Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


baby-python-mistral-1L-tiny-lua-ft - GGUF
- Model creator: https://huggingface.co/nilq/
- Original model: https://huggingface.co/nilq/baby-python-mistral-1L-tiny-lua-ft/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [baby-python-mistral-1L-tiny-lua-ft.Q2_K.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q2_K.gguf) | Q2_K | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.IQ3_XS.gguf) | IQ3_XS | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.IQ3_S.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.IQ3_S.gguf) | IQ3_S | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q3_K_S.gguf) | Q3_K_S | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.IQ3_M.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.IQ3_M.gguf) | IQ3_M | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q3_K.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q3_K.gguf) | Q3_K | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q3_K_M.gguf) | Q3_K_M | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q3_K_L.gguf) | Q3_K_L | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.IQ4_XS.gguf) | IQ4_XS | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q4_0.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q4_0.gguf) | Q4_0 | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.IQ4_NL.gguf) | IQ4_NL | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q4_K_S.gguf) | Q4_K_S | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q4_K.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q4_K.gguf) | Q4_K | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q4_K_M.gguf) | Q4_K_M | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q4_1.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q4_1.gguf) | Q4_1 | 0.02GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q5_0.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q5_0.gguf) | Q5_0 | 0.03GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q5_K_S.gguf) | Q5_K_S | 0.03GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q5_K.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q5_K.gguf) | Q5_K | 0.03GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q5_K_M.gguf) | Q5_K_M | 0.03GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q5_1.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q5_1.gguf) | Q5_1 | 0.03GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q6_K.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q6_K.gguf) | Q6_K | 0.03GB |
| [baby-python-mistral-1L-tiny-lua-ft.Q8_0.gguf](https://huggingface.co/RichardErkhov/nilq_-_baby-python-mistral-1L-tiny-lua-ft-gguf/blob/main/baby-python-mistral-1L-tiny-lua-ft.Q8_0.gguf) | Q8_0 | 0.04GB |




Original model description:
---
base_model: nilq/baby-python-mistral-1L-tiny-base
tags:
- generated_from_trainer
datasets:
- nilq/small-lua-stack
metrics:
- accuracy
model-index:
- name: baby-python-mistral-1L-tiny-lua-ft
  results:
  - task:
      name: Causal Language Modeling
      type: text-generation
    dataset:
      name: nilq/small-lua-stack
      type: nilq/small-lua-stack
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.4940860736493237
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# baby-python-mistral-1L-tiny-lua-ft

This model is a fine-tuned version of [nilq/baby-python-mistral-1L-tiny-base](https://huggingface.co/nilq/baby-python-mistral-1L-tiny-base) on the nilq/small-lua-stack dataset. This is the Lua model in the paper [Tracking Universal Features Through Fine-Tuning and Model Merging](https://arxiv.org/abs/2410.12391).
It achieves the following results on the evaluation set:
- Loss: 2.4518
- Accuracy: 0.4941

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 1.0

### Training results



### Framework versions

- Transformers 4.38.1
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2