afrideva commited on
Commit
92f94be
1 Parent(s): c58916d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +141 -0
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BEE-spoke-data/smol_llama-220M-bees-internal
3
+ datasets:
4
+ - BEE-spoke-data/bees-internal
5
+ inference: false
6
+ language:
7
+ - en
8
+ license: apache-2.0
9
+ metrics:
10
+ - accuracy
11
+ model_creator: BEE-spoke-data
12
+ model_name: smol_llama-220M-bees-internal
13
+ pipeline_tag: text-generation
14
+ quantized_by: afrideva
15
+ tags:
16
+ - generated_from_trainer
17
+ - gguf
18
+ - ggml
19
+ - quantized
20
+ - q2_k
21
+ - q3_k_m
22
+ - q4_k_m
23
+ - q5_k_m
24
+ - q6_k
25
+ - q8_0
26
+ widget:
27
+ - example_title: Queen Excluder
28
+ text: In beekeeping, the term "queen excluder" refers to
29
+ - example_title: Increasing Honey Production
30
+ text: One way to encourage a honey bee colony to produce more honey is by
31
+ - example_title: Lifecycle of a Worker Bee
32
+ text: The lifecycle of a worker bee consists of several stages, starting with
33
+ - example_title: Varroa Destructor
34
+ text: Varroa destructor is a type of mite that
35
+ - example_title: Beekeeping PPE
36
+ text: In the world of beekeeping, the acronym PPE stands for
37
+ - example_title: Robbing in Beekeeping
38
+ text: The term "robbing" in beekeeping refers to the act of
39
+ - example_title: Role of Drone Bees
40
+ text: 'Question: What''s the primary function of drone bees in a hive?
41
+
42
+ Answer:'
43
+ - example_title: Honey Harvesting Device
44
+ text: To harvest honey from a hive, beekeepers often use a device known as a
45
+ - example_title: Beekeeping Math Problem
46
+ text: 'Problem: You have a hive that produces 60 pounds of honey per year. You decide
47
+ to split the hive into two. Assuming each hive now produces at a 70% rate compared
48
+ to before, how much honey will you get from both hives next year?
49
+
50
+ To calculate'
51
+ - example_title: Swarming
52
+ text: In beekeeping, "swarming" is the process where
53
+ ---
54
+ # BEE-spoke-data/smol_llama-220M-bees-internal-GGUF
55
+
56
+ Quantized GGUF model files for [smol_llama-220M-bees-internal](https://huggingface.co/BEE-spoke-data/smol_llama-220M-bees-internal) from [BEE-spoke-data](https://huggingface.co/BEE-spoke-data)
57
+
58
+
59
+ | Name | Quant method | Size |
60
+ | ---- | ---- | ---- |
61
+ | [smol_llama-220m-bees-internal.fp16.gguf](https://huggingface.co/afrideva/smol_llama-220M-bees-internal-GGUF/resolve/main/smol_llama-220m-bees-internal.fp16.gguf) | fp16 | 436.50 MB |
62
+ | [smol_llama-220m-bees-internal.q2_k.gguf](https://huggingface.co/afrideva/smol_llama-220M-bees-internal-GGUF/resolve/main/smol_llama-220m-bees-internal.q2_k.gguf) | q2_k | 94.43 MB |
63
+ | [smol_llama-220m-bees-internal.q3_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-bees-internal-GGUF/resolve/main/smol_llama-220m-bees-internal.q3_k_m.gguf) | q3_k_m | 114.65 MB |
64
+ | [smol_llama-220m-bees-internal.q4_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-bees-internal-GGUF/resolve/main/smol_llama-220m-bees-internal.q4_k_m.gguf) | q4_k_m | 137.58 MB |
65
+ | [smol_llama-220m-bees-internal.q5_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-bees-internal-GGUF/resolve/main/smol_llama-220m-bees-internal.q5_k_m.gguf) | q5_k_m | 157.91 MB |
66
+ | [smol_llama-220m-bees-internal.q6_k.gguf](https://huggingface.co/afrideva/smol_llama-220M-bees-internal-GGUF/resolve/main/smol_llama-220m-bees-internal.q6_k.gguf) | q6_k | 179.52 MB |
67
+ | [smol_llama-220m-bees-internal.q8_0.gguf](https://huggingface.co/afrideva/smol_llama-220M-bees-internal-GGUF/resolve/main/smol_llama-220m-bees-internal.q8_0.gguf) | q8_0 | 232.28 MB |
68
+
69
+
70
+
71
+ ## Original Model Card:
72
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
73
+ should probably proofread and complete it, then remove this comment. -->
74
+
75
+ # smol_llama-220M-bees-internal
76
+
77
+ 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.
78
+ It achieves the following results on the evaluation set:
79
+ - Loss: 2.6892
80
+ - Accuracy: 0.4610
81
+
82
+ ## Model description
83
+
84
+ More information needed
85
+
86
+ ## Intended uses & limitations
87
+
88
+ More information needed
89
+
90
+ ## Training and evaluation data
91
+
92
+ More information needed
93
+
94
+ ## Training procedure
95
+
96
+ ### Training hyperparameters
97
+
98
+ The following hyperparameters were used during training:
99
+ - learning_rate: 0.0001
100
+ - train_batch_size: 4
101
+ - eval_batch_size: 2
102
+ - seed: 27634
103
+ - gradient_accumulation_steps: 8
104
+ - total_train_batch_size: 32
105
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
106
+ - lr_scheduler_type: cosine
107
+ - lr_scheduler_warmup_ratio: 0.05
108
+ - num_epochs: 2.0
109
+
110
+ ### Training results
111
+
112
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
113
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
114
+ | 3.0959 | 0.1 | 50 | 2.9671 | 0.4245 |
115
+ | 2.9975 | 0.19 | 100 | 2.8691 | 0.4371 |
116
+ | 2.8938 | 0.29 | 150 | 2.8271 | 0.4419 |
117
+ | 2.9027 | 0.39 | 200 | 2.7973 | 0.4457 |
118
+ | 2.8983 | 0.49 | 250 | 2.7719 | 0.4489 |
119
+ | 2.8789 | 0.58 | 300 | 2.7519 | 0.4515 |
120
+ | 2.8672 | 0.68 | 350 | 2.7366 | 0.4535 |
121
+ | 2.8369 | 0.78 | 400 | 2.7230 | 0.4558 |
122
+ | 2.8271 | 0.88 | 450 | 2.7118 | 0.4569 |
123
+ | 2.7775 | 0.97 | 500 | 2.7034 | 0.4587 |
124
+ | 2.671 | 1.07 | 550 | 2.6996 | 0.4592 |
125
+ | 2.695 | 1.17 | 600 | 2.6965 | 0.4598 |
126
+ | 2.6962 | 1.27 | 650 | 2.6934 | 0.4601 |
127
+ | 2.6034 | 1.36 | 700 | 2.6916 | 0.4605 |
128
+ | 2.716 | 1.46 | 750 | 2.6901 | 0.4609 |
129
+ | 2.6968 | 1.56 | 800 | 2.6896 | 0.4608 |
130
+ | 2.6626 | 1.66 | 850 | 2.6893 | 0.4609 |
131
+ | 2.6881 | 1.75 | 900 | 2.6891 | 0.4610 |
132
+ | 2.7339 | 1.85 | 950 | 2.6891 | 0.4610 |
133
+ | 2.6729 | 1.95 | 1000 | 2.6892 | 0.4610 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - Transformers 4.36.2
139
+ - Pytorch 2.1.0
140
+ - Datasets 2.16.1
141
+ - Tokenizers 0.15.0