README.md

---
base_model: BEE-spoke-data/TinyLlama-3T-1.1bee
datasets:
- BEE-spoke-data/bees-internal
inference: false
language:
- en
license: apache-2.0
metrics:
- accuracy
model_creator: BEE-spoke-data
model_name: TinyLlama-3T-1.1bee
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- bees
- bzz
- honey
- oprah winfrey
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
widget:
- example_title: Queen Excluder
  text: In beekeeping, the term "queen excluder" refers to
- example_title: Increasing Honey Production
  text: One way to encourage a honey bee colony to produce more honey is by
- example_title: Lifecycle of a Worker Bee
  text: The lifecycle of a worker bee consists of several stages, starting with
- example_title: Varroa Destructor
  text: Varroa destructor is a type of mite that
- example_title: Beekeeping PPE
  text: In the world of beekeeping, the acronym PPE stands for
- example_title: Robbing in Beekeeping
  text: The term "robbing" in beekeeping refers to the act of
- example_title: Role of Drone Bees
  text: 'Question: What''s the primary function of drone bees in a hive?

    Answer:'
- example_title: Honey Harvesting Device
  text: To harvest honey from a hive, beekeepers often use a device known as a
- example_title: Beekeeping Math Problem
  text: 'Problem: You have a hive that produces 60 pounds of honey per year. You decide
    to split the hive into two. Assuming each hive now produces at a 70% rate compared
    to before, how much honey will you get from both hives next year?

    To calculate'
- example_title: Swarming
  text: In beekeeping, "swarming" is the process where
---
# BEE-spoke-data/TinyLlama-3T-1.1bee-GGUF

Quantized GGUF model files for [TinyLlama-3T-1.1bee](https://huggingface.co/BEE-spoke-data/TinyLlama-3T-1.1bee) from [BEE-spoke-data](https://huggingface.co/BEE-spoke-data)


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [tinyllama-3t-1.1bee.fp16.gguf](https://huggingface.co/afrideva/TinyLlama-3T-1.1bee-GGUF/resolve/main/tinyllama-3t-1.1bee.fp16.gguf) | fp16 | 2.20 GB  |
| [tinyllama-3t-1.1bee.q2_k.gguf](https://huggingface.co/afrideva/TinyLlama-3T-1.1bee-GGUF/resolve/main/tinyllama-3t-1.1bee.q2_k.gguf) | q2_k | 432.13 MB  |
| [tinyllama-3t-1.1bee.q3_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-3T-1.1bee-GGUF/resolve/main/tinyllama-3t-1.1bee.q3_k_m.gguf) | q3_k_m | 548.40 MB  |
| [tinyllama-3t-1.1bee.q4_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-3T-1.1bee-GGUF/resolve/main/tinyllama-3t-1.1bee.q4_k_m.gguf) | q4_k_m | 667.81 MB  |
| [tinyllama-3t-1.1bee.q5_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-3T-1.1bee-GGUF/resolve/main/tinyllama-3t-1.1bee.q5_k_m.gguf) | q5_k_m | 782.04 MB  |
| [tinyllama-3t-1.1bee.q6_k.gguf](https://huggingface.co/afrideva/TinyLlama-3T-1.1bee-GGUF/resolve/main/tinyllama-3t-1.1bee.q6_k.gguf) | q6_k | 903.41 MB  |
| [tinyllama-3t-1.1bee.q8_0.gguf](https://huggingface.co/afrideva/TinyLlama-3T-1.1bee-GGUF/resolve/main/tinyllama-3t-1.1bee.q8_0.gguf) | q8_0 | 1.17 GB  |



## Original Model Card:
<!-- 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. -->

# TinyLlama-3T-1.1bee


![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/I6AfPId0Xo_vVobtkAP12.png)

A grand successor to [the original](https://huggingface.co/BEE-spoke-data/TinyLlama-1.1bee). This one has the following improvements:

- start from [finished 3T TinyLlama](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T)
- vastly improved and expanded SoTA beekeeping dataset


## Model description

This model is a fine-tuned version of TinyLlama-1.1b-3T on the BEE-spoke-data/bees-internal dataset.

It achieves the following results on the evaluation set:
- Loss: 2.1640
- Accuracy: 0.5406

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 13707
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.4432        | 0.19  | 50   | 2.3850          | 0.5033   |
| 2.3655        | 0.39  | 100  | 2.3124          | 0.5129   |
| 2.374         | 0.58  | 150  | 2.2588          | 0.5215   |
| 2.3558        | 0.78  | 200  | 2.2132          | 0.5291   |
| 2.2677        | 0.97  | 250  | 2.1828          | 0.5348   |
| 2.0701        | 1.17  | 300  | 2.1788          | 0.5373   |
| 2.0766        | 1.36  | 350  | 2.1673          | 0.5398   |
| 2.0669        | 1.56  | 400  | 2.1651          | 0.5402   |
| 2.0314        | 1.75  | 450  | 2.1641          | 0.5406   |
| 2.0281        | 1.95  | 500  | 2.1639          | 0.5407   |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.0
- Datasets 2.16.1
- Tokenizers 0.15.0