GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ai4bharat
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ai4bharat
Model Tree
sarvamai/sarvam-translate
Input Modalities
Output Modalities
Supported Functionality
The recommended inference recipe combines three things:
num_beams=4) instead of greedy.glossary.json, included in this repo) containing 6,400+ Bhili↔Marathi term pairs reviewed by native Bhili speakers.post_edit.py, included in this repo) that substitutes terms the model left in the source language with their target-language equivalents from the glossary.⚠️ For the best results, we strongly recommend using the Translate Gemma system prompt when interacting with this model. Using the recommended system prompt helps ensure more consistent and accurate translation outputs.
bash
pip install torch transformers peft accelerate huggingface_hubpython
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelfrom huggingface_hub import hf_hub_download # Load base model + adapterbase_model_name = "sarvamai/sarvam-translate"adapter_name = "ai4bharat/bhili-translate-bhb-mar" tokenizer = AutoTokenizer.from_pretrained(base_model_name)model = AutoModelForCausalLM.from_pretrained( base_model_name, torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(model, adapter_name)model.eval() # Load glossary + post-edit module from this repoglossary_path = hf_hub_download(adapter_name, "glossary.json")post_edit_path = hf_hub_download(adapter_name, "post_edit.py") import importlib.utilspec = importlib.util.spec_from_file_location("post_edit", post_edit_path)pe = importlib.util.module_from_spec(spec)spec.loader.exec_module(pe) glossary = pe.load_glossary(glossary_path) # Translatedef translate(text: str) -> str: messages = [ { "role": "system", "content": ( "You are a professional Bhili (bhb) to Marathi (mr) translator. " "Your goal is to accurately convey the meaning and nuances of the " "original Bhili text while adhering to Marathi grammar, vocabulary, " "and cultural sensitivities. Produce only the Marathi translation, " "without any additional explanations or commentary. Please translate " "the following Bhili text into Marathi:" ), }, {"role": "user", "content": text}, ] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer([prompt], return_tensors="pt").to(model.device) with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=256, do_sample=False, num_beams=4, early_stopping=True, ) raw = tokenizer.decode( output[0][len(inputs.input_ids[0]):], skip_special_tokens=True, ).strip() # Apply glossary post-edit edited, _edits = pe.post_edit( text, raw, glossary["bhb2mar_sorted_keys"], glossary["bhb2mar"] ) return edited # Exampleprint(translate("खेडूतांन वेगीवेळ फवारणी केरनु जोजे हाय."))print(translate("कोपास्यापापे गुलाबी बोंडअळीखातोर कॉपर ऑक्सिक्लोराईड फवारा."))This model was predominantly trained on agricultural-domain data. As a result, performance on domains outside agriculture may vary and may not be representative of the performance observed on agricultural-domain.
pip install torch transformers peft accelerate huggingface_hubimport torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelfrom huggingface_hub import hf_hub_download # Load base model + adapterbase_model_name = "sarvamai/sarvam-translate"adapter_name = "ai4bharat/bhili-translate-bhb-mar" tokenizer = AutoTokenizer.from_pretrained(base_model_name)model = AutoModelForCausalLM.from_pretrained( base_model_name, torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(model, adapter_name)model.eval() # Load glossary + post-edit module from this repoglossary_path = hf_hub_download(adapter_name, "glossary.json")post_edit_path = hf_hub_download(adapter_name, "post_edit.py") import importlib.utilspec = importlib.util.spec_from_file_location("post_edit", post_edit_path)pe = importlib.util.module_from_spec(spec)spec.loader.exec_module(pe) glossary = pe.load_glossary(glossary_path) # Translatedef translate(text: str) -> str: messages = [ { "role": "system", "content": ( "You are a professional Bhili (bhb) to Marathi (mr) translator. " "Your goal is to accurately convey the meaning and nuances of the " "original Bhili text while adhering to Marathi grammar, vocabulary, " "and cultural sensitivities. Produce only the Marathi translation, " "without any additional explanations or commentary. Please translate " "the following Bhili text into Marathi:" ), }, {"role": "user", "content": text}, ] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer([prompt], return_tensors="pt").to(model.device) with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=256, do_sample=False, num_beams=4, early_stopping=True, ) raw = tokenizer.decode( output[0][len(inputs.input_ids[0]):], skip_special_tokens=True, ).strip() # Apply glossary post-edit edited, _edits = pe.post_edit( text, raw, glossary["bhb2mar_sorted_keys"], glossary["bhb2mar"] ) return edited # Exampleprint(translate("खेडूतांन वेगीवेळ फवारणी केरनु जोजे हाय."))print(translate("कोपास्यापापे गुलाबी बोंडअळीखातोर कॉपर ऑक्सिक्लोराईड फवारा."))