ssmits commited on
Commit
1bd0cf8
1 Parent(s): c39b09d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - ssmits/Falcon2-5.5B-Swedish
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [ssmits/Falcon2-5.5B-Swedish](https://huggingface.co/ssmits/Falcon2-5.5B-Swedish)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+
30
+ slices:
31
+ - sources:
32
+ - model: ssmits/Falcon2-5.5B-Swedish
33
+ layer_range: [0, 9]
34
+ - sources:
35
+ - model: ssmits/Falcon2-5.5B-Swedish
36
+ layer_range: [5, 14]
37
+ - sources:
38
+ - model: ssmits/Falcon2-5.5B-Swedish
39
+ layer_range: [10, 19]
40
+ - sources:
41
+ - model: ssmits/Falcon2-5.5B-Swedish
42
+ layer_range: [15, 24]
43
+ - sources:
44
+ - model: ssmits/Falcon2-5.5B-Swedish
45
+ layer_range: [20, 27]
46
+ - sources:
47
+ - model: ssmits/Falcon2-5.5B-Swedish
48
+ layer_range: [27, 27]
49
+ merge_method: passthrough
50
+ dtype: bfloat16
51
+
52
+ ```
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ssmits/Falcon2-5.5B-Swedish",
3
+ "activation": "gelu",
4
+ "alibi": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-11B--configuration_falcon.FalconConfig",
11
+ "AutoModel": "tiiuae/falcon-11B--modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-11B--modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-11B--modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForTokenClassification"
16
+ },
17
+ "bias": false,
18
+ "bos_token_id": 11,
19
+ "eos_token_id": 11,
20
+ "ff_factor": 4,
21
+ "ffn_hidden_size": 16384,
22
+ "hidden_dropout": 0.0,
23
+ "hidden_size": 4096,
24
+ "initializer_range": 0.02,
25
+ "layer_norm_epsilon": 1e-05,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "falcon",
28
+ "multi_query": true,
29
+ "new_decoder_architecture": true,
30
+ "num_attention_heads": 32,
31
+ "num_hidden_layers": 43,
32
+ "num_kv_heads": 8,
33
+ "num_ln_in_parallel_attn": 1,
34
+ "parallel_attn": true,
35
+ "rope_scaling": null,
36
+ "rope_theta": 500042.0,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.41.1",
40
+ "use_cache": true,
41
+ "vocab_size": 65024
42
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: ssmits/Falcon2-5.5B-Swedish
5
+ layer_range: [0, 9]
6
+ - sources:
7
+ - model: ssmits/Falcon2-5.5B-Swedish
8
+ layer_range: [5, 14]
9
+ - sources:
10
+ - model: ssmits/Falcon2-5.5B-Swedish
11
+ layer_range: [10, 19]
12
+ - sources:
13
+ - model: ssmits/Falcon2-5.5B-Swedish
14
+ layer_range: [15, 24]
15
+ - sources:
16
+ - model: ssmits/Falcon2-5.5B-Swedish
17
+ layer_range: [20, 27]
18
+ - sources:
19
+ - model: ssmits/Falcon2-5.5B-Swedish
20
+ layer_range: [27, 27]
21
+ merge_method: passthrough
22
+ dtype: bfloat16
23
+
model-00001-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be473743446f6310af51e0c376f85362497f956b299ae82088be850871ebe058
3
+ size 885031960
model-00002-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b266af5f61b88975dc24c84b8c6a65a398b7ebdd1d47e17cc3e13e5d9e9e4a01
3
+ size 956335760
model-00003-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f6036667fd420ff2cff44197a2d9e814d07c859460d10cd34ead21facef5d6
3
+ size 939591904
model-00004-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080f28bc6e07ff50e1929fbe60d6ab56355f1ad40ec24c587f22d2f8a5a7dcd4
3
+ size 973112992
model-00005-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f35fea68f1b17a14d90f1d0c729bcbf42e11d073931991a007721447772c8b7
3
+ size 922798080
model-00006-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a08f3d9ebc44291af4ac3fef34a2bfeed2119e1e18723abc2b362540a275a54
3
+ size 973112992
model-00007-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796b57cd1b37fc5ae43b1fadf784fa25bfad5d2552aaedfd9cfed80db8800191
3
+ size 872483160
model-00008-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f6e072c60764babea3e21611bfbae2b182031dd26f6aca96dea308a15c5691
3
+ size 973096384
model-00009-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bada3bd0c35e57ada7023ed57cf3410387cb3742b4aea9321d05c8a1f4299aa
3
+ size 973129568
model-00010-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fab34c4cbb021242ac8e70c4a6b18a84e73d6d88b25bf763b6416977000a38a
3
+ size 872483160
model-00011-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea9c9be79b1d2f77b1240fd080b4dfe4d988d45a0d72aa8059a017c5f5e0e3f
3
+ size 973112992
model-00012-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2087e45e794c6379c2c030e7dac95bc9b09aefceeddf38ecdd8bdee77908189d
3
+ size 922781472
model-00013-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaec1c2fa1b1e0d136be1b9a91474861e6716fa728860bf00737d90df52a1d6a
3
+ size 922798056
model-00014-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60e5f9ea56fa70e5466aea48c23f7bf7d0de2f0c33ba341290cfa29687387bc
3
+ size 956335752
model-00015-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8fb63a7b23118e4c1dc8ef32ca6433b25f91432ccb6a22085e41a33fd8816e
3
+ size 939591880
model-00016-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81be0fcf8ef2fa681c11c381cd3b992f58e83776c00ad39ea465e07c9847e788
3
+ size 973112984
model-00017-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7eaba94b16f8080e2d6b44fc3f6412efc88f5491f168d4584ffbc9d8e000428
3
+ size 654345736
model-00018-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702a898add5350cfe6f7d138ac8b2c819b0a451103a73c6d908b0fb4aff091ec
3
+ size 532676752
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 16215900160}, "weight_map": {"lm_head.weight": "model-00001-of-00018.safetensors", "transformer.h.0.input_layernorm.bias": "model-00001-of-00018.safetensors", "transformer.h.0.input_layernorm.weight": "model-00001-of-00018.safetensors", "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00018.safetensors", "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00018.safetensors", "transformer.h.0.self_attention.dense.weight": "model-00001-of-00018.safetensors", "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00018.safetensors", "transformer.h.1.input_layernorm.bias": "model-00001-of-00018.safetensors", "transformer.h.1.input_layernorm.weight": "model-00001-of-00018.safetensors", "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00018.safetensors", "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00018.safetensors", "transformer.h.1.self_attention.dense.weight": "model-00002-of-00018.safetensors", "transformer.h.1.self_attention.query_key_value.weight": "model-00002-of-00018.safetensors", "transformer.h.18.input_layernorm.bias": "model-00002-of-00018.safetensors", "transformer.h.14.input_layernorm.bias": "model-00002-of-00018.safetensors", "transformer.h.18.input_layernorm.weight": "model-00002-of-00018.safetensors", "transformer.h.14.input_layernorm.weight": "model-00002-of-00018.safetensors", "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00018.safetensors", "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00018.safetensors", "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00018.safetensors", "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00018.safetensors", "transformer.h.18.self_attention.dense.weight": "model-00002-of-00018.safetensors", "transformer.h.14.self_attention.dense.weight": "model-00002-of-00018.safetensors", "transformer.h.18.self_attention.query_key_value.weight": "model-00003-of-00018.safetensors", "transformer.h.14.self_attention.query_key_value.weight": "model-00003-of-00018.safetensors", "transformer.h.19.input_layernorm.bias": "model-00003-of-00018.safetensors", "transformer.h.15.input_layernorm.bias": "model-00003-of-00018.safetensors", "transformer.h.19.input_layernorm.weight": "model-00003-of-00018.safetensors", "transformer.h.15.input_layernorm.weight": "model-00003-of-00018.safetensors", "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00003-of-00018.safetensors", "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00003-of-00018.safetensors", "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00003-of-00018.safetensors", "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00003-of-00018.safetensors", "transformer.h.19.self_attention.dense.weight": "model-00003-of-00018.safetensors", "transformer.h.15.self_attention.dense.weight": "model-00003-of-00018.safetensors", "transformer.h.19.self_attention.query_key_value.weight": "model-00003-of-00018.safetensors", "transformer.h.15.self_attention.query_key_value.weight": "model-00003-of-00018.safetensors", "transformer.h.20.input_layernorm.bias": "model-00003-of-00018.safetensors", "transformer.h.16.input_layernorm.bias": "model-00003-of-00018.safetensors", "transformer.h.20.input_layernorm.weight": "model-00003-of-00018.safetensors", "transformer.h.16.input_layernorm.weight": "model-00003-of-00018.safetensors", "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00003-of-00018.safetensors", "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00018.safetensors", "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00004-of-00018.safetensors", "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00004-of-00018.safetensors", "transformer.h.20.self_attention.dense.weight": "model-00004-of-00018.safetensors", "transformer.h.16.self_attention.dense.weight": "model-00004-of-00018.safetensors", "transformer.h.20.self_attention.query_key_value.weight": "model-00004-of-00018.safetensors", "transformer.h.16.self_attention.query_key_value.weight": "model-00004-of-00018.safetensors", "transformer.h.21.input_layernorm.bias": "model-00004-of-00018.safetensors", "transformer.h.17.input_layernorm.bias": "model-00004-of-00018.safetensors", "transformer.h.21.input_layernorm.weight": "model-00004-of-00018.safetensors", "transformer.h.17.input_layernorm.weight": "model-00004-of-00018.safetensors", "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00004-of-00018.safetensors", "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00004-of-00018.safetensors", "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00004-of-00018.safetensors", "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00005-of-00018.safetensors", "transformer.h.21.self_attention.dense.weight": "model-00005-of-00018.safetensors", "transformer.h.17.self_attention.dense.weight": "model-00005-of-00018.safetensors", "transformer.h.21.self_attention.query_key_value.weight": "model-00005-of-00018.safetensors", "transformer.h.17.self_attention.query_key_value.weight": "model-00005-of-00018.safetensors", "transformer.h.22.input_layernorm.bias": "model-00005-of-00018.safetensors", "transformer.h.22.input_layernorm.weight": "model-00005-of-00018.safetensors", "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00005-of-00018.safetensors", "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00005-of-00018.safetensors", "transformer.h.22.self_attention.dense.weight": "model-00005-of-00018.safetensors", "transformer.h.22.self_attention.query_key_value.weight": "model-00005-of-00018.safetensors", "transformer.h.27.input_layernorm.bias": "model-00005-of-00018.safetensors", "transformer.h.23.input_layernorm.bias": "model-00005-of-00018.safetensors", "transformer.h.27.input_layernorm.weight": "model-00005-of-00018.safetensors", "transformer.h.23.input_layernorm.weight": "model-00005-of-00018.safetensors", "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00005-of-00018.safetensors", "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00005-of-00018.safetensors", "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00006-of-00018.safetensors", "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00006-of-00018.safetensors", "transformer.h.27.self_attention.dense.weight": "model-00006-of-00018.safetensors", "transformer.h.23.self_attention.dense.weight": "model-00006-of-00018.safetensors", "transformer.h.27.self_attention.query_key_value.weight": "model-00006-of-00018.safetensors", "transformer.h.23.self_attention.query_key_value.weight": "model-00006-of-00018.safetensors", "transformer.h.28.input_layernorm.bias": "model-00006-of-00018.safetensors", "transformer.h.24.input_layernorm.bias": "model-00006-of-00018.safetensors", "transformer.h.28.input_layernorm.weight": "model-00006-of-00018.safetensors", "transformer.h.24.input_layernorm.weight": "model-00006-of-00018.safetensors", "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00006-of-00018.safetensors", "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00006-of-00018.safetensors", "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00006-of-00018.safetensors", "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00006-of-00018.safetensors", "transformer.h.28.self_attention.dense.weight": "model-00007-of-00018.safetensors", "transformer.h.24.self_attention.dense.weight": "model-00007-of-00018.safetensors", "transformer.h.28.self_attention.query_key_value.weight": "model-00007-of-00018.safetensors", "transformer.h.24.self_attention.query_key_value.weight": "model-00007-of-00018.safetensors", "transformer.h.29.input_layernorm.bias": "model-00007-of-00018.safetensors", "transformer.h.25.input_layernorm.bias": "model-00007-of-00018.safetensors", "transformer.h.29.input_layernorm.weight": "model-00007-of-00018.safetensors", "transformer.h.25.input_layernorm.weight": "model-00007-of-00018.safetensors", "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00007-of-00018.safetensors", "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00007-of-00018.safetensors", "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00007-of-00018.safetensors", "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00007-of-00018.safetensors", "transformer.h.29.self_attention.dense.weight": "model-00007-of-00018.safetensors", "transformer.h.25.self_attention.dense.weight": "model-00007-of-00018.safetensors", "transformer.h.29.self_attention.query_key_value.weight": "model-00007-of-00018.safetensors", "transformer.h.25.self_attention.query_key_value.weight": "model-00007-of-00018.safetensors", "transformer.h.30.input_layernorm.bias": "model-00007-of-00018.safetensors", "transformer.h.26.input_layernorm.bias": "model-00007-of-00018.safetensors", "transformer.h.30.input_layernorm.weight": "model-00007-of-00018.safetensors", "transformer.h.26.input_layernorm.weight": "model-00007-of-00018.safetensors", "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00008-of-00018.safetensors", "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00008-of-00018.safetensors", "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00008-of-00018.safetensors", "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00008-of-00018.safetensors", "transformer.h.30.self_attention.dense.weight": "model-00008-of-00018.safetensors", "transformer.h.26.self_attention.dense.weight": "model-00008-of-00018.safetensors", "transformer.h.30.self_attention.query_key_value.weight": "model-00008-of-00018.safetensors", "transformer.h.26.self_attention.query_key_value.weight": "model-00008-of-00018.safetensors", "transformer.h.31.input_layernorm.bias": "model-00008-of-00018.safetensors", "transformer.h.31.input_layernorm.weight": "model-00008-of-00018.safetensors", "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00008-of-00018.safetensors", "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00008-of-00018.safetensors", "transformer.h.31.self_attention.dense.weight": "model-00009-of-00018.safetensors", "transformer.h.31.self_attention.query_key_value.weight": "model-00009-of-00018.safetensors", "transformer.h.2.input_layernorm.bias": "model-00009-of-00018.safetensors", "transformer.h.2.input_layernorm.weight": "model-00009-of-00018.safetensors", "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00009-of-00018.safetensors", "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00009-of-00018.safetensors", "transformer.h.2.self_attention.dense.weight": "model-00009-of-00018.safetensors", "transformer.h.2.self_attention.query_key_value.weight": "model-00009-of-00018.safetensors", "transformer.h.36.input_layernorm.bias": "model-00009-of-00018.safetensors", "transformer.h.32.input_layernorm.bias": "model-00009-of-00018.safetensors", "transformer.h.36.input_layernorm.weight": "model-00009-of-00018.safetensors", "transformer.h.32.input_layernorm.weight": "model-00009-of-00018.safetensors", "transformer.h.36.mlp.dense_4h_to_h.weight": "model-00009-of-00018.safetensors", "transformer.h.32.mlp.dense_4h_to_h.weight": "model-00009-of-00018.safetensors", "transformer.h.36.mlp.dense_h_to_4h.weight": "model-00009-of-00018.safetensors", "transformer.h.32.mlp.dense_h_to_4h.weight": "model-00009-of-00018.safetensors", "transformer.h.36.self_attention.dense.weight": "model-00010-of-00018.safetensors", "transformer.h.32.self_attention.dense.weight": "model-00010-of-00018.safetensors", "transformer.h.36.self_attention.query_key_value.weight": "model-00010-of-00018.safetensors", "transformer.h.32.self_attention.query_key_value.weight": "model-00010-of-00018.safetensors", "transformer.h.37.input_layernorm.bias": "model-00010-of-00018.safetensors", "transformer.h.33.input_layernorm.bias": "model-00010-of-00018.safetensors", "transformer.h.37.input_layernorm.weight": "model-00010-of-00018.safetensors", "transformer.h.33.input_layernorm.weight": "model-00010-of-00018.safetensors", "transformer.h.37.mlp.dense_4h_to_h.weight": "model-00010-of-00018.safetensors", "transformer.h.33.mlp.dense_4h_to_h.weight": "model-00010-of-00018.safetensors", "transformer.h.37.mlp.dense_h_to_4h.weight": "model-00010-of-00018.safetensors", "transformer.h.33.mlp.dense_h_to_4h.weight": "model-00010-of-00018.safetensors", "transformer.h.37.self_attention.dense.weight": "model-00010-of-00018.safetensors", "transformer.h.33.self_attention.dense.weight": "model-00010-of-00018.safetensors", "transformer.h.37.self_attention.query_key_value.weight": "model-00010-of-00018.safetensors", "transformer.h.33.self_attention.query_key_value.weight": "model-00010-of-00018.safetensors", "transformer.h.38.input_layernorm.bias": "model-00010-of-00018.safetensors", "transformer.h.34.input_layernorm.bias": "model-00010-of-00018.safetensors", "transformer.h.38.input_layernorm.weight": "model-00010-of-00018.safetensors", "transformer.h.34.input_layernorm.weight": "model-00010-of-00018.safetensors", "transformer.h.38.mlp.dense_4h_to_h.weight": "model-00011-of-00018.safetensors", "transformer.h.34.mlp.dense_4h_to_h.weight": "model-00011-of-00018.safetensors", "transformer.h.38.mlp.dense_h_to_4h.weight": "model-00011-of-00018.safetensors", "transformer.h.34.mlp.dense_h_to_4h.weight": "model-00011-of-00018.safetensors", "transformer.h.38.self_attention.dense.weight": "model-00011-of-00018.safetensors", "transformer.h.34.self_attention.dense.weight": "model-00011-of-00018.safetensors", "transformer.h.38.self_attention.query_key_value.weight": "model-00011-of-00018.safetensors", "transformer.h.34.self_attention.query_key_value.weight": "model-00011-of-00018.safetensors", "transformer.h.39.input_layernorm.bias": "model-00011-of-00018.safetensors", "transformer.h.35.input_layernorm.bias": "model-00011-of-00018.safetensors", "transformer.h.39.input_layernorm.weight": "model-00011-of-00018.safetensors", "transformer.h.35.input_layernorm.weight": "model-00011-of-00018.safetensors", "transformer.h.39.mlp.dense_4h_to_h.weight": "model-00011-of-00018.safetensors", "transformer.h.35.mlp.dense_4h_to_h.weight": "model-00011-of-00018.safetensors", "transformer.h.39.mlp.dense_h_to_4h.weight": "model-00012-of-00018.safetensors", "transformer.h.35.mlp.dense_h_to_4h.weight": "model-00012-of-00018.safetensors", "transformer.h.39.self_attention.dense.weight": "model-00012-of-00018.safetensors", "transformer.h.35.self_attention.dense.weight": "model-00012-of-00018.safetensors", "transformer.h.39.self_attention.query_key_value.weight": "model-00012-of-00018.safetensors", "transformer.h.35.self_attention.query_key_value.weight": "model-00012-of-00018.safetensors", "transformer.h.40.input_layernorm.bias": "model-00012-of-00018.safetensors", "transformer.h.40.input_layernorm.weight": "model-00012-of-00018.safetensors", "transformer.h.40.mlp.dense_4h_to_h.weight": "model-00012-of-00018.safetensors", "transformer.h.40.mlp.dense_h_to_4h.weight": "model-00012-of-00018.safetensors", "transformer.h.40.self_attention.dense.weight": "model-00012-of-00018.safetensors", "transformer.h.40.self_attention.query_key_value.weight": "model-00012-of-00018.safetensors", "transformer.h.41.input_layernorm.bias": "model-00012-of-00018.safetensors", "transformer.h.41.input_layernorm.weight": "model-00012-of-00018.safetensors", "transformer.h.41.mlp.dense_4h_to_h.weight": "model-00012-of-00018.safetensors", "transformer.h.41.mlp.dense_h_to_4h.weight": "model-00013-of-00018.safetensors", "transformer.h.41.self_attention.dense.weight": "model-00013-of-00018.safetensors", "transformer.h.41.self_attention.query_key_value.weight": "model-00013-of-00018.safetensors", "transformer.h.42.input_layernorm.bias": "model-00013-of-00018.safetensors", "transformer.h.42.input_layernorm.weight": "model-00013-of-00018.safetensors", "transformer.h.42.mlp.dense_4h_to_h.weight": "model-00013-of-00018.safetensors", "transformer.h.42.mlp.dense_h_to_4h.weight": "model-00013-of-00018.safetensors", "transformer.h.42.self_attention.dense.weight": "model-00013-of-00018.safetensors", "transformer.h.42.self_attention.query_key_value.weight": "model-00013-of-00018.safetensors", "transformer.h.3.input_layernorm.bias": "model-00013-of-00018.safetensors", "transformer.h.3.input_layernorm.weight": "model-00013-of-00018.safetensors", "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00013-of-00018.safetensors", "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00013-of-00018.safetensors", "transformer.h.3.self_attention.dense.weight": "model-00013-of-00018.safetensors", "transformer.h.3.self_attention.query_key_value.weight": "model-00013-of-00018.safetensors", "transformer.h.4.input_layernorm.bias": "model-00013-of-00018.safetensors", "transformer.h.4.input_layernorm.weight": "model-00013-of-00018.safetensors", "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00014-of-00018.safetensors", "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00014-of-00018.safetensors", "transformer.h.4.self_attention.dense.weight": "model-00014-of-00018.safetensors", "transformer.h.4.self_attention.query_key_value.weight": "model-00014-of-00018.safetensors", "transformer.h.9.input_layernorm.bias": "model-00014-of-00018.safetensors", "transformer.h.5.input_layernorm.bias": "model-00014-of-00018.safetensors", "transformer.h.9.input_layernorm.weight": "model-00014-of-00018.safetensors", "transformer.h.5.input_layernorm.weight": "model-00014-of-00018.safetensors", "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00014-of-00018.safetensors", "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00014-of-00018.safetensors", "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00014-of-00018.safetensors", "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00014-of-00018.safetensors", "transformer.h.9.self_attention.dense.weight": "model-00014-of-00018.safetensors", "transformer.h.5.self_attention.dense.weight": "model-00014-of-00018.safetensors", "transformer.h.9.self_attention.query_key_value.weight": "model-00015-of-00018.safetensors", "transformer.h.5.self_attention.query_key_value.weight": "model-00015-of-00018.safetensors", "transformer.h.10.input_layernorm.bias": "model-00015-of-00018.safetensors", "transformer.h.6.input_layernorm.bias": "model-00015-of-00018.safetensors", "transformer.h.10.input_layernorm.weight": "model-00015-of-00018.safetensors", "transformer.h.6.input_layernorm.weight": "model-00015-of-00018.safetensors", "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00015-of-00018.safetensors", "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00015-of-00018.safetensors", "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00015-of-00018.safetensors", "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00015-of-00018.safetensors", "transformer.h.10.self_attention.dense.weight": "model-00015-of-00018.safetensors", "transformer.h.6.self_attention.dense.weight": "model-00015-of-00018.safetensors", "transformer.h.10.self_attention.query_key_value.weight": "model-00015-of-00018.safetensors", "transformer.h.6.self_attention.query_key_value.weight": "model-00015-of-00018.safetensors", "transformer.h.11.input_layernorm.bias": "model-00015-of-00018.safetensors", "transformer.h.7.input_layernorm.bias": "model-00015-of-00018.safetensors", "transformer.h.11.input_layernorm.weight": "model-00015-of-00018.safetensors", "transformer.h.7.input_layernorm.weight": "model-00015-of-00018.safetensors", "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00015-of-00018.safetensors", "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00016-of-00018.safetensors", "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00016-of-00018.safetensors", "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00016-of-00018.safetensors", "transformer.h.11.self_attention.dense.weight": "model-00016-of-00018.safetensors", "transformer.h.7.self_attention.dense.weight": "model-00016-of-00018.safetensors", "transformer.h.11.self_attention.query_key_value.weight": "model-00016-of-00018.safetensors", "transformer.h.7.self_attention.query_key_value.weight": "model-00016-of-00018.safetensors", "transformer.h.12.input_layernorm.bias": "model-00016-of-00018.safetensors", "transformer.h.8.input_layernorm.bias": "model-00016-of-00018.safetensors", "transformer.h.12.input_layernorm.weight": "model-00016-of-00018.safetensors", "transformer.h.8.input_layernorm.weight": "model-00016-of-00018.safetensors", "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00016-of-00018.safetensors", "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00016-of-00018.safetensors", "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00016-of-00018.safetensors", "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00017-of-00018.safetensors", "transformer.h.12.self_attention.dense.weight": "model-00017-of-00018.safetensors", "transformer.h.8.self_attention.dense.weight": "model-00017-of-00018.safetensors", "transformer.h.12.self_attention.query_key_value.weight": "model-00017-of-00018.safetensors", "transformer.h.8.self_attention.query_key_value.weight": "model-00017-of-00018.safetensors", "transformer.h.13.input_layernorm.bias": "model-00017-of-00018.safetensors", "transformer.h.13.input_layernorm.weight": "model-00017-of-00018.safetensors", "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00017-of-00018.safetensors", "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00017-of-00018.safetensors", "transformer.h.13.self_attention.dense.weight": "model-00017-of-00018.safetensors", "transformer.h.13.self_attention.query_key_value.weight": "model-00017-of-00018.safetensors", "transformer.ln_f.bias": "model-00017-of-00018.safetensors", "transformer.ln_f.weight": "model-00017-of-00018.safetensors", "transformer.word_embeddings.weight": "model-00018-of-00018.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "bos_token": {
16
+ "content": ">>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "eos_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "pad_token": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": ">>TITLE<<",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": ">>ABSTRACT<<",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": ">>INTRODUCTION<<",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": ">>SUMMARY<<",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": ">>COMMENT<<",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": ">>ANSWER<<",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": ">>QUESTION<<",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": ">>DOMAIN<<",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": ">>PREFIX<<",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": ">>SUFFIX<<",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": ">>MIDDLE<<",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<|endoftext|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "500": {
101
+ "content": ">>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ }
108
+ },
109
+ "additional_special_tokens": [
110
+ ">>TITLE<<",
111
+ ">>ABSTRACT<<",
112
+ ">>INTRODUCTION<<",
113
+ ">>SUMMARY<<",
114
+ ">>COMMENT<<",
115
+ ">>ANSWER<<",
116
+ ">>QUESTION<<",
117
+ ">>DOMAIN<<",
118
+ ">>PREFIX<<",
119
+ ">>SUFFIX<<",
120
+ ">>MIDDLE<<"
121
+ ],
122
+ "bos_token": ">>",
123
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'User: \n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ 'System: ' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ 'Falcon:\n' + message['content']}}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Falcon:' }}\n{% endif %}\n{% endfor %}",
124
+ "clean_up_tokenization_spaces": true,
125
+ "device_map": "cuda:2",
126
+ "eos_token": "<|endoftext|>",
127
+ "model_input_names": [
128
+ "input_ids",
129
+ "attention_mask"
130
+ ],
131
+ "model_max_length": 1000000000000000019884624838656,
132
+ "pad_token": "<|endoftext|>",
133
+ "padding_side": "left",
134
+ "tokenizer_class": "PreTrainedTokenizerFast"
135
+ }