Downloads · 30 days
30
13% of all-time downloads
math-nothink-q8b-20260908
modrill/math-nothink-q8b-20260908
math-nothink-q8b-20260908 is a text generation model from modrill. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Public freeze of Math NoThink source expert θs for ICLR 2027 task-vector transfer. Not a chatbot. Endpoint is the score. Do not promote milestones.
All-time downloads
229
Public
Parameters
8.2B
17.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Sep 8, 2026
- Updated
- Sep 10, 2026
- SHA
- 541d4719
Try a prompt
Base models
Model card
From the Hugging Face model README
math-nothink-q8b-20260908
Public freeze of Math NoThink source expert θ_s for ICLR 2027 task-vector transfer. Not a chatbot. Endpoint is the score. Do not promote milestones.
run_id=math_six_arms_train_v3_eot_20260908. Replaces the private 20260902 src freeze for this v3 EOT recipe; does not overwrite nothink-src-*-20260902.
Score (Exact-240)
AIME24+25 × seeds 42–45, EvalScope reviews, n=240.
| Model | Official /240 |
|---|---|
| This endpoint | 58 |
| Same-run Base | 26 |
τ_s = θ_s − θ_0. θ_0 is Qwen/Qwen3-8B-Base rev 49e3418fbbbca6ecbdf9608b4d22e5a407081db4.
Identity
| Field | Value |
|---|---|
| Arm | Q8B-NOTHINK-EP-X |
| Updates / tokens | 165 / 10,788,766 |
| Recipe | LoRA r64/α128, TPU 65536, 2ep row-matched, seed 42, Qwen tail 151643 / O7B tail 100257, B-rows both sides [151643, 151667, 151668] |
Merged model.safetensors sha256 | 160d8b85fafdf43a3507a57f0bd39932e769c9bda3966881e9f69f815e427cfe |
| Endpoint adapter sha256 | 228a582aff6cdd81f63353f439dbfb86c22dc52b8fafc2ad57f3a212c35f7cf5 |
Root of merged weights is this repo. Endpoint LoRA is in adapter/. MERGE_RECEIPT.json is the merge audit.
Load
from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("modrill/math-nothink-q8b-20260908", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("modrill/math-nothink-q8b-20260908")
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Sep 8, 2026
- Updated
- Sep 10, 2026