Hugging Face's logo

mfurqanhakim
/
genAI_model

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
mfurqanhakim commited on
Commit
4b9d7e5
·
verified ·
1 Parent(s): 5232293

Model save

Browse files
Files changed (5) hide show
  1. README.md +2 -2
  2. config.json +5 -34
  3. final_model_finetuned/config.json +5 -34
  4. final_model_finetuned/model.safetensors +2 -2
  5. model.safetensors +2 -2
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
- base_model: google/flan-t5-small
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # genAI_model
16
 
17
- This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
  - Loss: nan
20
 
 
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: google/flan-t5-large
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # genAI_model
16
 
17
+ This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
  - Loss: nan
20
 
config.json CHANGED
@@ -3,9 +3,9 @@
3
  "T5ForConditionalGeneration"
4
  ],
5
  "classifier_dropout": 0.0,
6
- "d_ff": 1024,
7
  "d_kv": 64,
8
- "d_model": 512,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
@@ -17,42 +17,13 @@
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
20
- "num_decoder_layers": 8,
21
- "num_heads": 6,
22
- "num_layers": 8,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
26
  "relative_attention_num_buckets": 32,
27
- "task_specific_params": {
28
- "summarization": {
29
- "early_stopping": true,
30
- "length_penalty": 2.0,
31
- "max_length": 200,
32
- "min_length": 30,
33
- "no_repeat_ngram_size": 3,
34
- "num_beams": 4,
35
- "prefix": "summarize: "
36
- },
37
- "translation_en_to_de": {
38
- "early_stopping": true,
39
- "max_length": 300,
40
- "num_beams": 4,
41
- "prefix": "translate English to German: "
42
- },
43
- "translation_en_to_fr": {
44
- "early_stopping": true,
45
- "max_length": 300,
46
- "num_beams": 4,
47
- "prefix": "translate English to French: "
48
- },
49
- "translation_en_to_ro": {
50
- "early_stopping": true,
51
- "max_length": 300,
52
- "num_beams": 4,
53
- "prefix": "translate English to Romanian: "
54
- }
55
- },
56
  "tie_word_embeddings": false,
57
  "torch_dtype": "float32",
58
  "transformers_version": "4.51.3",
 
3
  "T5ForConditionalGeneration"
4
  ],
5
  "classifier_dropout": 0.0,
6
+ "d_ff": 2816,
7
  "d_kv": 64,
8
+ "d_model": 1024,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
 
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
26
  "relative_attention_num_buckets": 32,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "tie_word_embeddings": false,
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.51.3",
final_model_finetuned/config.json CHANGED
@@ -3,9 +3,9 @@
3
  "T5ForConditionalGeneration"
4
  ],
5
  "classifier_dropout": 0.0,
6
- "d_ff": 1024,
7
  "d_kv": 64,
8
- "d_model": 512,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
@@ -17,42 +17,13 @@
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
20
- "num_decoder_layers": 8,
21
- "num_heads": 6,
22
- "num_layers": 8,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
26
  "relative_attention_num_buckets": 32,
27
- "task_specific_params": {
28
- "summarization": {
29
- "early_stopping": true,
30
- "length_penalty": 2.0,
31
- "max_length": 200,
32
- "min_length": 30,
33
- "no_repeat_ngram_size": 3,
34
- "num_beams": 4,
35
- "prefix": "summarize: "
36
- },
37
- "translation_en_to_de": {
38
- "early_stopping": true,
39
- "max_length": 300,
40
- "num_beams": 4,
41
- "prefix": "translate English to German: "
42
- },
43
- "translation_en_to_fr": {
44
- "early_stopping": true,
45
- "max_length": 300,
46
- "num_beams": 4,
47
- "prefix": "translate English to French: "
48
- },
49
- "translation_en_to_ro": {
50
- "early_stopping": true,
51
- "max_length": 300,
52
- "num_beams": 4,
53
- "prefix": "translate English to Romanian: "
54
- }
55
- },
56
  "tie_word_embeddings": false,
57
  "torch_dtype": "float32",
58
  "transformers_version": "4.51.3",
 
3
  "T5ForConditionalGeneration"
4
  ],
5
  "classifier_dropout": 0.0,
6
+ "d_ff": 2816,
7
  "d_kv": 64,
8
+ "d_model": 1024,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
 
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
26
  "relative_attention_num_buckets": 32,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "tie_word_embeddings": false,
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.51.3",
final_model_finetuned/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495fa51e204676f1a857a9fc13c4c89f3f5ba9f480b898cebca02add25e6d749
3
- size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473e1f8c9a16420b1fe5be89bcf1395a8418894d414f75217f701fe542089d60
3
+ size 3132668808
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495fa51e204676f1a857a9fc13c4c89f3f5ba9f480b898cebca02add25e6d749
3
- size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473e1f8c9a16420b1fe5be89bcf1395a8418894d414f75217f701fe542089d60
3
+ size 3132668808