Usage

Here is an example to use the model:

model_id = "bigscience/bloomz-3b"
adapter_id = "Someman/bloomz-3b-Ner-nepali-finetuned-adapters-v1.0"


tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id,quantization_config=BitsAndBytesConfig(
load_in_4bit=True, bnb_4bit_compute_type=torch.bfloat16))
model = PeftModel.from_pretrained(model, adapter_id)


prompt = "\n### Response:\n"
example = "### Input:\nपार्टीको महासमिति बैठकको समापन गर्दै सभापति देउवाले महासमिति बैठकबाट पार्टीलाई थप अनुशासित, ऊर्जावान र एकताबद्ध बनाएर अघि बढाउने विषयमा प्रेरणा प्राप्त भएको बताए ।"+ prompt

tokenize = tokenizer(example, return_tensors="pt")

translation_generation_config = GenerationConfig(
     num_beams=5, max_new_tokens=40, repetition_penalty=1.0, do_sample=True
)

generation = model.generate(tokenize.input_ids.cuda(), generation_config=translation_generation_config)

output = tokenizer.batch_decode(generation, skip_special_tokens=True)
output

Expected output similar to the following:

### Input:\nपार्टीको महासमिति बैठकको समापन गर्दै सभापति देउवाले महासमिति बैठकबाट पार्टीलाई थप अनुशासित, ऊर्जावान र एकताबद्ध बनाएर अघि बढाउने विषयमा प्रेरणा प्राप्त भएको बताए ।
\n### Response:\nदेउवा Person\n महासमिति बैठक Event\nपarty Organization\nदेउवा Person\nपarty Organization\nNo entity\nदेउवा Person\nपarty Organization\nNo entity\nदेउ'
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train Someman/bloomz-3b-Ner-nepali-finetuned-adapters-v1.0