File size: 3,690 Bytes
75c309e fa09dfd 1d85732 fa09dfd 1d85732 fa09dfd 75c309e fa09dfd 5a290c0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
---
license: llama2
widget:
- example_title: "ALMA-Cymraeg-13B"
text: "### Saesneg:\nFor the first time, GPs no longer have to physically print, sign and hand a green paper prescription form to the patient or wait for it to be taken to the pharmacy. Instead, the prescription is sent electronically from the surgery via the IT system to the patient’s chosen pharmacy - even without the patient needing to visit the surgery to pick up a repeat prescription form."
output:
text: "\n### Cymraeg:\nAm y tro cyntaf, nid oes rhaid i feddygon teulu bellach argraffu, llofnodi a throsglwyddo ffurflen bresgripsiwn werdd i'r claf neu aros iddi gael ei chludo i'r fferyllfa. Yn lle hynny, caiff y presgripsiwn ei anfon yn electronig gan y practis drwy'r system TG at fferyllfa ddewisedig y claf - heb fod angen i'r claf ymweld â'r practis er mwyn casglu ffurflen bresgripsiwn ailadrodd."
pipeline_tag: text-generation
---
BangorAI/ALMA-Cymraeg-13B-0.1-4.0bpw-exl2
#### Esiampl
```python
import time
import sys, os
import dataclasses
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from exllamav2 import(
ExLlamaV2,
ExLlamaV2Config,
ExLlamaV2Cache,
ExLlamaV2Tokenizer,
ExLlamaV2Lora,
)
from exllamav2.generator import (
ExLlamaV2StreamingGenerator,
ExLlamaV2Sampler
)
class ModelClass:
def __init__(self, generator, tokenizer, model):
self.generator = generator
self.tokenizer = tokenizer
self.model = model
DEBUG = os.environ.get("DEBUG") and True or False
# Cychwyn model a storfa
def load_model(model_directory, max_seq_len=8192):
"""
Yn llwytho model o gyfeiriadur ac yn dychwelyd y generadur a'r tocynnwr
"""
config = ExLlamaV2Config()
config.model_dir = model_directory
config.max_seq_len = max_seq_len
config.prepare()
model = ExLlamaV2(config)
print("Llwytho model: " + model_directory)
cache = ExLlamaV2Cache(model, lazy = True, max_seq_len=max_seq_len)
model.load_autosplit(cache)
tokenizer = ExLlamaV2Tokenizer(config)
generator = ExLlamaV2StreamingGenerator(model, cache, tokenizer)
model = ModelClass(generator=generator, tokenizer=tokenizer, model=model)
generator.warmup()
return model
def generate_text(prompt, settings, max_new_tokens):
sys.stdout.flush()
input_ids = base_model.tokenizer.encode(prompt)
generated_tokens = 0 # input_ids.shape[-1]
base_model.generator.set_stop_conditions(["\n"])
base_model.generator.begin_stream(input_ids, settings)
time_begin = time.time()
while True:
chunk, eos, _ = base_model.generator.stream()
generated_tokens += 1
print (chunk, end = "")
sys.stdout.flush()
if eos or generated_tokens == max_new_tokens: break
time_end = time.time()
time_total = time_end - time_begin
print(f"\nYmateb cyflawn mewn {time_total:.2f} eiliad, {generated_tokens} tocyn, {generated_tokens / time_total:.2f} tocyn/eiliad")
return ""
base_model = load_model("./ALMA-Cymraeg-13B-0.1-4.0bpw-exl2")
settings = ExLlamaV2Sampler.Settings()
settings.temperature = 0.15 # newid fel bod angen e.e. 0.75
settings.top_k = 90 # newid fel bod angen e.e. 50
settings.top_p = 1.0 # ayyb
settings.token_repetition_penalty = 1.15 # ayyb
max_new_tokens = 2000 # ayyb
system_prompt = "Cyfieithwch y testun Saesneg canlynol i'r Gymraeg."
while True:
user_input = input("Saesneg: ")
prompt = f"{system_prompt}\n\n### Saesneg:\n{user_input}\n\n### Cymraeg:\n"
if DEBUG: print(f"{prompt}\n\n")
print("Cymraeg:")
response = generate_text(prompt, settings, max_new_tokens)
print("="*132)
``` |