Downloads · 30 days
19
17% of all-time downloads
apol/gemma4-e2b-social-spain-v12-recovery-lora-public
gemma4-e2b-social-spain-v12-recovery-lora-public is a text generation model from apol. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as gemma.
Public experimental LoRA adapter for google/gemma-4-E2B-it.
Downloads · 30 days
19
17% of all-time downloads
All-time downloads
113
Public
Repo size
134 MB
Likes
0
Public
Click a slice to open those files.
.safetensors101 MB · 76%
From the Hugging Face model README
Public experimental LoRA adapter for google/gemma-4-E2B-it.
This is the best public adapter from the current research line because v12 plus runtime repair/abstention is the strongest internal-eval path. The v13 and v14 adapters remain private experimental artifacts and are not promoted.
Not production-ready. Not legal, medical, or professional social-work advice.
The recommended runtime is:
v12 adapter or public GGUF + dated RAG + validators + repair/abstention + human escalation
The public GGUF derived from this adapter is:
apol/gemma4-e2b-social-spain-v12-q4-k-m-gguf-public
The public demo wrapper is:
https://huggingface.co/spaces/apol/gemma4-social-spain-demo
Gemma 4 Multi-Token Prediction (MTP) can be used as an optional Transformers inference accelerator:
target: google/gemma-4-E2B-it + this v12 LoRA
assistant: google/gemma-4-E2B-it-assistant
MTP is not a fine-tuning method and not a safety layer. It should be evaluated as latency optimization only, while keeping dated RAG, validators, repair/abstention, and human escalation unchanged.
Benchmark from the public artifacts package:
python scripts/benchmark_mtp_runtime.py --dry-run
python scripts/benchmark_mtp_runtime.py
Small CPU benchmark completed on 2026-05-05:
target_only median: 2.81 tokens/s, 5.70 s median latency
target_plus_mtp median: 4.36 tokens/s, 3.67 s median latency
estimated speedup: 1.55x
This confirms functional integration, but it is not a production speed claim because it was CPU-only and short.
google/gemma-4-E2B-it1e-5The full training rows are not public in this release.
As of 2026-05-01:
As of 2026-05-04:
The wrapper eval is not a raw-model benchmark. It validates the intended safety runtime around the model.
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_id = "google/gemma-4-E2B-it"
adapter_id = "apol/gemma4-e2b-social-spain-v12-recovery-lora-public"
tokenizer = AutoTokenizer.from_pretrained(adapter_id, trust_remote_code=True)
base = AutoModelForCausalLM.from_pretrained(base_id, trust_remote_code=True)
model = PeftModel.from_pretrained(base, adapter_id)
Optional MTP generation with the official assistant:
from transformers import AutoModelForCausalLM, AutoProcessor
assistant = AutoModelForCausalLM.from_pretrained("google/gemma-4-E2B-it-assistant", device_map="auto")
assistant.generation_config.num_assistant_tokens = 4
assistant.generation_config.num_assistant_tokens_schedule = "heuristic"
outputs = model.generate(**inputs, assistant_model=assistant, max_new_tokens=220, do_sample=False)
This adapter is a modified Gemma derivative. It is distributed under and subject to the Gemma Terms of Use and Gemma Prohibited Use Policy:
See NOTICE.