granitte-8b-code-instruct-sft-en-sr

A full SFT of original 'ibm-granitte/granitte-8b-code-instruct' using a mix of English and Serbian instruction data.

Usage:

import torch from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # or "cpu" model_path = "cminja/granitte-8b-code-instruct" tokenizer = AutoTokenizer.from_pretrained(model_path)

drop device_map if running on CPU

model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device) model.eval()

change input text as desired

chat = [ { "role": "user", "content": "Write a code to find the maximum value in a list of numbers." }, ] chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

tokenize the text

input_tokens = tokenizer(chat, return_tensors="pt")

transfer tokenized inputs to the device

for i in input_tokens: input_tokens[i] = input_tokens[i].to(device)

generate output tokens

output = model.generate(**input_tokens, max_new_tokens=100)

decode output tokens into text

output = tokenizer.batch_decode(output)

loop over the batch to print, in this example the batch size is 1

for i in output: print(i)