Instructions to use OVHaiLLM/Olala-v1.0-translate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OVHaiLLM/Olala-v1.0-translate with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OVHaiLLM/Olala-v1.0-translate", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("OVHaiLLM/Olala-v1.0-translate", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OVHaiLLM/Olala-v1.0-translate with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OVHaiLLM/Olala-v1.0-translate" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OVHaiLLM/Olala-v1.0-translate", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/OVHaiLLM/Olala-v1.0-translate
- SGLang
How to use OVHaiLLM/Olala-v1.0-translate 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 "OVHaiLLM/Olala-v1.0-translate" \ --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": "OVHaiLLM/Olala-v1.0-translate", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "OVHaiLLM/Olala-v1.0-translate" \ --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": "OVHaiLLM/Olala-v1.0-translate", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use OVHaiLLM/Olala-v1.0-translate with Docker Model Runner:
docker model run hf.co/OVHaiLLM/Olala-v1.0-translate
Olala-v1.0-translate
Olala-v1.0-translate is a machine translation model, fine-tuned from Olala-v1.0-mini-7A1B and specialized for financial documents.
- 18 languages: European languages plus Arabic, Chinese (simplified and traditional), Japanese and Korean.
- Controllable: follows a terminology mapping you supply, adapts to a document domain (annual reports, fund factsheets, prospectuses, regulatory texts) and preserves casing and inline tags.
- Best on financial documents: 62.6 BLEU on DOLFIN English to French, 8.6 points ahead of the next model we compared, the best COMET-22 score (88.0) on news and financial text, and within 0.3 BLEU of the best on WMT news.
Model details
| Model | Description |
|---|---|
| Olala-v1.0-mini-7A1B-base | Pre-trained base model (12.8T tokens) |
| Olala-v1.0-mini-7A1B-SFT | After supervised fine-tuning, before RL |
| Olala-v1.0-mini-7A1B | Final post-trained model: reasoning, chat and tool use |
| Olala-v1.0-summarise | Specialized for document summarization |
| Olala-v1.0-translate | Specialized for machine translation, including financial documents |
| Property | Specification |
|---|---|
| Checkpoint | Fine-tuned from Olala-v1.0-mini-7A1B for translation (merge of SFT, ORPO and GRPO checkpoints) |
| Parameters | 6.8B total, about 1B active per token |
| Architecture | 36 layers: 29 Mamba-3 and 7 attention layers, mixture-of-experts with 256 routed experts (6 active) |
| Context length | 32K tokens (input + output) Translation fine-tuning and evaluation used inputs up to 8K tokens. |
| Languages | English, French, German, Spanish, Italian, Dutch, Portuguese, Swedish, Danish, Norwegian, Finnish, Polish, Czech, Russian, Arabic, Chinese (simplified and traditional), Japanese, Korean |
| License | Apache 2.0 |
Inference
The model was trained on a fixed instruction followed by a JSON request, with reasoning disabled. You do not need
to build it by hand: the repo ships a translation chat template,
additional_chat_templates/translation.jinja, that renders it
from the user message and a few chat_template_kwargs. The default chat_template.jinja is the general chat
template.
| Field | Required | Value |
|---|---|---|
source_language |
yes | English language name: English, French, German, Spanish, Italian, Dutch, Portuguese, Swedish, Danish, Norwegian, Finnish, Polish, Czech, Russian, Arabic, Chinese, zh-Hans, zh-Hant, Japanese, Korean |
target_language |
yes | same list |
domain |
no | default General. Trained domains include Annual Report IFRS, Fund Factsheet, Prospectus KIIDs, Regulatory, Asset Management Marketing, Equity Research, Life Insurance, Corporate Actions, Custom |
terminology_mapping |
no | default []; list of {"source_term": "...", "target_term": "..."} |
source_text |
no | default: the content of the last user message |
Decoding: greedy (temperature=0), as in the evaluation.
vLLM: always serve this model with
--mamba-ssm-cache-dtype float32. vLLM's default keeps the Mamba recurrent state in bf16, and long generations then degrade into repetition loops.
vLLM quick start (vLLM fork, installed as for Olala-v1.0-mini-7A1B):
vllm serve OVHaiLLM/Olala-v1.0-translate \
--served-model-name olala-translate \
--trust-remote-code \
--chat-template additional_chat_templates/translation.jinja \
--reasoning-parser olala \
--mamba-ssm-cache-dtype float32 \
--max-model-len 32688
--chat-template makes every request on this server a translation request. To keep the general chat template,
leave it out and send the content of translation.jinja in each request's chat_template field.
--max-model-len must be a multiple of 144.
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
r = client.chat.completions.create(
model="olala-translate",
messages=[{"role": "user", "content": "Le rapport annuel du fonds est publié en mars."}],
temperature=0,
max_tokens=2048,
extra_body={"chat_template_kwargs": {
"source_language": "French",
"target_language": "English",
"domain": "Fund Factsheet",
"terminology_mapping": [{"source_term": "fonds", "target_term": "fund"}],
}},
)
print(r.choices[0].message.content)
Transformers quick start:
from huggingface_hub import hf_hub_download
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "OVHaiLLM/Olala-v1.0-translate"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo, trust_remote_code=True, dtype="bfloat16",
device_map="cuda") # or "cpu" without a GPU (slow)
template = open(hf_hub_download(repo, "additional_chat_templates/translation.jinja")).read()
inputs = tok.apply_chat_template(
[{"role": "user", "content": "Le rapport annuel du fonds est publié en mars."}],
chat_template=template, add_generation_prompt=True, return_tensors="pt", return_dict=True,
source_language="French", target_language="English", domain="Fund Factsheet",
terminology_mapping=[{"source_term": "fonds", "target_term": "fund"}],
).to(model.device)
out = model.generate(**inputs, max_new_tokens=512, do_sample=False, use_cache=True)
text = tok.decode(out[0, inputs["input_ids"].shape[1]:])
print(text.split("<|content|>")[-1].split("<|channel_end|>")[0]) # the final channel: the translation
Chat template
The repo ships two chat templates:
chat_template.jinja: the general Olala 1.0 mini chat template (default), with reasoning in ananalysischannel and the answer in afinalchannel.additional_chat_templates/translation.jinja: the translation template. The client sends only the text to translate as the user message, and the request fields aschat_template_kwargs. The template writes the exact prompt the model was trained on: the translation instruction, then the JSON request (keys in the ordersource_language,target_language,source_text,terminology_mapping,domain).
The translation template always disables reasoning: the rendered prompt ends with
<|im_start|>assistant<|channel_start|>analysis<|content|><|channel_end|>, so the model answers directly in the
final channel. With the vLLM reasoning parser, the response content is the translation only.
A request without source_language or target_language fails with translation template: source_language and target_language are required (chat_template_kwargs).
Performance
Benchmarks
Olala-v1.0-translate against open translation and instruction models of up to 7B parameters, on the same data, with greedy decoding:
- WMT newstest: sentence-level translation quality on the WMT news test sets, 28 directions among English, French, German, Spanish, Italian, Dutch, Portuguese, Swedish, Danish, Norwegian and Finnish. BLEU averaged over the 28 directions.
- COMET-22 (
Unbabel/wmt22-comet-da, times 100) is computed on the full 28-pair set, i.e. the WMT news test sets plus 9 financial domains (fund factsheets, KIIDs, annual reports, regulatory, equity research, ...), not on the news test sets alone. - DOLFIN (Nakhlé et al., Findings of NAACL 2025; dataset:
OVHaiLLM/dolfin): document-level financial translation. 340 English→French KIID / PRIIPs documents (about 200 words each), each translated in one pass. BLEU.
| Model | Size | WMT newstest 28 directions, BLEU |
News + financial 28 pairs, COMET-22 |
DOLFIN en→fr financial documents, BLEU |
|---|---|---|---|---|
| Olala-v1.0-translate | 7B-A1B | 32.6 | 88.0 | 62.6 |
| Gemma 4 E4B | 4B | 31.9 | 87.4 | 54.0 |
| Gemma 3 4B | 4B | 28.7 | 86.1 | 51.9 |
| Qwen3.5 4B | 4B | 29.6 | 86.5 | 51.7 |
| Hy-MT2 7B | 7B | 29.1 | 86.2 | 51.7 |
| Tower+ 2B | 2B | 32.9 | 87.5 | 50.8 |
| TranslateGemma 4B | 4B | 26.8 | 86.6 | 48.6 |
| Hy-MT2 1.8B | 1.8B | 25.2 | 83.3 | 47.5 |
| Qwen3 4B 2507 | 4B | 26.9 | 84.7 | 46.8 |
| Ministral 3 3B | 3B | 20.9 | 79.7 | 36.7 |
Olala-v1.0-translate runs with reasoning disabled and the JSON translation request above. Each other model is shown with its best run per benchmark: its native prompt where its model card documents one (TranslateGemma, Hy-MT2, Tower+), otherwise the better of the same JSON request and a plain-text prompt with the same instructions.
Training
Starting from Olala-v1.0-mini-7A1B, the checkpoint is an equal-weight average (model merge) of three stages of the same translation run:
- Supervised fine-tuning on multilingual translation data, general and financial, with and without terminology constraints.
- Preference optimization (ORPO) on top of the SFT model.
- Reinforcement learning (GRPO) from the ORPO model, with metric-based rewards and no LLM judge.
Uses and limitations
Olala-v1.0-translate is built for machine translation, especially of financial documents. The limitations of Olala-v1.0-mini-7A1B apply. In addition:
- Translation only. Use it with the translation template; for chat, use Olala-v1.0-mini-7A1B.
- Supported languages only: the languages listed above. Other pairs are not supported.
- Long documents: fine-tuning and evaluation used inputs up to 8K tokens. Split longer documents.
- Not a certified translation. Have a qualified translator review legal, regulatory and contractual texts before you publish or rely on them.
- Terminology: the model follows the mapping you supply but can miss terms. Check key terms in the output.
Before you deploy: read the public summary of training content and our copyright policy.
License
| Licence | Apache License, Version 2.0 (SPDX: Apache-2.0) |
| Licensor | OVH LLM SAS, trading as OVHai LLM, 2 rue Kellermann, 59100 Roubaix, France |
| Copyright | Copyright 2026 OVH LLM SAS |
| Release date | 19 November 2026 |
| Distribution | Open weights |
| Notices | NOTICE: keep it when you redistribute the model or a derivative. It includes the attribution of the Qwen tokenizer (Copyright 2024 Alibaba Cloud, Apache 2.0) |
| Training content (EU AI Act) | Public summary of training content, on the European Commission template (Art. 53(1)(d)) |
Citation
@techreport{ovhaillm2026olala,
title = {Olala v1.0 mini Technical Report},
author = {{OVHai LLM Research Team}},
institution = {OVHcloud},
year = {2026},
url = {https://huggingface.co/OVHaiLLM/Olala-v1.0-mini-7A1B/blob/main/Olala-v1.0-mini.pdf},
}
To cite the translation model itself:
@misc{olala-v1.0-translate,
title = {Olala-v1.0-translate: a hybrid Mamba-3 / MoE model for financial machine translation},
author = {OVHaiLLM},
year = {2026},
url = {https://huggingface.co/OVHaiLLM/Olala-v1.0-translate}
}
- Downloads last month
- 69
Model tree for OVHaiLLM/Olala-v1.0-translate
Base model
OVHaiLLM/Olala-v1.0-mini-7A1B-base