AI & ML interests

None defined yet.

EricFillion 
posted an update 14 days ago
view post
Post
159
Here's how to perform full-parameter fine-tuning for openai/gpt-oss-20b with a single H200 GPU. Only a few lines of code are needed using my new Python package called Eric Transformer.

Article: https://www.vennify.ai/gpt-oss-20b-fine-tune/

@vennify

pip install erictransformer

from erictransformer import EricChat, EricTrainArgs

eric_chat = EricChat(model_name="openai/gpt-oss-20b")

train_args = EricTrainArgs(optim="sgd")

# see the article to learn how to format the data 

eric_chat.train("train.jsonl",  eval_path="eval.jsonl", args=train_args)
  • 1 reply
·
EricFillion 
posted an update 16 days ago
view post
Post
162
Here’s how to perform retrieval-augmented (RAG) with two new open-source Python packages I just released. I included a full article below that provides a step-by-step guide on how to build a vector database with this wikimedia/wikipedia dump and use it to perform RAG with openai/gpt-oss-20b.

FULL ARTICLE: https://www.vennify.ai/vector-eric-search/

vennify


pip install erictransformer ericsearch

import json
from ericsearch import EricSearch
from erictransformer import EricChat

eric_search = EricSearch()

with open("data.jsonl", "w", encoding="utf-8") as f:
    sample_case = {"text": "This contains example data. It should contain at least two sentences."}
    f.write(json.dumps(sample_case)+ "\n")

eric_search.train("data.jsonl")

eric_search = EricSearch(data_name="eric_search/")

eric_chat = EricChat(model_name="openai/gpt-oss-20b", eric_search=eric_search)

result = eric_chat("Tell me about artificial intelligence ")

print(result.text)
  • 1 reply
·
EricFillion 
posted an update about 1 month ago
EricFillion 
posted an update about 1 month ago
EricFillion 
posted an update about 1 month ago
EricFillion 
posted an update about 2 months ago
view post
Post
274
I just launched three new open-source Python packages!

Eric Chat: Run LLMs locally, securely and offline on macOS through a GUI. Quantized models up to 120 billion parameters are supported.

Eric Transformer: Pre-train, fine-tune and perform inference with LLMs.

Eric Search: A vector database with built-in text ranking that scales to millions of documents while remaining fast. Integrates easily with Eric Transformer to enable RAG.

https://youtu.be/hgP4eBVfmFM