Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+---
+base_model:
+- prithivMLmods/Taurus-Opus-7B
+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:
+* [prithivMLmods/Taurus-Opus-7B](https://huggingface.co/prithivMLmods/Taurus-Opus-7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: prithivMLmods/Taurus-Opus-7B
+      layer_range: [0, 14]
+    - model: prithivMLmods/Taurus-Opus-7B
+      layer_range: [14, 28]
+merge_method: passthrough
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "prithivMLmods/Taurus-Opus-7B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 4,
+  "pad_token_id": 2023,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000042,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,8 @@
+slices:
+  - sources:
+    - model: prithivMLmods/Taurus-Opus-7B
+      layer_range: [0, 14]
+    - model: prithivMLmods/Taurus-Opus-7B
+      layer_range: [14, 28]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca8471326533cfbda87136624d0fbfb66c32b75b0bc3f09641cffaaed91a787
+size 805306496

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bdabfde62d0f37ae6467c6fe6db53f685949b6777ae73bfb595f34dcccd2cf
+size 946870632

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7268fc734694edb569d264eb00046ed5aea8ea8b99bd379cfaefd7acafdcea
+size 950036512

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8e7c50214c88e8f54aa59432472e4fdac459c5ba6f0f44418c994107800922
+size 950036512

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3877b5807b30058cb9d7690f84661bce65e5f5a49ba0614b79a17e62e104ae
+size 950036512

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ee0422e1b66a84f67fb3097c72bc68d0accf539e1278284d6d94a3311f785b
+size 950036512

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebf3c5ddce837c196f2aaeb059e989739e384414dd31cf2be0b47ec8e61fc1a
+size 950036504

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab1daef2b38f69982437a9a65040722785baa5f0c1a8db285b9d032c84f5c57
+size 950036536

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7e9a5142154c83a590ce923e3a61bbe892a4b9d51aef2ea03609b65159e2e2
+size 808478640

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 8260859904}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00002-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>EMAIL_ADDRESS<<",
+    ">>IP_ADDRESS<<",
+    "<|startoftext|>",
+    ">>IP_ADDRESS_0<<",
+    ">>IP_ADDRESS_1<<",
+    ">>IP_ADDRESS_2<<",
+    ">>IP_ADDRESS_3<<",
+    ">>IP_ADDRESS_4<<",
+    ">>IP_ADDRESS_5<<",
+    ">>IP_ADDRESS_6<<",
+    ">>IP_ADDRESS_7<<",
+    ">>IP_ADDRESS_8<<",
+    ">>IP_ADDRESS_9<<",
+    ">>PASSWORD<<",
+    ">>KEY<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}