HeshamHaroon commited on
Commit
69c8fbe
1 Parent(s): c9be52d

Upload FalconForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +55 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tiiuae/falcon-rw-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
+ "quantization_config": {
32
+ "batch_size": 1,
33
+ "bits": 4,
34
+ "block_name_to_quantize": "transformer.h",
35
+ "damp_percent": 0.1,
36
+ "dataset": "c4",
37
+ "desc_act": false,
38
+ "disable_exllama": false,
39
+ "group_size": 128,
40
+ "model_seqlen": 2048,
41
+ "module_name_preceding_first_block": [
42
+ "transformer.word_embeddings"
43
+ ],
44
+ "pad_token_id": null,
45
+ "quant_method": "gptq",
46
+ "sym": true,
47
+ "tokenizer": null,
48
+ "true_sequential": true,
49
+ "use_cuda_fp16": true
50
+ },
51
+ "torch_dtype": "float16",
52
+ "transformers_version": "4.32.0",
53
+ "use_cache": true,
54
+ "vocab_size": 50304
55
+ }
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": "4.32.0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bcd5355566d3dc1d3853d23e47c93d6fe5566537cfcf2f6d5508e34a860fa8
3
+ size 836477401