Update README.md
Browse files
README.md
CHANGED
|
@@ -5,15 +5,56 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
# smol_llama-220M-
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [BEE-spoke-data/smol_llama-220M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-220M-GQA) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
|
@@ -79,4 +120,4 @@ The following hyperparameters were used during training:
|
|
| 79 |
- Transformers 4.36.2
|
| 80 |
- Pytorch 2.1.0
|
| 81 |
- Datasets 2.16.1
|
| 82 |
-
- Tokenizers 0.15.0
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
+
inference:
|
| 9 |
+
parameters:
|
| 10 |
+
max_new_tokens: 64
|
| 11 |
+
do_sample: true
|
| 12 |
+
renormalize_logits: true
|
| 13 |
+
repetition_penalty: 1.05
|
| 14 |
+
no_repeat_ngram_size: 6
|
| 15 |
+
temperature: 0.9
|
| 16 |
+
top_p: 0.95
|
| 17 |
+
epsilon_cutoff: 0.0008
|
| 18 |
+
widget:
|
| 19 |
+
- text: In beekeeping, the term "queen excluder" refers to
|
| 20 |
+
example_title: Queen Excluder
|
| 21 |
+
- text: One way to encourage a honey bee colony to produce more honey is by
|
| 22 |
+
example_title: Increasing Honey Production
|
| 23 |
+
- text: The lifecycle of a worker bee consists of several stages, starting with
|
| 24 |
+
example_title: Lifecycle of a Worker Bee
|
| 25 |
+
- text: Varroa destructor is a type of mite that
|
| 26 |
+
example_title: Varroa Destructor
|
| 27 |
+
- text: In the world of beekeeping, the acronym PPE stands for
|
| 28 |
+
example_title: Beekeeping PPE
|
| 29 |
+
- text: The term "robbing" in beekeeping refers to the act of
|
| 30 |
+
example_title: Robbing in Beekeeping
|
| 31 |
+
- text: |-
|
| 32 |
+
Question: What's the primary function of drone bees in a hive?
|
| 33 |
+
Answer:
|
| 34 |
+
example_title: Role of Drone Bees
|
| 35 |
+
- text: To harvest honey from a hive, beekeepers often use a device known as a
|
| 36 |
+
example_title: Honey Harvesting Device
|
| 37 |
+
- text: >-
|
| 38 |
+
Problem: You have a hive that produces 60 pounds of honey per year. You
|
| 39 |
+
decide to split the hive into two. Assuming each hive now produces at a 70%
|
| 40 |
+
rate compared to before, how much honey will you get from both hives next
|
| 41 |
+
year?
|
| 42 |
+
|
| 43 |
+
To calculate
|
| 44 |
+
example_title: Beekeeping Math Problem
|
| 45 |
+
- text: In beekeeping, "swarming" is the process where
|
| 46 |
+
example_title: Swarming
|
| 47 |
+
pipeline_tag: text-generation
|
| 48 |
+
datasets:
|
| 49 |
+
- BEE-spoke-data/bees-internal
|
| 50 |
+
language:
|
| 51 |
+
- en
|
| 52 |
---
|
| 53 |
|
| 54 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 55 |
should probably proofread and complete it, then remove this comment. -->
|
| 56 |
|
| 57 |
+
# smol_llama-220M-bees-internal
|
| 58 |
|
| 59 |
This model is a fine-tuned version of [BEE-spoke-data/smol_llama-220M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-220M-GQA) on the None dataset.
|
| 60 |
It achieves the following results on the evaluation set:
|
|
|
|
| 120 |
- Transformers 4.36.2
|
| 121 |
- Pytorch 2.1.0
|
| 122 |
- Datasets 2.16.1
|
| 123 |
+
- Tokenizers 0.15.0
|