+
def describe_batch(images: List[Image.Image], context_json: str,
|
| 78 |
+
max_new_tokens: int = 256, temperature: float = 0.7) -> List[str]:
|
| 79 |
+
"""Endpoint batch para ENGINE: lista de imágenes + contexto (JSON) → lista de textos."""
|
| 80 |
+
try:
|
| 81 |
+
context = json.loads(context_json) if context_json else None
|
| 82 |
+
except Exception:
|
| 83 |
+
context = None
|
| 84 |
+
outputs: List[str] = []
|
| 85 |
+
for img in images:
|
| 86 |
+
outputs.append(_infer_one(img, text="Describe la imagen con detalle.", max_new_tokens=max_new_tokens,
|
| 87 |
+
temperature=temperature, context=context))
|
| 88 |
+
return outputs
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
# ----------------------------- UI & Endpoints --------------------------------
|
| 92 |
+
|
| 93 |
with gr.Blocks(title="Salamandra Vision 7B · ZeroGPU") as demo:
|
| 94 |
gr.Markdown("## Salamandra-Vision 7B · ZeroGPU\nImagen + texto → descripción.")
|
| 95 |
with gr.Row():
|
|
|
|
| 102 |
with gr.Column():
|
| 103 |
out = gr.Textbox(label="Descripción", lines=18)
|
| 104 |
|
| 105 |
+
# UI
|
| 106 |
+
btn.click(_infer_one, [in_img, in_txt, max_new, temp], out, api_name="describe")
|
| 107 |
+
|
| 108 |
+
# API simple (multipart) compatible con tu versión anterior
|
| 109 |
+
demo.load(
|
| 110 |
+
None,
|
| 111 |
+
[gr.Image(label="image", type="pil"),
|
| 112 |
+
gr.Textbox(value="Describe la imagen con detalle."),
|
| 113 |
+
gr.Slider(16, 1024, value=256),
|
| 114 |
+
gr.Slider(0.0, 1.5, value=0.7)],
|
| 115 |
+
describe_raw,
|
| 116 |
+
api_name="describe_raw"
|
| 117 |
+
)
|
| 118 |
|
| 119 |
+
# API BATCH para ENGINE (Gradio Client): images + context_json → list[str]
|
| 120 |
+
# Firma que espera el VisionClient del engine (api_name="/predict")
|
| 121 |
+
batch_in_images = gr.Gallery(label="Imágenes (batch)", show_label=False).style(grid=[4], height="auto")
|
| 122 |
+
batch_context = gr.Textbox(label="context_json", value="{}", lines=4)
|
| 123 |
+
batch_max = gr.Slider(16, 1024, value=256, step=16, label="max_new_tokens")
|
| 124 |
+
batch_temp = gr.Slider(0.0, 1.5, value=0.7, step=0.05, label="temperature")
|
| 125 |
+
batch_btn = gr.Button("Describir lote")
|
| 126 |
+
batch_out = gr.JSON(label="Descripciones (lista)")
|
| 127 |
+
|
| 128 |
+
# Nota: Gradio Gallery entrega rutas/obj; nos apoyamos en el cliente para cargar archivos
|
| 129 |
+
batch_btn.click(describe_batch, [batch_in_images, batch_context, batch_max, batch_temp], batch_out,
|
| 130 |
+
api_name="predict")
|
| 131 |
|
| 132 |
demo.queue(concurrency_count=1, max_size=16).launch()
|
| 133 |
+
|
clients/client_test.py
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from gradio_client import Client
|
| 2 |
+
c = Client("https://veureu-svision.hf.space")
|
| 3 |
+
out = c.predict(
|
| 4 |
+
["tests/cat.jpg", "tests/dog.jpg"], # lista de imágenes
|
| 5 |
+
'{"hint":"animales domésticos"}', # context_json
|
| 6 |
+
256, 0.7,
|
| 7 |
+
api_name="/predict"
|
| 8 |
+
)
|
| 9 |
+
print(out) # -> ["desc para cat", "desc para dog"]
|
requirements.txt
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
# app (ZeroGPU Gradio)
|
| 2 |
gradio>=4.44.1
|
| 3 |
spaces>=0.25.0
|
| 4 |
transformers>=4.44.0
|
|
@@ -6,7 +5,3 @@ torch>=2.2
|
|
| 6 |
accelerate>=0.30.0
|
| 7 |
safetensors>=0.4.2
|
| 8 |
pillow>=10.3
|
| 9 |
-
|
| 10 |
-
# clients
|
| 11 |
-
#requests>=2.31.0
|
| 12 |
-
#streamlit>=1.36.0
|
|
|
|
|
|
|
| 1 |
gradio>=4.44.1
|
| 2 |
spaces>=0.25.0
|
| 3 |
transformers>=4.44.0
|
|
|
|
| 5 |
accelerate>=0.30.0
|
| 6 |
safetensors>=0.4.2
|
| 7 |
pillow>=10.3
|
|
|
|
|
|
|
|
|
|
|
|