ManiWavelabs commited on
Commit
525be6c
1 Parent(s): bb6a7f2

Upload FalconForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tiiuae/falcon-40b",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-40b--configuration_falcon.FalconConfig",
11
+ "AutoModel": "tiiuae/falcon-40b--modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-40b--modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-40b--modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-40b--modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-40b--modeling_falcon.FalconForTokenClassification"
16
+ },
17
+ "bias": false,
18
+ "bos_token_id": 11,
19
+ "eos_token_id": 11,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 8192,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "model_type": "falcon",
25
+ "multi_query": true,
26
+ "new_decoder_architecture": true,
27
+ "num_attention_heads": 128,
28
+ "num_hidden_layers": 60,
29
+ "num_kv_heads": 8,
30
+ "parallel_attn": true,
31
+ "quantization_config": {
32
+ "bnb_4bit_compute_dtype": "float32",
33
+ "bnb_4bit_quant_type": "fp4",
34
+ "bnb_4bit_use_double_quant": false,
35
+ "llm_int8_enable_fp32_cpu_offload": false,
36
+ "llm_int8_has_fp16_weight": false,
37
+ "llm_int8_skip_modules": null,
38
+ "llm_int8_threshold": 6.0,
39
+ "load_in_4bit": false,
40
+ "load_in_8bit": true,
41
+ "quant_method": "bitsandbytes"
42
+ },
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.34.0.dev0",
45
+ "use_cache": false,
46
+ "vocab_size": 65024
47
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef30bb3a35451d6432077a221ddeb505217d59c37c5edc93721ec3b1f3c03e45
3
+ size 9934892374
pytorch_model-00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056e3a2056c6265c1f1f391f3bd818b1a4abf810115f48505645510c5f391bf5
3
+ size 9932599395
pytorch_model-00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c58bcb69a94709af3eaf550270b6097ce2c69198b18fb2dcd69e6b9b5444472
3
+ size 9932599395
pytorch_model-00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf90973720b38fb727c674d887ee3aa87bafd7b70729d58332a172d11b204f5
3
+ size 9932599395
pytorch_model-00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc2c02f02983e404116ba142d2f5e4669229991759f4862d88bfed981db640d9
3
+ size 4966365049
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff