qwen3.5-2b-ml-paper-translate API & Inference Endpoint

Training

Training rows: 98127
Per-device batch size: 4
Gradient accumulation: 4
Effective batch size: 16
Sequence length: 2048
Epochs: 1.0
Learning rate: 0.0001
QLoRA rank/alpha/dropout: 32/64/0.05
Training hardware: NVIDIA GeForce RTX 4090 24 GB
Objective: English-to-Japanese causal language modeling with assistant-only loss
Target domains: deep learning, robotics, language models, and vision-language-action models
Grounding: recent arXiv metadata, abstracts, and available ar5iv excerpts

Dataset

json
{
  "accepted": 100000,
  "rejected": 24871,
  "splits": {
    "train": 98127,
    "valid": 957,
    "test": 916
  },
  "domains": {
    "deep_learning": 25123,
    "language_models": 24548,
    "robotics": 25686,
    "vision_language_action": 24643
  },
  "complete": true
}

The training dataset, references, and per-example predictions are not distributed from this repository. Only aggregate evaluation results are published.

Evaluation

chrF++ is reported on a 0–100 scale. Preservation and terminology values are fractions from 0–1.

Table with columns: Run, Rows, chrF++, Numeric/symbol preservation, Math preservation, Terminology accuracy
Run	Rows	chrF++	Numeric/symbol preservation	Math preservation	Terminology accuracy
base-valid	957	45.47	0.89	0.85	0.35
tuned-valid	957	66.56	0.92	1.00	0.81
base-test	916

json
{
  "base-valid.metrics": {
    "count": 957,
    "chrf_pp": 45.468870997399854,
    "numeric_symbol_preservation": 0.8938547486033519,
    "numeric_symbol_examples": 716,
    "math_preservation": 0.8472222222222222,
    "math_examples": 72,
    "terminology_recall": 0.34812286689419797,
    "terminology_accuracy": 0.34812286689419797,
    "terminology_terms": 293,
    "no_extraneous_prefix": 1.0
  },
  "base-test.metrics": {
    "count": 916,
    "chrf_pp": 44.07591737903462,
    "numeric_symbol_preservation": 0.8801213960546282,
    "numeric_symbol_examples": 659,
    "math_preservation": 0.863013698630137,
    "math_examples": 73,
    "terminology_recall": 0.3767441860465116,
    "terminology_accuracy": 0.3767441860465116,
    "terminology_terms": 215,
    "no_extraneous_prefix": 1.0
  },
  "tuned-valid.metrics": {
    "count": 957,
    "chrf_pp": 66.5621385606034,
    "numeric_symbol_preservation": 0.9175977653631285,
    "numeric_symbol_examples": 716,
    "math_preservation": 1.0,
    "math_examples": 72,
    "terminology_recall": 0.8088737201365188,
    "terminology_accuracy": 0.8088737201365188,
    "terminology_terms": 293,
    "no_extraneous_prefix": 1.0
  },
  "tuned-test.metrics": {
    "count": 916,
    "chrf_pp": 65.9248842697133,
    "numeric_symbol_preservation": 0.9059180576631259,
    "numeric_symbol_examples": 659,
    "math_preservation": 1.0,
    "math_examples": 73,
    "terminology_recall": 0.8372093023255814,
    "terminology_accuracy": 0.8372093023255814,
    "terminology_terms": 215,
    "no_extraneous_prefix": 1.0
  },
  "gpu-stability": {
    "training_completed": true,
    "training_rows": 98127,
    "per_device_train_batch_size": 4,
    "samples": 2633,
    "first_sample": "2026/09/11 15:21:25.431",
    "last_sample": "2026/09/11 19:02:39.979",
    "peak_memory_used_mib": 19785.0,
    "minimum_memory_free_mib": 4308.0,
    "peak_gpu_util_percent": 100.0,
    "peak_temperature_c": 74.0,
    "peak_power_w": 360.9
  }
}

Local deployment

Convert this merged model to MLX 4-bit on Apple Silicon with qwen-translate export-mlx, then install the Native Messaging Host with scripts/install_macos.sh. The companion Manifest V3 Chrome extension translates selected text locally and restores ar5iv MathML after generation.

Transformers

python
import torch
from transformers import AutoModelForImageTextToText, AutoTokenizer

model_id = "Teluteru/qwen3.5-2b-ml-paper-translate"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id, dtype=torch.bfloat16, device_map="auto"
)
messages = [
    {
        "role": "system",
        "content": (
            "Translate technical English into natural Japanese. Preserve equations, "
            "numbers, units, identifiers, and formatting. Return only the translation."
        ),
    },
    {"role": "user", "content": "The VLA policy predicts robot actions from images."},
]
prompt = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True, enable_thinking=False
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.inference_mode():
    generated = model.generate(**inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(generated[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))

MLX 4-bit on Apple Silicon

bash
hf download Teluteru/qwen3.5-2b-ml-paper-translate --local-dir model-hf
python -m mlx_lm convert --hf-path model-hf --mlx-path model-mlx-4bit   -q --q-bits 4 --q-group-size 64

Use enable_thinking=False; fine-tuning used the non-thinking chat-template prefix. The companion project defaults to the 2B model and can switch between installed 2B and 4B MLX models.

Limitations

The corpus and references are synthetic and can contain unnatural wording or factual errors.
Automatic preservation scores are not perfect; callers should retain deterministic MathML placeholder checks and verify numbers for consequential use.
Qualitative review found that unsupervised/supervised may occasionally be rendered as the understandable but unnatural 非監督/監督; 教師なし/教師あり is preferred.
This model is not validated for safety-critical robot control or languages other than English to Japanese.

The data and automatic metrics may contain errors. Review translations before safety-critical use. MathML on ar5iv pages is preserved by the companion Chrome extension outside the language model.

json

{
  "accepted": 100000,
  "rejected": 24871,
  "splits": {
    "train": 98127,
    "valid": 957,
    "test": 916
  },
  "domains": {
    "deep_learning": 25123,
    "language_models": 24548,
    "robotics": 25686,
    "vision_language_action": 24643
  },
  "complete": true
}

Run

Rows

chrF++

Numeric/symbol preservation

Math preservation

Terminology accuracy

base-valid

957

45.47

0.89

0.85

0.35

tuned-valid

957

66.56

0.92

1.00

0.81

base-test

916

json

{
  "base-valid.metrics": {
    "count": 957,
    "chrf_pp": 45.468870997399854,
    "numeric_symbol_preservation": 0.8938547486033519,
    "numeric_symbol_examples": 716,
    "math_preservation": 0.8472222222222222,
    "math_examples": 72,
    "terminology_recall": 0.34812286689419797,
    "terminology_accuracy": 0.34812286689419797,
    "terminology_terms": 293,
    "no_extraneous_prefix": 1.0
  },
  "base-test.metrics": {
    "count": 916,
    "chrf_pp": 44.07591737903462,
    "numeric_symbol_preservation": 0.8801213960546282,
    "numeric_symbol_examples": 659,
    "math_preservation": 0.863013698630137,
    "math_examples": 73,
    "terminology_recall": 0.3767441860465116,
    "terminology_accuracy": 0.3767441860465116,
    "terminology_terms": 215,
    "no_extraneous_prefix": 1.0
  },
  "tuned-valid.metrics": {
    "count": 957,
    "chrf_pp": 66.5621385606034,
    "numeric_symbol_preservation": 0.9175977653631285,
    "numeric_symbol_examples": 716,
    "math_preservation": 1.0,
    "math_examples": 72,
    "terminology_recall": 0.8088737201365188,
    "terminology_accuracy": 0.8088737201365188,
    "terminology_terms": 293,
    "no_extraneous_prefix": 1.0
  },
  "tuned-test.metrics": {
    "count": 916,
    "chrf_pp": 65.9248842697133,
    "numeric_symbol_preservation": 0.9059180576631259,
    "numeric_symbol_examples": 659,
    "math_preservation": 1.0,
    "math_examples": 73,
    "terminology_recall": 0.8372093023255814,
    "terminology_accuracy": 0.8372093023255814,
    "terminology_terms": 215,
    "no_extraneous_prefix": 1.0
  },
  "gpu-stability": {
    "training_completed": true,
    "training_rows": 98127,
    "per_device_train_batch_size": 4,
    "samples": 2633,
    "first_sample": "2026/09/11 15:21:25.431",
    "last_sample": "2026/09/11 19:02:39.979",
    "peak_memory_used_mib": 19785.0,
    "minimum_memory_free_mib": 4308.0,
    "peak_gpu_util_percent": 100.0,
    "peak_temperature_c": 74.0,
    "peak_power_w": 360.9
  }
}

python

import torch
from transformers import AutoModelForImageTextToText, AutoTokenizer

model_id = "Teluteru/qwen3.5-2b-ml-paper-translate"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id, dtype=torch.bfloat16, device_map="auto"
)
messages = [
    {
        "role": "system",
        "content": (
            "Translate technical English into natural Japanese. Preserve equations, "
            "numbers, units, identifiers, and formatting. Return only the translation."
        ),
    },
    {"role": "user", "content": "The VLA policy predicts robot actions from images."},
]
prompt = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True, enable_thinking=False
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.inference_mode():
    generated = model.generate(**inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(generated[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))

qwen3.5-2b-ml-paper-translate

README

Training

Dataset

Evaluation

Local deployment

Transformers

MLX 4-bit on Apple Silicon

Limitations

Explore FriendliAI today

README

Training

Dataset

Evaluation

Local deployment

Transformers

MLX 4-bit on Apple Silicon

Limitations