mrutyunjay-patil commited on
Commit
22faf24
1 Parent(s): 0fbd1d5

Initial commit with trained model.

Browse files
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
config.json CHANGED
@@ -1,19 +1,60 @@
1
  {
2
- "base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
3
- "bias": "none",
4
- "fan_in_fan_out": false,
5
- "inference_mode": true,
6
- "init_lora_weights": true,
7
- "layers_pattern": null,
8
- "layers_to_transform": null,
9
- "lora_alpha": 32,
10
- "lora_dropout": 0.05,
11
- "modules_to_save": null,
12
- "peft_type": "LORA",
13
- "r": 16,
14
- "revision": null,
15
- "target_modules": [
16
- "query_key_value"
17
  ],
18
- "task_type": "CAUSAL_LM"
19
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
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
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.31.0",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.31.0"
7
+ }
adapter_model.bin → pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55bc75c3c1a99f2de1429876e5f153e9c514018270971b9ec50e04e7ffa37048
3
- size 18898161
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9535acb89c00c64df41586e0ee80dde73860025aef94b77985be90442cea801
3
+ size 891702929