Hugging Face's logo

RichardErkhov
/
Isotonic_-_gpt2-context_generator-gguf

GGUF
Model card Files
xet
Community
RichardErkhov commited on
Commit
977eebb
·
verified ·
1 Parent(s): a1a84ae

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +100 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ gpt2-context_generator - GGUF
11
+ - Model creator: https://huggingface.co/Isotonic/
12
+ - Original model: https://huggingface.co/Isotonic/gpt2-context_generator/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [gpt2-context_generator.Q2_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q2_K.gguf) | Q2_K | 0.08GB |
18
+ | [gpt2-context_generator.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.IQ3_XS.gguf) | IQ3_XS | 0.08GB |
19
+ | [gpt2-context_generator.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.IQ3_S.gguf) | IQ3_S | 0.08GB |
20
+ | [gpt2-context_generator.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q3_K_S.gguf) | Q3_K_S | 0.08GB |
21
+ | [gpt2-context_generator.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.IQ3_M.gguf) | IQ3_M | 0.09GB |
22
+ | [gpt2-context_generator.Q3_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q3_K.gguf) | Q3_K | 0.09GB |
23
+ | [gpt2-context_generator.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q3_K_M.gguf) | Q3_K_M | 0.09GB |
24
+ | [gpt2-context_generator.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q3_K_L.gguf) | Q3_K_L | 0.1GB |
25
+ | [gpt2-context_generator.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.IQ4_XS.gguf) | IQ4_XS | 0.1GB |
26
+ | [gpt2-context_generator.Q4_0.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q4_0.gguf) | Q4_0 | 0.1GB |
27
+ | [gpt2-context_generator.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.IQ4_NL.gguf) | IQ4_NL | 0.1GB |
28
+ | [gpt2-context_generator.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q4_K_S.gguf) | Q4_K_S | 0.1GB |
29
+ | [gpt2-context_generator.Q4_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q4_K.gguf) | Q4_K | 0.11GB |
30
+ | [gpt2-context_generator.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q4_K_M.gguf) | Q4_K_M | 0.11GB |
31
+ | [gpt2-context_generator.Q4_1.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q4_1.gguf) | Q4_1 | 0.11GB |
32
+ | [gpt2-context_generator.Q5_0.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q5_0.gguf) | Q5_0 | 0.11GB |
33
+ | [gpt2-context_generator.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q5_K_S.gguf) | Q5_K_S | 0.11GB |
34
+ | [gpt2-context_generator.Q5_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q5_K.gguf) | Q5_K | 0.12GB |
35
+ | [gpt2-context_generator.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q5_K_M.gguf) | Q5_K_M | 0.12GB |
36
+ | [gpt2-context_generator.Q5_1.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q5_1.gguf) | Q5_1 | 0.12GB |
37
+ | [gpt2-context_generator.Q6_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q6_K.gguf) | Q6_K | 0.13GB |
38
+ | [gpt2-context_generator.Q8_0.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_gpt2-context_generator-gguf/blob/main/gpt2-context_generator.Q8_0.gguf) | Q8_0 | 0.17GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ language:
46
+ - en
47
+ license: cc-by-sa-4.0
48
+ tags:
49
+ - generated_from_trainer
50
+ - text-generation-inference
51
+ datasets:
52
+ - Non-Residual-Prompting/C2Gen
53
+ pipeline_tag: text-generation
54
+ base_model: gpt2
55
+ model-index:
56
+ - name: gpt2-commongen-finetuned
57
+ results: []
58
+ ---
59
+
60
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
61
+ should probably proofread and complete it, then remove this comment. -->
62
+
63
+ # gpt2-context_generator
64
+
65
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2/) on [Non-Residual-Prompting/C2Gen](https://huggingface.co/datasets/Non-Residual-Prompting/C2Gen) dataset.
66
+
67
+ ## Model description
68
+
69
+ More information needed
70
+
71
+ ## Intended uses & limitations
72
+
73
+ - Check config.json for prompt template and sampling strategy.
74
+
75
+ ### Dataset Summary
76
+
77
+ CommonGen [Lin et al., 2020](https://arxiv.org/abs/1911.03705) is a dataset for the constrained text generation task of word inclusion. But the task does not allow to include context. Therefore, to complement CommonGen, we provide an extended test set C2Gen [Carlsson et al., 2022](https://aclanthology.org/2022.acl-long.471) where an additional context is provided for each set of target words. The task is therefore reformulated to both generate commonsensical text which include the given words, and also have the generated text adhere to the given context.
78
+
79
+ ## Training procedure
80
+ - Causal Language Modelling
81
+
82
+ ### Training hyperparameters
83
+
84
+ The following hyperparameters were used during training:
85
+ - learning_rate: 9e-05
86
+ - train_batch_size: 32
87
+ - eval_batch_size: 32
88
+ - seed: 42
89
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
90
+ - lr_scheduler_type: linear
91
+ - lr_scheduler_warmup_ratio: 0.2
92
+ - num_epochs: 8
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.27.3
97
+ - Pytorch 1.13.1+cu116
98
+ - Datasets 2.13.1
99
+ - Tokenizers 0.13.2
100
+