Downloads · 30 days
2
11% of all-time downloads
woojin93/qwen0_5b-gsm8k-lora-20251101-0949
qwen0_5b-gsm8k-lora-20251101-0949 is a machine learning model from woojin93. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Base: Qwen/Qwen2.5-0.5B Training: 1 epoch, bs=1, gradacc=8, lr=1e-4, warmup=0.03 Max length: 896 Data size: train≈0, eval≈0 Eval: EleutherAI lm-eval-harness (fewshot=5, limit=50, hf backend)
Downloads · 30 days
2
11% of all-time downloads
All-time downloads
19
Public
Parameters
494M
2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2 GB · 99%
From the Hugging Face model README
Base: Qwen/Qwen2.5-0.5B
Training: 1 epoch, bs=1, grad_acc=8, lr=1e-4, warmup=0.03
Max length: 896
Data size: train≈0, eval≈0
Eval: EleutherAI lm-eval-harness (fewshot=5, limit=50, hf backend)
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tok = AutoTokenizer.from_pretrained("woojin93/qwen0_5b-gsm8k-lora-20251101-0949")
m = AutoModelForCausalLM.from_pretrained("woojin93/qwen0_5b-gsm8k-lora-20251101-0949", torch_dtype="auto", device_map="auto")
prompt = "<|im_start|>user\nSolve: 12 + 35 = ?\n<|im_end|>\n<|im_start|>assistant\n"
x = tok(prompt, return_tensors='pt').to(m.device)
y = m.generate(**x, max_new_tokens=64)
print(tok.decode(y[0], skip_special_tokens=True))