Downloads · 30 days
335
8% of all-time downloads
afrideva/malaysian-tinyllama-1.1b-16k-instructions-GGUF
malaysian-tinyllama-1.1b-16k-instructions-GGUF is a text generation model from afrideva. Use it when you need the model to write or continue text.
Quantized GGUF model files for malaysian-tinyllama-1.1b-16k-instructions from mesolitica
Downloads · 30 days
335
8% of all-time downloads
All-time downloads
4.3K
Public
Repo size
4.6 GB
Likes
2
Public
Click a slice to open those files.
.gguf4.6 GB · 100%
From the Hugging Face model README
Quantized GGUF model files for malaysian-tinyllama-1.1b-16k-instructions from mesolitica
| Name | Quant method | Size |
|---|---|---|
| malaysian-tinyllama-1.1b-16k-instructions.q2_k.gguf | q2_k | 482.14 MB |
| malaysian-tinyllama-1.1b-16k-instructions.q3_k_m.gguf | q3_k_m | 549.85 MB |
| malaysian-tinyllama-1.1b-16k-instructions.q4_k_m.gguf | q4_k_m | 667.81 MB |
| malaysian-tinyllama-1.1b-16k-instructions.q5_k_m.gguf | q5_k_m | 782.04 MB |
| malaysian-tinyllama-1.1b-16k-instructions.q6_k.gguf | q6_k | 903.41 MB |
| malaysian-tinyllama-1.1b-16k-instructions.q8_0.gguf | q8_0 | 1.17 GB |
We use exact Llama2 Instruct chat template, added with function call
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch
def parse_llama_chat(messages, function_call = None):
system = messages[0]['content']
user_query = messages[-1]['content']
users, assistants = [], []
for q in messages[1:-1]:
if q['role'] == 'user':
users.append(q['content'])
elif q['role'] == 'assistant':
assistants.append(q['content'])
texts = [f'<s>[INST] <<SYS>>\n{system}\n<</SYS>>\n\n']
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'{u.strip()} [/INST] {a.strip()} </s><s>[INST] ')
texts.append(f'{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/malaysian-tinyllama-1.1b-16k-instructions')
model = AutoModelForCausalLM.from_pretrained(
'mesolitica/malaysian-tinyllama-1.1b-16k-instructions',
use_flash_attention_2 = True,
quantization_config = nf4_config
)
messages = [
{'role': 'system', 'content': 'awak adalah AI yang mampu jawab segala soalan'},
{'role': 'user', 'content': 'kwsp tu apa'}
]
prompt = parse_llama_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)
print(tokenizer.decode(r[0]))
'<s> [INST] <<SYS>>
awak adalah AI yang mampu jawab segala soalan
<</SYS>>
kwsp tu apa [/INST] KWSP bermaksud Kumpulan Wang Persaraan. </s>'
messages = [
{'role': 'system', 'content': 'awak adalah AI yang mampu jawab segala soalan'},
{'role': 'user', 'content': 'awat malaysia ada jabatan koko, malaysia bukan buat keluaq koko banyak pun'}
]
prompt = parse_llama_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)
print(tokenizer.decode(r[0]))
<s> [INST] <<SYS>>
awak adalah AI yang mampu jawab segala soalan
<</SYS>>
awat malaysia ada jabatan koko, malaysia bukan buat keluaq koko banyak pun [/INST] Jabatan ini bertanggungjawab untuk mengeluarkan dan mengagihkan produk koko ke pasaran tempatan dan antarabangsa. Mereka juga menyumbang kepada pembangunan industri koko dan memastikan penggunaan sumber asli yang bertanggungjawab. Selain itu, mereka menjalankan penyelidikan dan inovasi untuk meningkatkan proses pengeluaran dan meningkatkan daya saing produk koko. </s>
f2 = {
'name': 'parse_entities',
'description': 'extract entities from the text',
'parameters': {
'type': 'object',
'properties': {
'drink': {
'type': 'string',
'description': 'drink name',
},
'event': {
'type': 'string',
'description': 'event name',
},
'person_name': {
'type': 'string',
'description': 'person name',
}
},
'required': [
'drink',
'event',
'person_name'
]
}
}
messages = [
{'role': 'system', 'content': 'awak adalah AI yang mampu jawab segala soalan'},
{'role': 'user', 'content': 'nama saya husein bin zolkepli, saya sekarang berada di putrajaya merdeka 2023 sambil minum teh o ais'}
]
prompt = parse_llama_chat(messages, function_call = [f2])
inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to('cuda')
generate_kwargs = dict(
inputs,
max_new_tokens=128,
top_p=0.95,
top_k=50,
temperature=0.9,
do_sample=True,
num_beams=1,
)
r = model.generate(**generate_kwargs)
print(tokenizer.decode(r[0]))
<s> [INST] <<SYS>>
awak adalah AI yang mampu jawab segala soalan
<</SYS>>
[FUNCTIONCALL]
{
"name": "parse_entities",
"description": "extract entities from the text",
"parameters": {
"type": "object",
"properties": {
"drink": {
"type": "string",
"description": "drink name"
},
"event": {
"type": "string",
"description": "event name"
},
"person_name": {
"type": "string",
"description": "person name"
}
},
"required": [
"drink",
"event",
"person_name"
]
}
}
nama saya husein bin zolkepli, saya sekarang berada di putrajaya merdeka 2023 sambil minum teh o ais [/INST] <functioncall> {"name": "parse_entities", "arguments": '{"drink": "teh o ais", "event": "Merdeka 2023", "person_name": "Husein bin Zolkepli"}'}
<functioncall> {"entities": [{"name": "Husein bin Zolkepli", "confidence": 0.95}]} </s>