Downloads · 30 days
52
22% of all-time downloads
math-nothink-q4b-20260908
modrill/math-nothink-q4b-20260908
math-nothink-q4b-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
239
Public
Parameters
4.4B
9.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.4 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
- 5ed3c44b
Try a prompt
Base models
Model card
From the Hugging Face model README
math-nothink-q4b-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 | 49 |
| Same-run Base | 22 |
τ_s = θ_s − θ_0. θ_0 is Qwen/Qwen3-4B-Base rev 906bfd4b4dc7f14ee4320094d8b41684abff8539.
Identity
| Field | Value |
|---|---|
| Arm | Q4B-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 | f58598701c77f8b82d8ac31abf35689c1cf097dde8d9652bf446a8fa4b2e1465 |
| Endpoint adapter sha256 | b6e1a5fe40eb2407880953e746ce4788af62034ee395918c4fee179c8770bf54 |
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-q4b-20260908", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("modrill/math-nothink-q4b-20260908")
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Sep 8, 2026
- Updated
- Sep 10, 2026