home_run_llm

S-ukhanov/home_run_llm

home_run_llm is a text generation model from S-ukhanov. Use it when you need the model to write or continue text. It is set up for transformers.

Downloads · 30 days

19% of all-time downloads

All-time downloads

Public

Parameters

1.2B

2.3 GB on disk

Likes

Public

Repo makeup

Click a slice to open those files.

.safetensors2.3 GB · 100%

From the Hugging Face model README

112 gb data with llama 1.2b model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "home_run_llm"

tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(model_name)

prompt = "The foggy streets of London in 1840 were" inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=100) print(tokenizer.decode(outputs[0], skip_special_tokens=True))


## Заметки по тренировке

- **Железо**: H100 SXM 
- **Время**: ~118 часов.
- **Денег ушло**: ~350 долларов
- **Лосс**: Упал с 10.79 до 3.35.