GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
nithin093
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nithin093
Model Tree
sarvamai/sarvam-1
Input Modalities
Output Modalities
Supported Functionality
To run inference using this model, you need to install the dependencies including unsloth for ultra-fast performance.
bash
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"pip install torch transformers peft accelerate bitsandbytes deep-translatorpython
from unsloth import FastLanguageModelimport torch # Load the base model and the custom LoRA adaptermodel, tokenizer = FastLanguageModel.from_pretrained( model_name = "nithin093/annamacharya_sangeetha_sankeerthanalu", max_seq_length = 2048, dtype = None, load_in_4bit = True,)FastLanguageModel.for_inference(model) prompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:పద్మావతీ దేవి వైభవమును మరియు ఆమె కరుణను కీర్తిస్తూ ఒక మధురమైన అన్నమయ్య శైలి సంకీర్తన వ్రాయుము. ### Response:""" inputs = tokenizer([prompt], return_tensors = "pt").to("cuda")outputs = model.generate( **inputs, max_new_tokens = 512, use_cache = True, temperature = 0.7, top_p = 0.9, repetition_penalty = 1.15) print(tokenizer.batch_decode(outputs, skip_special_tokens = True)[0])Perfect for applications serving end-users who wish to prompt in English while expecting high-quality classical Telugu output.
python
from deep_translator import GoogleTranslator def generate_sankeerthana_from_english(english_instruction): # 1. Translate English prompt to Telugu telugu_translation = GoogleTranslator(source='en', target='te').translate(english_instruction) # 2. Format with the instruction-tuning template formatted_prompt = f"""Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:{telugu_translation} ### Response:""" # 3. Tokenize and generate inputs = tokenizer([formatted_prompt], return_tensors = "pt").to("cuda") outputs = model.generate( **inputs, max_new_tokens = 512, use_cache = True, temperature = 0.7, top_p = 0.9, repetition_penalty = 1.15 ) generated_output = tokenizer.batch_decode(outputs, skip_special_tokens = True)[0] if "### Response:" in generated_output: return generated_output.split("### Response:")[1].strip() return generated_output # Run the pipelineenglish_prompt = "Write a classical sankeerthana about the divine beauty of Goddess Padmavati and her eternal love connection with Lord Venkateswara"print(generate_sankeerthana_from_english(english_prompt))sarvamai/sarvam-1keerthanas_instructions_3k.jsonl).Unsloth & trl.SFTTraineradamw_8bit2e-4r=16, alpha=16, Target modules including Attention & MLP projections.This project is licensed under the Apache-2.0 License.
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"pip install torch transformers peft accelerate bitsandbytes deep-translatorfrom unsloth import FastLanguageModelimport torch # Load the base model and the custom LoRA adaptermodel, tokenizer = FastLanguageModel.from_pretrained( model_name = "nithin093/annamacharya_sangeetha_sankeerthanalu", max_seq_length = 2048, dtype = None, load_in_4bit = True,)FastLanguageModel.for_inference(model) prompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:పద్మావతీ దేవి వైభవమును మరియు ఆమె కరుణను కీర్తిస్తూ ఒక మధురమైన అన్నమయ్య శైలి సంకీర్తన వ్రాయుము. ### Response:""" inputs = tokenizer([prompt], return_tensors = "pt").to("cuda")outputs = model.generate( **inputs, max_new_tokens = 512, use_cache = True, temperature = 0.7, top_p = 0.9, repetition_penalty = 1.15) print(tokenizer.batch_decode(outputs, skip_special_tokens = True)[0])from deep_translator import GoogleTranslator def generate_sankeerthana_from_english(english_instruction): # 1. Translate English prompt to Telugu telugu_translation = GoogleTranslator(source='en', target='te').translate(english_instruction) # 2. Format with the instruction-tuning template formatted_prompt = f"""Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:{telugu_translation} ### Response:""" # 3. Tokenize and generate inputs = tokenizer([formatted_prompt], return_tensors = "pt").to("cuda") outputs = model.generate( **inputs, max_new_tokens = 512, use_cache = True, temperature = 0.7, top_p = 0.9, repetition_penalty = 1.15 ) generated_output = tokenizer.batch_decode(outputs, skip_special_tokens = True)[0] if "### Response:" in generated_output: return generated_output.split("### Response:")[1].strip() return generated_output # Run the pipelineenglish_prompt = "Write a classical sankeerthana about the divine beauty of Goddess Padmavati and her eternal love connection with Lord Venkateswara"print(generate_sankeerthana_from_english(english_prompt))