Instructions to use luispoveda93/Gala with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luispoveda93/Gala with Transformers:

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

pipe = pipeline("image-text-to-text", model="luispoveda93/Gala")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("luispoveda93/Gala")
model = AutoModelForMultimodalLM.from_pretrained("luispoveda93/Gala", device_map="auto")
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 Settings

vLLM

How to use luispoveda93/Gala with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luispoveda93/Gala"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luispoveda93/Gala",
		"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/luispoveda93/Gala

SGLang

How to use luispoveda93/Gala 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 "luispoveda93/Gala" \
    --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": "luispoveda93/Gala",
		"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 "luispoveda93/Gala" \
        --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": "luispoveda93/Gala",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use luispoveda93/Gala with Docker Model Runner:
```
docker model run hf.co/luispoveda93/Gala
```

Gala

Gala is a Catalan-focused conversational model, fine-tuned from Qwen/Qwen3.5-0.8B on Catalan chat data from BSC-LT and projecte-aina.

Base: Qwen/Qwen3.5-0.8B (chat variant, Apache-2.0, multimodal — the vision tower is untouched; all 192 trained modules are language-model projections)
Method: LoRA SFT (r=16, α=32, dropout 0.05) on the language model only, merged into full weights before publish
Data: 43,478 conversations — 35k Catalan slice of BSC-LT/ALIA-2606-SFT (the SFT mix behind BSC's ALIA-40b-instruct), 7,122 projecte-aina/MentorCA train rows converted to chat turns, 1,750 English anchor (~4%); assistant-only loss, packing at 2,048 tokens, 2 epochs (350 steps)
Hardware: 21 h 22 m on a single T4 (fp16, flash-linear-attention kernel active)
Final train loss: 1.496 → 1.074 · eval loss (MentorCA validation): 1.339 · token accuracy 72.6%

Catalan evaluation (Gala vs base Qwen3.5-0.8B)

Generation-based evaluation, letter-parsing for multiple choice, sampled decoding (temp 0.7, top_p 0.9, repetition penalty 1.1). Full JSON: private luispoveda93/Gala-project-report/eval_all_v4.json.

Benchmark	Gala	Base	Δ
IFEval_ca (strict acc, 150-prompt verifier subset)	41.3%	32.7%	+8.7
hhh_alignment_ca (overall)	15.8%	10.4%	+5.4
tecla (4-way news classification, n=300)	44.3%	25.3%	+19.0
COPA-ca (n=500)	64.0%	54.0%	+10.0
arc_ca Easy (n=300)	64.7%	59.3%	+5.3
arc_ca Challenge (n=300)	55.7%	54.0%	+1.7
mgsm_ca (n=250)	23.6%	22.4%	+1.2
EQ-bench_ca (MAE 0–10, lower better, 160/167 parsed)	2.96	3.35	−0.39
CaBBQ (overall, n=400)	41.5%	45.0%	−3.5
xquad-ca (F1, n=300)	37.9	56.1	−18.2

Summary: Gala beats the base model on both core-gate metrics (instruction following and alignment) and on 7 of 10 reported measurements, with the largest gains in Catalan cultural knowledge (Tecla), commonsense (COPA) and instruction following (IFEval_ca).

Limitations (honest)

Fluency ceiling: long-form Catalan output still contains grammatical errors, invented words and hallucinated content — a limitation of the 0.8B scale and the SFT-only recipe, not fixable by more of the same data. Short conversational turns are noticeably more reliable than long generations.
Extractive QA regression: on XQuAD-ca the base model's F1 is higher; Gala's chattier style hurts span-extraction tasks.
CaBBQ is slightly lower than base; MC bias-probe agreement at 0.8B is near chance for both models and should be read cautiously.
Both models were evaluated with the same harness; small-model MC letter-parsing adds noise to all absolute numbers.
Multimodal (vision) behaviour is inherited from the base model and was not fine-tuned or evaluated.

Intended use

Catalan-first conversational assistant for experimentation and demos. Not recommended for production factual use without guardrails.

Training data licenses

ALIA-2606-SFT (CC-BY-4.0) · MentorCA (CC-BY-SA-4.0) · English anchor from ALIA-2606-SFT. InstruCAT (CC-BY-NC-ND) was deliberately excluded.

Decision-reasoning report: private repo luispoveda93/Gala-project-report · Training dashboard: https://huggingface.co/spaces/luispoveda93/gala-catalan-sft-trackio

Downloads last month: -

Safetensors

Model size

0.9B params

Tensor type

F16

Model tree for luispoveda93/Gala

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

(360)

this model

luispoveda93
/

Gala