Downloads · 30 days
7
23% of all-time downloads
yujackein/onereason-8b-lora-item32k-user75-rec50-worldclean1601-all1-lr2e4-r32a32-step323
onereason-8b-lora-item32k-user75-rec50-worldclean1601-all1-lr2e4-r32a32-step323 is a text generation model from yujackein. Use it when you need the model to write or continue text. It is set up for peft.
This is an experimental LoRA adapter for OpenOneRec/OneReason-8B-pretrain-competition, trained for the OneReason recommendation competition.
Downloads · 30 days
7
23% of all-time downloads
All-time downloads
31
Public
Repo size
365 MB
Likes
0
Public
Click a slice to open those files.
.safetensors349 MB · 96%
From the Hugging Face model README
This is an experimental LoRA adapter for
OpenOneRec/OneReason-8B-pretrain-competition,
trained for the OneReason recommendation competition.
This repository contains the intermediate checkpoint at step 323 from a 646-step, two-epoch-schedule run. It is the state after one packing pass, but it is not equivalent to a standalone one-epoch run because warmup and cosine decay were configured over all 646 steps.
| Category | Rows | Rendered tokens |
|---|---|---|
| R0 perception | 32,000 | 5,801,468 |
| R2 evolution | 24,636 | 119,130,968 |
| R3 recommendation | 24,134 | 34,445,219 |
| Clean C-Eval world data | 1,601 | 195,253 |
| Total | 82,371 | 159,572,908 |
All assistant loss weights were normalized to 1.0. The 32,768-token packing plan covers 99.1727% of rendered tokens in one safe pass.
r=32, alpha=32, dropout 0.05)q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj2e-4, cosine schedule, 3% warmupimport torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_id = "OpenOneRec/OneReason-8B-pretrain-competition"
adapter_id = "yujackein/onereason-8b-lora-item32k-user75-rec50-worldclean1601-all1-lr2e4-r32a32-step323"
tokenizer = AutoTokenizer.from_pretrained(adapter_id, trust_remote_code=True)
base_model = AutoModelForCausalLM.from_pretrained(
base_id,
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True,
)
model = PeftModel.from_pretrained(base_model, adapter_id)
Formal evaluation results have not yet been added. This checkpoint is kept separately from the final step-646 adapter for controlled comparison.