Text Generation
Transformers
Safetensors
Telugu
llama
conversational
Inference Endpoints
text-generation-inference
Edit model card

Model card for Llama2chat_telugu (romanized)

meta-llama/Llama-2-7b-chat-hf is finetuned on tranliterated telugu sentences.

usage

from transformers import pipeline

pipe = pipeline(
    "text-generation", 
    model="eswardivi/llama2chat_telugu", 
    device_map="auto"
)

def create_prompt(instruction: str, input: str = "") -> str:
    prompt = f"""
### Instruction:
{instruction}

### Response:
"""
    return prompt

prompt = create_prompt("Naku python Program 1 to 10 count cheyadaniki ivvu")

out = pipe(
    prompt, 
    num_return_sequences=1, 
    max_new_tokens=1024, 
    temperature=0.7, 
    top_p=0.9, 
    do_sample=True
)

print(out[0]['generated_text'])

Downloads last month
4
Safetensors
Model size
6.74B params
Tensor type
FP16
·

Datasets used to train eswardivi/llama2chat_telugu