Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+base_model:
+- ssmits/Falcon2-5.5B-Swedish
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [ssmits/Falcon2-5.5B-Swedish](https://huggingface.co/ssmits/Falcon2-5.5B-Swedish)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+    slices:
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [0, 9]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [5, 14]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [10, 19]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [15, 24]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [20, 27]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [27, 27]
+    merge_method: passthrough
+    dtype: bfloat16
+    
+```

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "ssmits/Falcon2-5.5B-Swedish",
+  "activation": "gelu",
+  "alibi": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-11B--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-11B--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-11B--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-11B--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "ff_factor": 4,
+  "ffn_hidden_size": 16384,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 8192,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": true,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 43,
+  "num_kv_heads": 8,
+  "num_ln_in_parallel_attn": 1,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 500042.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 65024
+}

mergekit_config.yml

@@ -0,0 +1,23 @@
+
+    slices:
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [0, 9]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [5, 14]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [10, 19]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [15, 24]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [20, 27]
+      - sources:
+        - model: ssmits/Falcon2-5.5B-Swedish
+          layer_range: [27, 27]
+    merge_method: passthrough
+    dtype: bfloat16
+    

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be473743446f6310af51e0c376f85362497f956b299ae82088be850871ebe058
+size 885031960

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b266af5f61b88975dc24c84b8c6a65a398b7ebdd1d47e17cc3e13e5d9e9e4a01
+size 956335760

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f6036667fd420ff2cff44197a2d9e814d07c859460d10cd34ead21facef5d6
+size 939591904

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080f28bc6e07ff50e1929fbe60d6ab56355f1ad40ec24c587f22d2f8a5a7dcd4
+size 973112992

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f35fea68f1b17a14d90f1d0c729bcbf42e11d073931991a007721447772c8b7
+size 922798080

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a08f3d9ebc44291af4ac3fef34a2bfeed2119e1e18723abc2b362540a275a54
+size 973112992

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796b57cd1b37fc5ae43b1fadf784fa25bfad5d2552aaedfd9cfed80db8800191
+size 872483160

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f6e072c60764babea3e21611bfbae2b182031dd26f6aca96dea308a15c5691
+size 973096384

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bada3bd0c35e57ada7023ed57cf3410387cb3742b4aea9321d05c8a1f4299aa
+size 973129568

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fab34c4cbb021242ac8e70c4a6b18a84e73d6d88b25bf763b6416977000a38a
+size 872483160

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea9c9be79b1d2f77b1240fd080b4dfe4d988d45a0d72aa8059a017c5f5e0e3f
+size 973112992

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2087e45e794c6379c2c030e7dac95bc9b09aefceeddf38ecdd8bdee77908189d
+size 922781472

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaec1c2fa1b1e0d136be1b9a91474861e6716fa728860bf00737d90df52a1d6a
+size 922798056

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60e5f9ea56fa70e5466aea48c23f7bf7d0de2f0c33ba341290cfa29687387bc
+size 956335752

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8fb63a7b23118e4c1dc8ef32ca6433b25f91432ccb6a22085e41a33fd8816e
+size 939591880

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81be0fcf8ef2fa681c11c381cd3b992f58e83776c00ad39ea465e07c9847e788
+size 973112984

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7eaba94b16f8080e2d6b44fc3f6412efc88f5491f168d4584ffbc9d8e000428
+size 654345736

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702a898add5350cfe6f7d138ac8b2c819b0a451103a73c6d908b0fb4aff091ec
+size 532676752

model.safetensors.index.json

@@ -0,0 +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

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "bos_token": {
+    "content": ">>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,135 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "500": {
+      "content": ">>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "bos_token": ">>",
+  "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 %}",
+  "clean_up_tokenization_spaces": true,
+  "device_map": "cuda:2",
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}