Downloads · 30 days
37
19% of all-time downloads
la-math-v5-fix2
j01001100/la-math-v5-fix2
la-math-v5-fix2 is a text generation model from j01001100. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
A Qwen3-4B fine-tuned with LoRA (3 rounds, 7.5k + 1.5k + 1.5k iters) into a linear-algebra specialist. Fused and requantized to a standalone MLX model (2.1 GB, 4-bit, group size 64) — loads with mlxlm.load(path), no a…
All-time downloads
191
Public
Parameters
4B
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 99%
Parameter types
How the weights are stored.
U324B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
la-math-v5-fix2 — Linear Algebra Specialist (MLX)
A Qwen3-4B fine-tuned with LoRA (3 rounds, 7.5k + 1.5k + 1.5k iters) into a
linear-algebra specialist. Fused and requantized to a standalone MLX model
(2.1 GB, 4-bit, group size 64) — loads with mlx_lm.load(path), no adapter file.
Benchmark
416 held-out linear algebra pairs, SymPy-verified grading, ~67% auto-graded computational core (rest are theory/concept items):
| Category | Base Qwen3-4B | This model |
|---|---|---|
| Overall graded | 67.8% | 73.5% |
| determinants | 79% | 88% |
| inverses | 70% | 82% |
| matrix ops | 93% | 100% |
| least squares | 40% | 70% |
| orthogonality | 89% | 100% |
| linear transforms | 75% | 88% |
| systems | 47% | 50% |
| eigen | 58% | 60% |
Training data
- 8,337 base pairs (SymPy-verified generated, textbook extraction from 11 books, hand-crafted) — zero benchmark test-set contamination
- +1,866 targeted gap-fill items from failure analysis (eigen char-poly procedure, LU, 4x4 determinants, 3x3 Gauss-Jordan, parametric systems, null-space bases)
Usage
from mlx_lm import load, generate
model, tokenizer = load("jason/la-math-v5-fix2")
prompt = tokenizer.apply_chat_template(
[{"role": "user", "content": "Compute the determinant of \\[ A = \\begin{bmatrix} 1 & 2 \\\\ 3 & 4 \\end{bmatrix} \\]"}],
tokenize=False, add_generation_prompt=True)
print(generate(model, tokenizer, prompt=prompt, max_tokens=1024))
Answers use LaTeX matrices (\begin{bmatrix}), show step-by-step work, and
finish with a boxed final answer (\boxed{...}).
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3
- License
- apache-2.0
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026