Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+base_model:
+- tiiuae/falcon-11B
+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:
+* [tiiuae/falcon-11B](https://huggingface.co/tiiuae/falcon-11B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+    - model: tiiuae/falcon-11B
+      layer_range: [0, 14]
+  - sources:
+    - model: tiiuae/falcon-11B
+      layer_range: [58, 59]
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "tiiuae/falcon-11B",
+  "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": 15,
+  "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": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 65024
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+slices:
+  - sources:
+    - model: tiiuae/falcon-11B
+      layer_range: [0, 14]
+  - sources:
+    - model: tiiuae/falcon-11B
+      layer_range: [58, 59]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00007.safetensors

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

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7958aad384a953d794c245dc1fb049cf2e88db6555ebef8a37db39727a4f268
+size 973112984

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af88d2b4088e25940d9ed659d6c5d51a6f45ea30ebc6225df8566e6a1b4889b
+size 922798064

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4d2a53884c65e30d3d5accbfe6da44300241ec0858e1ce6ea5b57e2170cdb8
+size 922798064

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251be00d26c131569bdc3581d9d8c76c62d9f0cde1acb3ef04da3ffc37c47cb9
+size 973112960

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67831f9550c08191e7d2fd3db9894f450ed021284e73c22e147b796b8de0ba1c
+size 922798056

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1067d933aff18dee2cb3dccae118097ecec785625a688e64ee753c2d93313a3a
+size 750797504

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 6350438400}, "weight_map": {"lm_head.weight": "model-00001-of-00007.safetensors", "transformer.h.0.input_layernorm.bias": "model-00001-of-00007.safetensors", "transformer.h.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors", "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors", "transformer.h.0.self_attention.dense.weight": "model-00001-of-00007.safetensors", "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors", "transformer.h.1.input_layernorm.bias": "model-00001-of-00007.safetensors", "transformer.h.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors", "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors", "transformer.h.1.self_attention.dense.weight": "model-00002-of-00007.safetensors", "transformer.h.1.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors", "transformer.h.10.input_layernorm.bias": "model-00002-of-00007.safetensors", "transformer.h.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors", "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors", "transformer.h.10.self_attention.dense.weight": "model-00002-of-00007.safetensors", "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors", "transformer.h.11.input_layernorm.bias": "model-00002-of-00007.safetensors", "transformer.h.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors", "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors", "transformer.h.11.self_attention.dense.weight": "model-00003-of-00007.safetensors", "transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors", "transformer.h.12.input_layernorm.bias": "model-00003-of-00007.safetensors", "transformer.h.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors", "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors", "transformer.h.12.self_attention.dense.weight": "model-00003-of-00007.safetensors", "transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors", "transformer.h.13.input_layernorm.bias": "model-00003-of-00007.safetensors", "transformer.h.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors", "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors", "transformer.h.13.self_attention.dense.weight": "model-00003-of-00007.safetensors", "transformer.h.13.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors", "transformer.h.2.input_layernorm.bias": "model-00003-of-00007.safetensors", "transformer.h.2.input_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors", "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors", "transformer.h.2.self_attention.dense.weight": "model-00004-of-00007.safetensors", "transformer.h.2.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors", "transformer.h.3.input_layernorm.bias": "model-00004-of-00007.safetensors", "transformer.h.3.input_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors", "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors", "transformer.h.3.self_attention.dense.weight": "model-00004-of-00007.safetensors", "transformer.h.3.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors", "transformer.h.4.input_layernorm.bias": "model-00004-of-00007.safetensors", "transformer.h.4.input_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors", "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors", "transformer.h.4.self_attention.dense.weight": "model-00004-of-00007.safetensors", "transformer.h.4.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors", "transformer.h.5.input_layernorm.bias": "model-00004-of-00007.safetensors", "transformer.h.5.input_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors", "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors", "transformer.h.5.self_attention.dense.weight": "model-00005-of-00007.safetensors", "transformer.h.5.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors", "transformer.h.14.input_layernorm.bias": "model-00005-of-00007.safetensors", "transformer.h.14.input_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors", "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors", "transformer.h.14.self_attention.dense.weight": "model-00005-of-00007.safetensors", "transformer.h.14.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors", "transformer.h.6.input_layernorm.bias": "model-00005-of-00007.safetensors", "transformer.h.6.input_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors", "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors", "transformer.h.6.self_attention.dense.weight": "model-00006-of-00007.safetensors", "transformer.h.6.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors", "transformer.h.7.input_layernorm.bias": "model-00006-of-00007.safetensors", "transformer.h.7.input_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors", "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors", "transformer.h.7.self_attention.dense.weight": "model-00006-of-00007.safetensors", "transformer.h.7.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors", "transformer.h.8.input_layernorm.bias": "model-00006-of-00007.safetensors", "transformer.h.8.input_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors", "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors", "transformer.h.8.self_attention.dense.weight": "model-00006-of-00007.safetensors", "transformer.h.8.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors", "transformer.h.9.input_layernorm.bias": "model-00006-of-00007.safetensors", "transformer.h.9.input_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors", "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00007-of-00007.safetensors", "transformer.h.9.self_attention.dense.weight": "model-00007-of-00007.safetensors", "transformer.h.9.self_attention.query_key_value.weight": "model-00007-of-00007.safetensors", "transformer.ln_f.bias": "model-00007-of-00007.safetensors", "transformer.ln_f.weight": "model-00007-of-00007.safetensors", "transformer.word_embeddings.weight": "model-00007-of-00007.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"
+}