This model is a quick demonstration that the base model can be easily fine-tuned to achieve some performance. It does have minimal moderation mechanisms.

how-to

python

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch
import json

def parse_mistral_chat(messages, function_call = None):

    user_query = messages[-1]['content']

    users, assistants = [], []
    for q in messages[:-1]:
        if q['role'] == 'user':
            users.append(q['content'])
        elif q['role'] == 'assistant':
            assistants.append(q['content'])

    texts = ['<s>']
    
    if function_call:
        fs = []
        for f in function_call:
            f = json.dumps(f, indent=4)
            fs.append(f)
        fs = '\n\n'.join(fs)
        texts.append(f'\n[FUNCTIONCALL]\n{fs}\n')
        
    for u, a in zip(users, assistants):
        texts.append(f'[INST] {u.strip()} [/INST] {a.strip()}</s>')

    texts.append(f'[INST] {user_query.strip()} [/INST]')
    prompt = ''.join(texts).strip()
    return prompt

TORCH_DTYPE = 'bfloat16'
nf4_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type='nf4',
    bnb_4bit_use_double_quant=True,
    bnb_4bit_compute_dtype=getattr(torch, TORCH_DTYPE)
)

tokenizer = AutoTokenizer.from_pretrained('mesolitica/mallam-5b-20k-instructions')
model = AutoModelForCausalLM.from_pretrained(
    'mesolitica/mallam-5b-20k-instructions',
    use_flash_attention_2 = True,
    quantization_config = nf4_config
)

messages = [
    {'role': 'user', 'content': 'kwsp tu apa'}
]
prompt = parse_mistral_chat(messages)
inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to('cuda')
generate_kwargs = dict(
    inputs,
    max_new_tokens=1024,
    top_p=0.95,
    top_k=50,
    temperature=0.9,
    do_sample=True,
    num_beams=1,
)
r = model.generate(**generate_kwargs)
tokenizer.decode(r[0])

<s> [INST] kwsp tu apa [/INST]KWSP bermaksud Kumpulan Wang Simpanan Pekerja. Ia adalah sebuah institusi simpanan persaraan yang ditubuhkan oleh Kementerian Kewangan Malaysia untuk tujuan mengumpul simpanan ahli untuk dibayar pada umur persaraan, penuh atau penuh persaraan penuh. KWSP ditubuhkan pada tahun 1951 dan mula beroperasi pada tahun 1952. KWSP adalah salah satu institusi simpanan persaraan terbesar di dunia, dengan pangkalan ahli sekitar 14 juta ahli.</s>

RichardErkhov/mesolitica_-_mallam-5b-20k-instructions-8bits

Original model description:

Full Parameter Finetuning MaLLaM 🌙 5B 20480 context length on Malaysian instructions dataset

Dataset

Limitations

how-to

RichardErkhov/
mesolitica_-_mallam-5b-20k-instructions-8bits