Downloads · 30 days
118
10% of all-time downloads
Financial-v1-2B-GGUF
theprint/Financial-v1-2B-GGUF
Financial-v1-2B-GGUF is a machine learning model from theprint. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
A fine-tuned version of unsloth/Qwen3.5-2B trained on PersonalFinance Extended data using Auto-SFT — an automated hyperparameter search and supervised fine-tuning pipeline.
All-time downloads
1.2K
Public
Repo size
20.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf20.7 GB · 100%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026
- SHA
- d616e7de
Base models
Model card
From the Hugging Face model README
Financial-v1-2B (GGUF)
A fine-tuned version of unsloth/Qwen3.5-2B trained on PersonalFinance Extended data using Auto-SFT — an automated hyperparameter search and supervised fine-tuning pipeline.
The base model was adapted to follow the style and content of the PersonalFinance Extended dataset. Expect improved performance on tasks similar to those represented in the training data.
Model Details
| Property | Value |
|---|---|
| Base model | unsloth/Qwen3.5-2B |
| Training data | data/PersonalFinance-Extended.json |
| Fine-tuning epochs | 1 |
| Fine-tuning date | 2026-07-26 |
| Fine-tuning method | LoRA (merged to full 16-bit) |
Training Hyperparameters
LoRA
| Parameter | Value |
|---|---|
r | 64 |
alpha | 128 |
dropout | 0.02 |
target_modules | ['q_proj', 'v_proj'] |
Training
| Parameter | Value |
|---|---|
learning_rate | 1e-05 |
batch_size | 1 |
gradient_accumulation_steps | 8 |
warmup_ratio | 0.1 |
max_seq_length | 512 |
quantization | none |
GGUF Files
These quantized GGUF files can be used directly with llama.cpp, Ollama, LM Studio, and other compatible runtimes.
| File | Description |
|---|---|
Financial-v1-2B-GGUF-BF16.gguf | BF16 |
Financial-v1-2B-GGUF-Q8_0.gguf | 8-bit — near-lossless, larger file |
Financial-v1-2B-GGUF-Q6_K.gguf | 6-bit — high quality |
Financial-v1-2B-GGUF-Q5_K_M.gguf | 5-bit medium — good quality/size balance |
Financial-v1-2B-GGUF-Q5_K_S.gguf | Q5_K_S |
Financial-v1-2B-GGUF-Q4_K_M.gguf | 4-bit medium — recommended for most use cases |
Financial-v1-2B-GGUF-Q4_K_S.gguf | Q4_K_S |
Financial-v1-2B-GGUF-Q3_K_L.gguf | Q3_K_L |
Financial-v1-2B-GGUF-Q3_K_M.gguf | Q3_K_M |
Financial-v1-2B-GGUF-Q3_K_S.gguf | Q3_K_S |
Financial-v1-2B-GGUF-Q2_K.gguf | 2-bit — smallest size, lowest quality |
Financial-v1-2B-GGUF-IQ4_XS.gguf | IQ4_XS |
Financial-v1-2B-GGUF-IQ4_NL.gguf | IQ4_NL |
Financial-v1-2B-GGUF-TQ2_0.gguf | TQ2_0 |
Generated by Auto-SFT
- Library
- transformers
- Languages
- en
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026