Upload folder using huggingface_hub

README.md

@@ -0,0 +1,51 @@
+---
+base_model:
+- microsoft/Phi-3-medium-128k-instruct
+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 using [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [0, 10]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [12, 14]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [16, 18]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [20, 32]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [34, 36]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [38, 40]
+merge_method: passthrough
+base_model: "microsoft/Phi-3-medium-128k-instruct"
+dtype: bfloat16
+```

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

config.json

@@ -0,0 +1,169 @@
+{
+  "_name_or_path": "microsoft/Phi-3-medium-128k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-medium-128k-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3-medium-128k-instruct--modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": null,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.25,
+      1.25,
+      1.5,
+      2.0,
+      2.75,
+      5.75,
+      5.75,
+      6.5,
+      9.25,
+      11.0,
+      13.25,
+      19.25,
+      19.75,
+      19.75,
+      21.25,
+      21.5,
+      26.5,
+      30.0,
+      33.75,
+      35.25,
+      38.5,
+      42.0,
+      42.25,
+      46.0,
+      47.0,
+      50.0,
+      50.5,
+      51.0,
+      52.0,
+      52.75,
+      53.75,
+      54.75,
+      57.0,
+      57.25,
+      58.5,
+      59.25,
+      59.5,
+      62.0,
+      62.5,
+      62.75,
+      63.25,
+      63.25,
+      63.25,
+      63.75,
+      64.0,
+      64.0,
+      64.25,
+      64.5,
+      64.5,
+      65.0,
+      65.0
+    ],
+    "short_factor": [
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.01,
+      1.02,
+      1.02,
+      1.04,
+      1.04,
+      1.07,
+      1.07,
+      1.1,
+      1.3000000000000003,
+      1.3000000000000003,
+      1.5000000000000004,
+      1.5700000000000005,
+      1.9000000000000008,
+      2.3100000000000014,
+      2.759999999999992,
+      3.3899999999999784,
+      3.9399999999999666,
+      4.009999999999965,
+      4.289999999999959,
+      4.349999999999958,
+      5.349999999999937,
+      6.659999999999909,
+      7.029999999999901,
+      7.51999999999989,
+      8.00999999999988,
+      8.249999999999876,
+      8.279999999999875,
+      9.629999999999846,
+      9.89999999999984,
+      10.589999999999826,
+      11.049999999999816,
+      11.7899999999998,
+      12.189999999999792,
+      12.889999999999777,
+      13.129999999999772,
+      13.16999999999977,
+      13.20999999999977,
+      13.479999999999764,
+      13.539999999999763,
+      13.779999999999758,
+      13.929999999999755,
+      14.429999999999744,
+      14.759999999999737,
+      15.149999999999729,
+      15.419999999999723,
+      15.53999999999972,
+      15.659999999999718,
+      15.749999999999716,
+      15.759999999999716,
+      15.799999999999715,
+      16.05999999999971,
+      16.079999999999714,
+      16.11999999999972,
+      16.11999999999972,
+      16.18999999999973,
+      16.31999999999975,
+      16.539999999999786,
+      16.799999999999827
+    ],
+    "type": "su"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+slices:
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [0, 10]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [12, 14]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [16, 18]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [20, 32]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [34, 36]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [38, 40]
+merge_method: passthrough
+base_model: "microsoft/Phi-3-medium-128k-instruct"
+dtype: bfloat16

model-00001-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd319676683bc4a74924af0037f325b4bf9a313717cbfa30bf9b6b7cf69aee19
+size 840182216

model-00002-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd490d39eb5f9554d2d91cef03b3223b5a1b705d0237c5bc127fff02d5d46ad
+size 681595600

model-00003-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d1c3d5297c2f0799566f1c32a7bc0a26d322616bfab40a13a3e46471d5faf0
+size 681595608

model-00004-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db5a5bc001b0b38745ae78367fe9f74dfe64e2442fe4cb9e1272caaa242d3c4
+size 681595608

model-00005-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2434ac1a5f05236997e96ed7609f0263ff371919bade8e5ef02a385eedff8278
+size 681595608

model-00006-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f592f4512cdd79f81678d5918a6d4cebafe0dbf55480465b3c3410701a15c8
+size 681595608

model-00007-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f430f78944a070a3bbb83dc8f6a6ba93a4000a733937b09b2a83ca1813043812
+size 681595608

model-00008-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a21f9c214cb7f571a74acfec2c41cbd4e8c577d78beef8ada61f3b75f4e0aa
+size 681595600

model-00009-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dafbe49f58f8bc8682e661dd532c5262d4602bc7e3dbe3c5811a29a11d7a1ca5
+size 681595608

model-00010-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b65ad651e31ae4c4819b333bea50a8304861cf0a9c189d8496299abe011934e
+size 681595608

model-00011-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f94e74a300715f9d603fb229c4eceddd84250486f33afd83ebb04f85a93227
+size 681595608

model-00012-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb903d2540ee6d3897bd0c294afeb866aa38993802a7906f9cbb3dc2448f983
+size 681595608

model-00013-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe9d306d942e6622326f58ea57b6f26e05818e946e7627cccd7c2ef06c54910
+size 681595608

model-00014-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39811cfc2e713b576014c083ff9be15a1afec8a5f6f3fa8302877a72c5b06cc
+size 681595608

model-00015-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e571711a1a8f4f1c833984692e411afcbb81c43dfc49725dba8a4c21386d59c
+size 681595608

model-00016-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222394bd76ff287ed5c052dc6dd511f7066f7b101d607e6fe323a3bf1f644df
+size 681595608

model-00017-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3623df71c62c884ee72f9c923991b615cd8d06cd54cf9211d4c79ae20209fd1f
+size 681595608

model-00018-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca4acdcf26c6e677140922625e30afc10ba91783246db5770b90b1c0201b4ca
+size 681595608

model-00019-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c2098ebd1fb3a8e7e6dccd7a3750e8b4d4a6db23461356004e70ad590208c6
+size 681595600

model-00020-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3803958f6e56a2528cb2c2edf22ab22efb0260c81b538441307ccffc513be16c
+size 681595608

model-00021-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafb16df0bd1ff9ab1f8af3dbb73d11e31eabf463b3c9d2166db4813104db8b5
+size 681595608

model-00022-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e61c85c4b7d7d41d60184510786e60f3004a3615cfef8a647f6e7ff47ffcff7
+size 681595608

model-00023-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e3999422946e99cd4047e5e962a87d441a92f95bc1e5f0878a4008e2b731f8
+size 681595608

model-00024-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1fd0ac45d72e4dfda425aa51a70bc4fb8fb0a067e1afd18fb3d87996041925c
+size 681595608

model-00025-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16e2721ce00172f8d8e2e9d3a08e1027621cd7c7b084c54761d027460bf92df
+size 681595608

model-00026-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412667381303b0c97993e332326c9258b2af6c39ea360221e5d4b6b4c23c63e3
+size 681595600

model-00027-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d330ca4213583d70661b87b3dc7f4173f7c33f740b2d37fe602fb2d11d2b7276
+size 681595600

model-00028-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a415acc306d6630ee13a510f47263c6d9e46d464b3911a6f750a930a999617f5
+size 681595600

model-00029-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d08c807d59b0657456d3ff6f5b388b3833ed3c76baedfc95d8c2c843c962f2
+size 681595600

model-00030-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92756ceaf0d9d72001469db255b89d7457e2046c5c1cb399a8a638da30a0dda3
+size 681595600

model-00031-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd1f28d909b104be7815756f6c4cdc1a86c664b572de672e6e218975c0879ac
+size 498094672

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 21104527360}, "weight_map": {"lm_head.weight": "model-00001-of-00031.safetensors", "model.embed_tokens.weight": "model-00001-of-00031.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00031.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.qkv_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00004-of-00031.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00005-of-00031.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00006-of-00031.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00007-of-00031.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00008-of-00031.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00009-of-00031.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00010-of-00031.safetensors", "model.layers.16.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00011-of-00031.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00012-of-00031.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.18.self_attn.qkv_proj.weight": "model-00013-of-00031.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.19.self_attn.qkv_proj.weight": "model-00014-of-00031.safetensors", "model.layers.20.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.20.self_attn.qkv_proj.weight": "model-00015-of-00031.safetensors", "model.layers.21.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.21.self_attn.qkv_proj.weight": "model-00016-of-00031.safetensors", "model.layers.22.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.22.self_attn.qkv_proj.weight": "model-00017-of-00031.safetensors", "model.layers.23.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.23.self_attn.qkv_proj.weight": "model-00018-of-00031.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00019-of-00031.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.24.self_attn.qkv_proj.weight": "model-00020-of-00031.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.25.self_attn.qkv_proj.weight": "model-00021-of-00031.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.26.self_attn.qkv_proj.weight": "model-00022-of-00031.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.27.self_attn.qkv_proj.weight": "model-00023-of-00031.safetensors", "model.layers.28.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.28.self_attn.qkv_proj.weight": "model-00024-of-00031.safetensors", "model.layers.29.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.29.self_attn.qkv_proj.weight": "model-00025-of-00031.safetensors", "model.layers.4.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00026-of-00031.safetensors", "model.layers.5.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00027-of-00031.safetensors", "model.layers.6.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00028-of-00031.safetensors", "model.layers.7.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00029-of-00031.safetensors", "model.layers.8.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00031-of-00031.safetensors", "model.norm.weight": "model-00031-of-00031.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,129 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}