Downloads · 30 days
6
13% of all-time downloads
mh-v1b-math-4b-sym-sp2
hyunseoki/mh-v1b-math-4b-sym-sp2
mh-v1b-math-4b-sym-sp2 is a text generation model from hyunseoki. 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.
Part of the Meta-Harness v1b study — co-evolution GRPO (verl) where a shared-weight policy plays two roles: TA (grader / solver, single-turn) and Proposer (harness/scaffold editor via multi-turn SEARCH/REPLACE). Quest…
All-time downloads
47
Public
Parameters
4.2B
8.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_5_text
- Access
- Public
- Created
- Jul 19, 2026
- Updated
- Jul 19, 2026
- SHA
- c7441284
Try a prompt
Model card
From the Hugging Face model README
mh-v1b-math-4b-sym-sp2
Part of the Meta-Harness v1b study — co-evolution GRPO (verl) where a shared-weight policy plays two roles: TA (grader / solver, single-turn) and Proposer (harness/scaffold editor via multi-turn SEARCH/REPLACE). Question: does co-evolving the policy and its evaluation harness help, and through which lever (policy vs scaffold)?
| Domain | Math (symbolic) |
| Architecture | Qwen3_5ForCausalLM — 32 layers, hidden 2560 |
| Precision | bf16 (merged from FSDP via verl.model_merger) |
| Notes | No-reclaim, sequence-parallel=2 long-context, symbolic math. (Qwen3.5-4B) |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("hyunseoki/mh-v1b-math-4b-sym-sp2")
model = AutoModelForCausalLM.from_pretrained("hyunseoki/mh-v1b-math-4b-sym-sp2", torch_dtype="bfloat16")
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_5_text
- License
- apache-2.0
- Created
- Jul 19, 2026
- Updated
- Jul 19, 2026