sam2ai commited on
Commit
0d010d9
1 Parent(s): 5d34cfc

model base v1.1

Browse files
added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sam2ai/falcon-extend-odia-1B",
3
+ "alibi": true,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
11
+ "AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
16
+ },
17
+ "bias": true,
18
+ "bos_token_id": 1,
19
+ "eos_token_id": 2,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 2048,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "model_type": "falcon",
25
+ "multi_query": false,
26
+ "new_decoder_architecture": false,
27
+ "num_attention_heads": 32,
28
+ "num_hidden_layers": 24,
29
+ "num_kv_heads": 32,
30
+ "parallel_attn": false,
31
+ "torch_dtype": "float16",
32
+ "transformers_version": "4.33.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 54594
35
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.33.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2fa35a7f69f4657da55b437c0d73c04761fb99e7a914ca777c6269dc6a85fc4
3
+ size 2864537949
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": ">>ABSTRACT<<",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff