Hugging Face's logo

Kooltek68
/
sn9_163

Text Generation
Transformers
Safetensors
falcon
text-generation-inference
Model card Files Community
Kooltek68 commited on
Commit
b6cd984
·
verified ·
1 Parent(s): d0b67d0

Upload FalconForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +21 -38
  2. generation_config.json +2 -5
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,46 +1,29 @@
1
  {
2
- "_name_or_path": "/home/bts/subnet9/models/checkpoint-14000",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
  "architectures": [
6
- "BartForCausalLM"
7
  ],
8
  "attention_dropout": 0.0,
9
- "bos_token_id": 0,
10
- "classifier_dropout": 0.0,
11
- "d_model": 768,
12
- "decoder_attention_heads": 12,
13
- "decoder_ffn_dim": 3072,
14
- "decoder_layerdrop": 0.0,
15
- "decoder_layers": 15,
16
- "decoder_start_token_id": 2,
17
- "dropout": 0.1,
18
- "encoder_attention_heads": 12,
19
- "encoder_ffn_dim": 3072,
20
- "encoder_layerdrop": 0.0,
21
- "encoder_layers": 15,
22
- "eos_token_id": 2,
23
- "forced_eos_token_id": 2,
24
- "id2label": {
25
- "0": "LABEL_0",
26
- "1": "LABEL_1",
27
- "2": "LABEL_2"
28
- },
29
- "init_std": 0.02,
30
- "is_decoder": true,
31
- "is_encoder_decoder": false,
32
- "label2id": {
33
- "LABEL_0": 0,
34
- "LABEL_1": 1,
35
- "LABEL_2": 2
36
- },
37
- "max_position_embeddings": 1024,
38
- "model_type": "bart",
39
- "num_hidden_layers": 15,
40
- "pad_token_id": 1,
41
- "scale_embedding": false,
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.34.1",
44
  "use_cache": true,
45
- "vocab_size": 50265
46
  }
 
1
  {
2
+ "_name_or_path": "/home/bts/subnet9/models/falcon-772m-v1",
3
+ "alibi": false,
 
4
  "architectures": [
5
+ "FalconForCausalLM"
6
  ],
7
  "attention_dropout": 0.0,
8
+ "bias": false,
9
+ "bos_token_id": 11,
10
+ "eos_token_id": 11,
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 1344,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_position_embeddings": 2368,
16
+ "model_type": "falcon",
17
+ "multi_query": true,
18
+ "new_decoder_architecture": false,
19
+ "num_attention_heads": 21,
20
+ "num_hidden_layers": 37,
21
+ "num_kv_heads": 21,
22
+ "parallel_attn": true,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.34.1",
27
  "use_cache": true,
28
+ "vocab_size": 65024
29
  }
generation_config.json CHANGED
@@ -1,9 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "decoder_start_token_id": 2,
5
- "eos_token_id": 2,
6
- "forced_eos_token_id": 2,
7
- "pad_token_id": 1,
8
  "transformers_version": "4.34.1"
9
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
 
 
 
5
  "transformers_version": "4.34.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:383a51f94387a4fb4b9728ff02e2d4dd6d3be3b1412518619acd4ae69fcdea09
3
- size 724724784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:022e57d58e0bcd3c283ed172e652a495acc6fb55d939dca52e699bb1042c789b
3
+ size 3048842120