Instructions to use oddadmix/50M-MSA-Egyptian-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oddadmix/50M-MSA-Egyptian-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="oddadmix/50M-MSA-Egyptian-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("oddadmix/50M-MSA-Egyptian-v1") model = AutoModelForCausalLM.from_pretrained("oddadmix/50M-MSA-Egyptian-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use oddadmix/50M-MSA-Egyptian-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "oddadmix/50M-MSA-Egyptian-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "oddadmix/50M-MSA-Egyptian-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/oddadmix/50M-MSA-Egyptian-v1
- SGLang
How to use oddadmix/50M-MSA-Egyptian-v1 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 "oddadmix/50M-MSA-Egyptian-v1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "oddadmix/50M-MSA-Egyptian-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "oddadmix/50M-MSA-Egyptian-v1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "oddadmix/50M-MSA-Egyptian-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use oddadmix/50M-MSA-Egyptian-v1 with Docker Model Runner:
docker model run hf.co/oddadmix/50M-MSA-Egyptian-v1
50M-MSA-Egyptian-v1 — Bidirectional MSA ↔ Egyptian Arabic
A 51.8M-parameter small language model that translates both ways between Modern Standard Arabic (الفصحى) and Egyptian colloquial Arabic (المصرية العامية). A single set of weights serves both directions; a direction-specific Arabic system prompt selects which way to translate.
Finetuned from oddadmix/50M-2048-Emhotob,
a tiny Arabic base model trained from scratch.
Evaluation
Evaluated on a deterministic held-out set of 3,000 pairs (seed=42), decoded
greedily (do_sample=False, no repetition penalty), scored with sacreBLEU:
| Direction | sacreBLEU | chrF |
|---|---|---|
| MSA → Egyptian | 24.00 | 52.45 |
| Egyptian → MSA | 26.28 | 52.22 |
Egyptian→MSA scores a bit higher, as expected — MSA is more standardized, so a
single reference captures more of the valid output space. The saved weights are
the best checkpoint by validation loss (eval_loss=1.249, epoch 2 of 3).
Decoding note: use plain greedy. A repetition penalty (
1.2) was tested and lowered BLEU by ~12 points in both directions, because Arabic legitimately repeats short particles that the penalty suppresses.
Example translations
Real greedy-decoded outputs from the held-out set:
MSA → Egyptian
| MSA input | Model output (Egyptian) |
|---|---|
| شكرًا جزيلًا لك، أنت لطيف للغاية. | متشكرة قوي، إنتي طيبة أوي. |
| عزيزتي، المقصد ليس أن لاعبًا واحدًا هو الذي يؤثر على المنتخب الوطني. | يا حبيبي، الفكرة مش إن لاعب واحد هو اللي بيأثر على المنتخب. |
| ليكمل الله لك الخير مقابل ضيافتك الرائعة. | ربنا يكرمك بالخير على ضيافتك الحلوة. |
Egyptian → MSA
| Egyptian input | Model output (MSA) |
|---|---|
| شكراً جداً، إنت طيب قوي. | شكرًا جزيلًا لك، أنت لطيف جدًا. |
| يا حبيبي الفكرة مش إن لعيب واحد هو اللي هيأثر على المنتخب. | يا عزيزتي، الفكرة ليست أن لاعب واحد سيؤثر على الفريق الوطني. |
| ربنا يجازيك خير على كرمك وحسن ضيافتك. | ليجلب الله لك الخير على كرمك، وحسن ضيافتك. |
A larger set of 20 examples per direction (with references) is in
eval_bidirectional_greedy.json.
Usage
ChatML format. Pick the system prompt for the direction you want:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "oddadmix/50M-MSA-Egyptian-v1"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16).to("cuda").eval()
SYS_TO_EGY = "أنت مترجم محترف. ترجم النص من اللغة العربية الفصحى إلى اللهجة المصرية العامية."
SYS_TO_MSA = "أنت مترجم محترف. ترجم النص من اللهجة المصرية العامية إلى اللغة العربية الفصحى."
def translate(text: str, system: str) -> str:
prompt = (
f"<|im_start|>system\n{system}<|im_end|>\n"
f"<|im_start|>user\n{text.strip()}<|im_end|>\n"
f"<|im_start|>assistant\n"
)
ids = tok(prompt, return_tensors="pt", add_special_tokens=False).to(model.device)
if tok.bos_token_id is not None: # training prepends BOS
bos = torch.tensor([[tok.bos_token_id]], device=model.device)
ids["input_ids"] = torch.cat([bos, ids["input_ids"]], dim=1)
ids["attention_mask"] = torch.cat([torch.ones_like(bos), ids["attention_mask"]], dim=1)
out = model.generate(**ids, max_new_tokens=256, do_sample=False,
eos_token_id=tok.eos_token_id, pad_token_id=tok.pad_token_id)
return tok.decode(out[0, ids["input_ids"].size(1):], skip_special_tokens=True).strip()
print(translate("ليكمل الله لك الخير مقابل ضيافتك الرائعة.", SYS_TO_EGY))
# → ربنا يكرمك بالخير على ضيافتك الحلوة.
print(translate("ربنا يجازيك خير على كرمك وحسن ضيافتك.", SYS_TO_MSA))
# → ليجلب الله لك الخير على كرمك، وحسن ضيافتك.
Training
- Base model:
oddadmix/50M-2048-Emhotob(Llama arch, ~51.8M params) - Dataset:
oddadmix/egyptian-msa-2.9-openai-bytedance-translations(132K rows,egyptian/msacolumns) - Method: HuggingFace
Trainer, ChatML, prompt-masked cross-entropy. Each row is exploded into two training examples (one per direction, ~258K total). Two ChatML special tokens (<|im_start|>,<|im_end|>) were added and embeddings resized. - Hyperparameters: 3 epochs · effective batch 64 · LR 3e-4 (cosine, 5% warmup) ·
bf16 · max length 1024 ·
load_best_model_at_endoneval_loss. - Split: 129,009 train / 3,000 deterministic held-out (
seed=42), scored both directions.
Limitations
- A 50M model: expect errors on rare / technical vocabulary and occasional drift on long inputs. Idioms and honorifics are mostly handled well.
- Gender is disambiguated only from context; ambiguous inputs may default one way.
- Trained on conversational Egyptian ↔ MSA; other dialects are out of scope.
License
Apache-2.0, inherited from the base model.
- Downloads last month
- 20
Model tree for oddadmix/50M-MSA-Egyptian-v1
Base model
oddadmix/50M-2048-Emhotob