Telegram Group & Telegram Channel
🚀Только что выпущено новое семейство моделей генерации кода Salesforce (SFR-Embedding-Code), занявшее 1-е место на бенчмарке CoIR!

Модель доступна в в 2-х размерах: 2B, 400M.

Основные характеристики:
1️⃣ Модель 2B: Занимает первое место в CoIR.
2️⃣ Модель 400M: демонстрирует лучшие показатели среди моделей на 0,5B параметров.
3️⃣ Поддерживает 12 языков программирования, Python, Java, C++, JavaScript, C# и другие!

Пример Запуска:

import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModel

# Each query needs to be accompanied by an corresponding instruction describing the task.
query_instruction_example = "Given Code or Text, retrieval relevant content"
queries = [
"how to implement quick sort in Python?"
]

# No instruction needed for retrieval passages
passages = [
"def quick_sort(arr):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)",
"def bubble_sort(arr):\n n = len(arr)\n for i in range(n):\n for j in range(0, n-i-1):\n if arr[j] > arr[j+1]:\n arr[j], arr[j+1] = arr[j+1], arr[j]\n return arr"
]

# load model with tokenizer
model = AutoModel.from_pretrained('Salesforce/SFR-Embedding-Code-2B_R', trust_remote_code=True)

# get the embeddings
max_length = 32768
query_embeddings = model.encode_queries(queries, instruction=query_instruction_example, max_length=max_length)
passage_embeddings = model.encode_corpus(passages, max_length=max_length)

# normalize embeddings
query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
passage_embeddings = F.normalize(passage_embeddings, p=2, dim=1)

scores = (query_embeddings @ passage_embeddings.T) * 100
print(scores.tolist())



Документация
Модель 400M
Модель 2B


📌Лицензирование моделей: CC-BY-NC-SA-4.0 License.

@ai_machinelearning_big_data


#CodeAI #MLResearch #SOTA #OpenScience #code #llm #ml



group-telegram.com/ai_machinelearning_big_data/6580
Create:
Last Update:

🚀Только что выпущено новое семейство моделей генерации кода Salesforce (SFR-Embedding-Code), занявшее 1-е место на бенчмарке CoIR!

Модель доступна в в 2-х размерах: 2B, 400M.

Основные характеристики:
1️⃣ Модель 2B: Занимает первое место в CoIR.
2️⃣ Модель 400M: демонстрирует лучшие показатели среди моделей на 0,5B параметров.
3️⃣ Поддерживает 12 языков программирования, Python, Java, C++, JavaScript, C# и другие!

Пример Запуска:

import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModel

# Each query needs to be accompanied by an corresponding instruction describing the task.
query_instruction_example = "Given Code or Text, retrieval relevant content"
queries = [
"how to implement quick sort in Python?"
]

# No instruction needed for retrieval passages
passages = [
"def quick_sort(arr):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)",
"def bubble_sort(arr):\n n = len(arr)\n for i in range(n):\n for j in range(0, n-i-1):\n if arr[j] > arr[j+1]:\n arr[j], arr[j+1] = arr[j+1], arr[j]\n return arr"
]

# load model with tokenizer
model = AutoModel.from_pretrained('Salesforce/SFR-Embedding-Code-2B_R', trust_remote_code=True)

# get the embeddings
max_length = 32768
query_embeddings = model.encode_queries(queries, instruction=query_instruction_example, max_length=max_length)
passage_embeddings = model.encode_corpus(passages, max_length=max_length)

# normalize embeddings
query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
passage_embeddings = F.normalize(passage_embeddings, p=2, dim=1)

scores = (query_embeddings @ passage_embeddings.T) * 100
print(scores.tolist())



Документация
Модель 400M
Модель 2B


📌Лицензирование моделей: CC-BY-NC-SA-4.0 License.

@ai_machinelearning_big_data


#CodeAI #MLResearch #SOTA #OpenScience #code #llm #ml

BY Machinelearning











Share with your friend now:
group-telegram.com/ai_machinelearning_big_data/6580

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

Individual messages can be fully encrypted. But the user has to turn on that function. It's not automatic, as it is on Signal and WhatsApp. "Your messages about the movement of the enemy through the official chatbot … bring new trophies every day," the government agency tweeted. In the United States, Telegram's lower public profile has helped it mostly avoid high level scrutiny from Congress, but it has not gone unnoticed. Under the Sebi Act, the regulator has the power to carry out search and seizure of books, registers, documents including electronics and digital devices from any person associated with the securities market. The S&P 500 fell 1.3% to 4,204.36, and the Dow Jones Industrial Average was down 0.7% to 32,943.33. The Dow posted a fifth straight weekly loss — its longest losing streak since 2019. The Nasdaq Composite tumbled 2.2% to 12,843.81. Though all three indexes opened in the green, stocks took a turn after a new report showed U.S. consumer sentiment deteriorated more than expected in early March as consumers' inflation expectations soared to the highest since 1981.
from in


Telegram Machinelearning
FROM American