Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

qwen25-1.5b-gsm8k-reinforce-step425 – AI Model by ahmed-3m | AlphaNeural AI

You can deploy this model and start earning money today!

ahmed-3m/
qwen25-1.5b-gsm8k-reinforce-step425

like

0

text-generation

Qwen/Qwen2.5-1.5B-Instruct

Views

No views yet

Best GSM8K checkpoint: step 425

LoRA adapter for Qwen/Qwen2.5-1.5B-Instruct trained in a self-training math reasoning experiment on GSM8K using a LaSeR-lite REINFORCE setup.

Results

True reproducible exact-match evaluation with deterministic greedy decoding and required #### <integer> answer extraction:

20% GSM8K / 8% SVAMP
Evaluation subsets: GSM8K test first 100 examples, SVAMP first 50 examples
Decoding: greedy, max_new_tokens=256

Training-time metrics from the original run used non-reseeded random subsets and should not be used as final accuracy claims.

Intended Use

Use when GSM8K in-distribution accuracy matters most. This is a research checkpoint, not a production math solver.

Loading

python

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base_id = "Qwen/Qwen2.5-1.5B-Instruct"
adapter_id = "ahmed-3m/qwen25-1.5b-gsm8k-reinforce-step425"

tok = AutoTokenizer.from_pretrained(base_id)
base = AutoModelForCausalLM.from_pretrained(
    base_id,
    torch_dtype=torch.float32,
    attn_implementation="sdpa",
    device_map="auto",
)
model = PeftModel.from_pretrained(base, adapter_id)
model.eval()

Training Context

Base model: Qwen2.5-1.5B-Instruct
Adapter: LoRA r=16 over projection modules
Task: GSM8K math reasoning
Hardware used: Tesla P40; fp16 + SDPA constraints