Text Generation
MLX
Safetensors
qwen3_5
transliteration
ime
input-method
pinyin
romaji
hinglish
arabizi
cyrillic
greeklish
vietnamese
qwen3.5
v2.6
conversational
6-bit
Instructions to use UnimeType/Transliteration-2.0-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use UnimeType/Transliteration-2.0-9B with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("UnimeType/Transliteration-2.0-9B") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use UnimeType/Transliteration-2.0-9B with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "UnimeType/Transliteration-2.0-9B"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "UnimeType/Transliteration-2.0-9B" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use UnimeType/Transliteration-2.0-9B with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "UnimeType/Transliteration-2.0-9B"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "UnimeType/Transliteration-2.0-9B" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "UnimeType/Transliteration-2.0-9B", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use UnimeType/Transliteration-2.0-9B with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "UnimeType/Transliteration-2.0-9B"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default UnimeType/Transliteration-2.0-9B
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use UnimeType/Transliteration-2.0-9B with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "UnimeType/Transliteration-2.0-9B"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "UnimeType/Transliteration-2.0-9B" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download PROVENANCE.json from UnimeType/Transliteration-2.0-9B: direct link, hf CLI and curl.
- Browser
- Download file 3.89 kB
-
https://huggingface.co/UnimeType/Transliteration-2.0-9B/resolve/main/PROVENANCE.json
- Command line
-
hf download hf://UnimeType/Transliteration-2.0-9B/PROVENANCE.json
-
curl -L -o PROVENANCE.json https://huggingface.co/UnimeType/Transliteration-2.0-9B/resolve/main/PROVENANCE.json
3.89 kB
| { | |
| "repository": "UnimeType/Transliteration-2.0-9B", | |
| "version": "2.6", | |
| "model_version": "2.6 (dataset_v5.1 12-language upgrade)", | |
| "release_tag": "v2.6", | |
| "protocol_version": "unimetype-convert-short-v3", | |
| "format": "MLX 6-bit affine, group size 64", | |
| "base_model": "Qwen/Qwen3.5-9B", | |
| "base_snapshot_revision": "c202236235762e1c871ad0ccb60c8ee5ba337b9a", | |
| "base_source_sha256": { | |
| "model.safetensors-00001-of-00004.safetensors": "db6f444b43d318c92f360a13a25561a6a65b10c0631b8ed305a426dbaa6c380e", | |
| "model.safetensors-00002-of-00004.safetensors": "31c7d7e2dd5d207840b31cc59083c8f4c4718959149e0358c0364052bb9a0330", | |
| "model.safetensors-00003-of-00004.safetensors": "7ec36ba3a4176a44c3c0876ad80c56a2f70c84bf008d82e9501df642f17dadec", | |
| "model.safetensors-00004-of-00004.safetensors": "b62b0c4cd7e44edee103ee8f4fe225f246d5e768e07bfd5f25b63a8aa1fdd0c6" | |
| }, | |
| "lora_adapter_sha256": "ed51a188f09bef51c82fba732e8c9c8990998175d63a24b2994f97b4dcbe43e4", | |
| "lora_hyperparameters": { | |
| "r": 32, | |
| "lora_alpha": 96.0, | |
| "scale": 3.0, | |
| "num_layers": 32, | |
| "fused_linear_modules": 248 | |
| }, | |
| "training_method": "LoRA SFT + Zero-Overlap Contrastive Preference Alignment (r=32, alpha=96, all 32 layers) on native unquantized BF16 Qwen/Qwen3.5-9B across 12 languages / 13 modes", | |
| "native_unquantized_base_precision": true, | |
| "training_dataset_public": false, | |
| "source_safetensors_repo": "UnimeType/Transliteration-2.0-9B-Safetensors", | |
| "standard_weight_sha256": { | |
| "model-00001-of-00004.safetensors": "800d3318a76943b7313231e4dbc64e34f4b5c94a180e10f65e2ab248847beb2a", | |
| "model-00002-of-00004.safetensors": "ab374a3bceae7c48d61701b7b3ec8034eccb3035083f4205f96e07468e55ad85", | |
| "model-00003-of-00004.safetensors": "3973ff5f69d3f9f7279258673ef22835d4d77974747b94f654b4ce03f1d3d321", | |
| "model-00004-of-00004.safetensors": "cc10ea28a11931916b5befcb6fc9e9314c78ae42e0cce19401f9b3a22faf8b78" | |
| }, | |
| "published_weight_sha256": { | |
| "model-00001-of-00002.safetensors": "c369564008e7e976b241d6eb7b81351cb2eec96684d60388903e4fb0e7751307", | |
| "model-00002-of-00002.safetensors": "9390344fcd1d769b8a0fdf6342d33fd1876cbcb154ab0a47e88777e520c16562" | |
| }, | |
| "evaluation": { | |
| "protocol": "unimetype-convert-short-v3", | |
| "dataset_generation": "dataset_v5.1_clean_12lang (0.00% eval overlap)", | |
| "cloud_reference": { | |
| "model": "deepseek/deepseek-v4.1-flash (system prompt ~2,800 tok)", | |
| "v4_shared_708": 0.9082, | |
| "core5_773": 0.903, | |
| "multilingual_12lang_1573": 0.932, | |
| "mst_bench_520_exact": 0.7346, | |
| "mst_bench_520_tolerant": 0.7481, | |
| "dogfood_30_exact": 0.5333, | |
| "dogfood_30_tolerant": 0.7667, | |
| "ood_unseen_20_probe_repair": 0.9 | |
| }, | |
| "models": { | |
| "0.8B": { | |
| "best_epoch": 3.0, | |
| "valid_loss": 0.263216, | |
| "v4_shared_708": 0.7232, | |
| "core5_773": 0.7115, | |
| "multilingual_12lang_1573": 0.6999, | |
| "mst_bench_520_exact": 0.4115, | |
| "mst_bench_520_tolerant": 0.4173, | |
| "dogfood_30_exact": 0.3667, | |
| "dogfood_30_tolerant": 0.3667, | |
| "ood_unseen_20_probe_repair": 0.45 | |
| }, | |
| "4B": { | |
| "best_epoch": 2.0, | |
| "valid_loss": 0.1105, | |
| "v4_shared_708": 0.8912, | |
| "core5_773": 0.8745, | |
| "multilingual_12lang_1573": 0.8811, | |
| "mst_bench_520_exact": 0.6327, | |
| "mst_bench_520_tolerant": 0.6385, | |
| "dogfood_30_exact": 0.5, | |
| "dogfood_30_tolerant": 0.5667, | |
| "ood_unseen_20_probe_repair": 0.75 | |
| }, | |
| "9B": { | |
| "best_epoch": 2.0, | |
| "valid_loss": 0.0799, | |
| "v4_shared_708": 0.9209, | |
| "core5_773": 0.9094, | |
| "multilingual_12lang_1573": 0.9154, | |
| "mst_bench_520_exact": 0.6558, | |
| "mst_bench_520_tolerant": 0.6731, | |
| "dogfood_30_exact": 0.7333, | |
| "dogfood_30_tolerant": 0.7667, | |
| "ood_unseen_20_probe_repair": 0.9 | |
| } | |
| } | |
| } | |
| } | |