afrideva commited on
Commit
2ce208b
1 Parent(s): 52fd3c5

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +77 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BEE-spoke-data/smol_llama-101M-midjourney-messages
3
+ datasets:
4
+ - pszemraj/midjourney-messages-cleaned
5
+ inference: false
6
+ license: apache-2.0
7
+ metrics:
8
+ - accuracy
9
+ model_creator: BEE-spoke-data
10
+ model_name: smol_llama-101M-midjourney-messages
11
+ pipeline_tag: text-generation
12
+ quantized_by: afrideva
13
+ tags:
14
+ - generated_from_trainer
15
+ - gguf
16
+ - ggml
17
+ - quantized
18
+ - q2_k
19
+ - q3_k_m
20
+ - q4_k_m
21
+ - q5_k_m
22
+ - q6_k
23
+ - q8_0
24
+ widget:
25
+ - example_title: avocado chair
26
+ text: avocado chair
27
+ - example_title: potato
28
+ text: A mysterious potato
29
+ ---
30
+ # BEE-spoke-data/smol_llama-101M-midjourney-messages-GGUF
31
+
32
+ Quantized GGUF model files for [smol_llama-101M-midjourney-messages](https://huggingface.co/BEE-spoke-data/smol_llama-101M-midjourney-messages) from [BEE-spoke-data](https://huggingface.co/BEE-spoke-data)
33
+
34
+
35
+ | Name | Quant method | Size |
36
+ | ---- | ---- | ---- |
37
+ | [smol_llama-101m-midjourney-messages.fp16.gguf](https://huggingface.co/afrideva/smol_llama-101M-midjourney-messages-GGUF/resolve/main/smol_llama-101m-midjourney-messages.fp16.gguf) | fp16 | 203.28 MB |
38
+ | [smol_llama-101m-midjourney-messages.q2_k.gguf](https://huggingface.co/afrideva/smol_llama-101M-midjourney-messages-GGUF/resolve/main/smol_llama-101m-midjourney-messages.q2_k.gguf) | q2_k | 50.93 MB |
39
+ | [smol_llama-101m-midjourney-messages.q3_k_m.gguf](https://huggingface.co/afrideva/smol_llama-101M-midjourney-messages-GGUF/resolve/main/smol_llama-101m-midjourney-messages.q3_k_m.gguf) | q3_k_m | 57.06 MB |
40
+ | [smol_llama-101m-midjourney-messages.q4_k_m.gguf](https://huggingface.co/afrideva/smol_llama-101M-midjourney-messages-GGUF/resolve/main/smol_llama-101m-midjourney-messages.q4_k_m.gguf) | q4_k_m | 65.40 MB |
41
+ | [smol_llama-101m-midjourney-messages.q5_k_m.gguf](https://huggingface.co/afrideva/smol_llama-101M-midjourney-messages-GGUF/resolve/main/smol_llama-101m-midjourney-messages.q5_k_m.gguf) | q5_k_m | 74.34 MB |
42
+ | [smol_llama-101m-midjourney-messages.q6_k.gguf](https://huggingface.co/afrideva/smol_llama-101M-midjourney-messages-GGUF/resolve/main/smol_llama-101m-midjourney-messages.q6_k.gguf) | q6_k | 83.83 MB |
43
+ | [smol_llama-101m-midjourney-messages.q8_0.gguf](https://huggingface.co/afrideva/smol_llama-101M-midjourney-messages-GGUF/resolve/main/smol_llama-101m-midjourney-messages.q8_0.gguf) | q8_0 | 108.35 MB |
44
+
45
+
46
+
47
+ ## Original Model Card:
48
+ # smol_llama-101M-midjourney-messages
49
+
50
+ Given a 'partial prompt' for a text2image model, this generates additional relevant text to include for a full prompt.
51
+
52
+
53
+ ![example](https://i.imgur.com/f2hzgq1.png)
54
+
55
+ ## Model description
56
+
57
+ This model is a fine-tuned version of [BEE-spoke-data/smol_llama-101M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA) on the `pszemraj/midjourney-messages-cleaned` dataset.
58
+ It achieves the following results on the evaluation set:
59
+ - Loss: 2.8431
60
+ - Accuracy: 0.4682
61
+
62
+
63
+ ## Training procedure
64
+
65
+ ### Training hyperparameters
66
+
67
+ The following hyperparameters were used during training:
68
+ - learning_rate: 0.00025
69
+ - train_batch_size: 4
70
+ - eval_batch_size: 4
71
+ - seed: 17056
72
+ - gradient_accumulation_steps: 16
73
+ - total_train_batch_size: 64
74
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
75
+ - lr_scheduler_type: inverse_sqrt
76
+ - lr_scheduler_warmup_ratio: 0.05
77
+ - num_epochs: 1.0