GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
oddadmix
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
oddadmix
Model Tree
oddadmix/Emhotob-10M-v2
Input Modalities
Output Modalities
Supported Functionality
Deterministic held-out set of 3,000 pairs (seed=42),
decoded greedily (do_sample=False, no repetition penalty), scored with sacreBLEU:
| Direction | sacreBLEU | chrF |
|---|---|---|
| Darija → English | 19.84 | 29.42 |
| English → Darija | 21.96 | 27.77 |
Saved weights are the best checkpoint by validation loss (eval_loss = 2.093). 20 samples
per direction with references are in eval_bidirectional.json.
Real greedy-decoded outputs from the held-out set:
Darija → English
| Source | Model output | Reference |
|---|---|---|
| لا، عندنا تذاكر يا حبيبة | No, we're going to the game | No, we have tickets darling |
| غطّا وجهو و بكا | he is the first time | He covered his face and wept |
English → Darija
| Source | Model output | Reference |
|---|---|---|
| No, we have tickets darling | لا، عندنا شي حاجة خايبة | لا، عندنا تذاكر يا حبيبة |
| He covered his face and wept | kan7al l7al l7al l7al | غطّا وجهو و بكا |
ChatML format. Pick the system prompt for the direction you want:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "oddadmix/Emhotob-10M-Darija-English-v2"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16).to("cuda").eval() SYSTEM = "You are a professional translator. Translate the Moroccan Darija text into English." def translate(text, system=SYSTEM): prompt = (f"<|im_start|>system\n{system}<|im_end|>\n" f"<|im_start|>user\n{text.strip()}<|im_end|>\n<|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: 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()oddadmix/Emhotob-10M-v2 (Llama arch, hidden 256, 4 layers, 8 heads, vocab 32000, tied embeddings;
10,947,328 params after resizing for 2 ChatML tokens)oddadmix/darija_english_msa_parallel_datasetTrainer, ChatML, prompt-masked cross-entropy (loss only on the
assistant turn). Each row is exploded into two training examples (one per direction).load_best_model_at_end on eval_loss.seed=42), scored both directions.A ~10.9M model: reliable on short/common sentences, but drift, repetition, and errors appear on long or rare inputs. Gender is disambiguated only from context. For fluent translation use the 50M sibling.
Apache-2.0, inherited from the base model.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "oddadmix/Emhotob-10M-Darija-English-v2"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16).to("cuda").eval() SYSTEM = "You are a professional translator. Translate the Moroccan Darija text into English." def translate(text, system=SYSTEM): prompt = (f"<|im_start|>system\n{system}<|im_end|>\n" f"<|im_start|>user\n{text.strip()}<|im_end|>\n<|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: 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()