Upload folder using huggingface_hub

README.md

@@ -0,0 +1,95 @@
+---
+base_model:
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+- microsoft/Phi-3-medium-128k-instruct
+tags:
+- merge
+- mergekit
+- lazymergekit
+- microsoft/Phi-3-medium-128k-instruct
+---
+
+# experiment-13
+
+experiment-13 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+- sources:
+  - layer_range: [0, 4]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [5, 8]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [9, 12]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [13, 16]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [17, 20]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [21, 24]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [25, 28]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [29, 32]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [33, 36]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [37, 40]
+    model: microsoft/Phi-3-medium-128k-instruct
+merge_method: passthrough
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "KingNish/experiment-13"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

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 +1,170 @@
+{
+  "_name_or_path": "microsoft/Phi-3-medium-128k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 31,
+  "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": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 32064
+}

mergekit_config.yml

@@ -0,0 +1,34 @@
+
+slices:
+- sources:
+  - layer_range: [0, 4]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [5, 8]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [9, 12]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [13, 16]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [17, 20]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [21, 24]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [25, 28]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [29, 32]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [33, 36]
+    model: microsoft/Phi-3-medium-128k-instruct
+- sources:
+  - layer_range: [37, 40]
+    model: microsoft/Phi-3-medium-128k-instruct
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00032.safetensors

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

model-00002-of-00032.safetensors

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

model-00003-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151e672eb67fc415885357c6d4dc1b1ceb86aab76cb6a613a9bf900aad894c18
+size 681595600

model-00004-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2484c2c07276a0f41ac8c6b9765da108df6e7ae27dad6ac89efa6a2b5590f2d
+size 681595600

model-00005-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b684ed782f0e47eecbb16b96996ec3bab019a904f24ea00ead8b4840d133cc9
+size 681595600

model-00006-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386d6cb5c81afe269b0c0013eb2848f790f5fb667b2e2c9102ba698a39c8e474
+size 681595608

model-00007-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:850f61d02b395bac15e537c3eb085d2719ece1ebdee415e7e7abbe307e228dc4
+size 681595608

model-00008-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa298523147c4260d79d791a0261a8c902dabc17d53f26585d7978a400cb095
+size 681595608

model-00009-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a01ce07beab6726ba210ce142b8dee4c863b318bbe53768f3432a4c0daff14
+size 681595608

model-00010-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a33cfa93b23893047ba4c9962c1f949c2cc7cdcb19562b75bc6b751ce3b9b80
+size 681595608

model-00011-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136a39745f175fa746a1d31da04701ed88579b546f69c0711eca6d519c7d7f09
+size 681595608

model-00012-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f0f1a587f0110447c0d5f5d4e8e85b97470152791af9f6a509254800bad717
+size 681595600

model-00013-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48da3783e481692773a09426cf505b412fbd8fad402bf947f18128f878758ea2
+size 681595608

model-00014-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d219c5be8c978703ee0ca6c44abc1cbbee7f406a80c908a516405437f4c70ef
+size 681595608

model-00015-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7acc70815f3313b3c8964316078a696990feac0c2ac8329145581e7f78d097e7
+size 681595608

model-00016-of-00032.safetensors

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

model-00017-of-00032.safetensors

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

model-00018-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9639b8863dfd88c6f43da714cff3e020807210c73dcc1c0403c7107f0679fc3b
+size 681595608

model-00019-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc6e235ed9c47e7a6f0df6c7ed9e79a934a8e94e8e7924da9aa7e874c31283e
+size 681595608

model-00020-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8291e08085c0a39491fc4be5fb3583c724093abbf74c856bfe3ab4ff9435fb
+size 681595600

model-00021-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5286ae17e11699cd2fe060ebbf23747e3f6ea24f16b1b9b23a5d21f3dda7c209
+size 681595608

model-00022-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37539ed55b8e960bea7db4424bb7881df4d3c90cca8ac5f5eacce37c8489fa7
+size 681595608

model-00023-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426e6e7c92a90f06367c118742d098f9bc4871a21eff24569ac1a5b8e2a7a4a1
+size 681595608

model-00024-of-00032.safetensors

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

model-00025-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750c1b28b948a2109a53c4cbce7053a4cdeb13956bd17bd0e42074539664d5ac
+size 681595608

model-00026-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0525907323f2159c01c5880819d5def306a360bb80490564c82501963a3ef548
+size 681595608

model-00027-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7347d8ba5889a6371165dfb03a7d11e598bbfb27314941d3a6792c40344e593
+size 681595608

model-00028-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74f7e9d0e7f0b51aef56bd7198c2ac1d16a9672b65ecff38be9c723379a9d7f
+size 681595608

model-00029-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5c5612141e1ac1f66b6baea5398d7bbc3ef3c5ac76fcc43f383de1c4f85d97
+size 681595600

model-00030-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1b9945676e4d5420bda0151f8cdd14c9af436422baaa17b196de2c25d0ae92
+size 681595600

model-00031-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847fd1ed7c3dbd846d8525a6dd8591307b89c53d11f1221ce92119057c2f0853
+size 681595600

model-00032-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2416250a366e93961e4f1f1333847557564c02df2dd81d9ce947181af997f319
+size 498094672

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 21786122240}, "weight_map": {"lm_head.weight": "model-00001-of-00032.safetensors", "model.embed_tokens.weight": "model-00001-of-00032.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00032.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00032.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00002-of-00032.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00032.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00032.safetensors", "model.layers.0.self_attn.qkv_proj.weight": "model-00002-of-00032.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00032.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00032.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00003-of-00032.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00032.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00032.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00003-of-00032.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00032.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00032.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00004-of-00032.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00032.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00032.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00004-of-00032.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00032.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00032.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00005-of-00032.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00032.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00032.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00005-of-00032.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00032.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00032.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00006-of-00032.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00032.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00032.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00006-of-00032.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00032.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00032.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00007-of-00032.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00032.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00032.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00007-of-00032.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00032.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00032.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00008-of-00032.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00032.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00032.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00008-of-00032.safetensors", "model.layers.13.input_layernorm.weight": "model-00008-of-00032.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00008-of-00032.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00009-of-00032.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00032.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00032.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00009-of-00032.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00032.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00032.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00010-of-00032.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00032.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00032.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00010-of-00032.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00032.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00010-of-00032.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00011-of-00032.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00032.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00032.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00011-of-00032.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00032.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00032.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00012-of-00032.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00032.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00032.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00012-of-00032.safetensors", "model.layers.16.input_layernorm.weight": "model-00012-of-00032.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00012-of-00032.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00013-of-00032.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00013-of-00032.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00032.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00013-of-00032.safetensors", "model.layers.17.input_layernorm.weight": "model-00013-of-00032.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00013-of-00032.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00014-of-00032.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00032.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00032.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00014-of-00032.safetensors", "model.layers.18.input_layernorm.weight": "model-00014-of-00032.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00014-of-00032.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00015-of-00032.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00015-of-00032.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00032.safetensors", "model.layers.18.self_attn.qkv_proj.weight": "model-00015-of-00032.safetensors", "model.layers.19.input_layernorm.weight": "model-00015-of-00032.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00015-of-00032.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00016-of-00032.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00016-of-00032.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00016-of-00032.safetensors", "model.layers.19.self_attn.qkv_proj.weight": "model-00016-of-00032.safetensors", "model.layers.20.input_layernorm.weight": "model-00016-of-00032.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00016-of-00032.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00017-of-00032.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00017-of-00032.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00017-of-00032.safetensors", "model.layers.20.self_attn.qkv_proj.weight": "model-00017-of-00032.safetensors", "model.layers.21.input_layernorm.weight": "model-00017-of-00032.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00017-of-00032.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00018-of-00032.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00032.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00018-of-00032.safetensors", "model.layers.21.self_attn.qkv_proj.weight": "model-00018-of-00032.safetensors", "model.layers.22.input_layernorm.weight": "model-00018-of-00032.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00018-of-00032.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00019-of-00032.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00019-of-00032.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00032.safetensors", "model.layers.22.self_attn.qkv_proj.weight": "model-00019-of-00032.safetensors", "model.layers.3.input_layernorm.weight": "model-00019-of-00032.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00019-of-00032.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00020-of-00032.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00032.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00032.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00020-of-00032.safetensors", "model.layers.23.input_layernorm.weight": "model-00020-of-00032.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00020-of-00032.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00021-of-00032.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00021-of-00032.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00021-of-00032.safetensors", "model.layers.23.self_attn.qkv_proj.weight": "model-00021-of-00032.safetensors", "model.layers.24.input_layernorm.weight": "model-00021-of-00032.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00021-of-00032.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00022-of-00032.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00022-of-00032.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00022-of-00032.safetensors", "model.layers.24.self_attn.qkv_proj.weight": "model-00022-of-00032.safetensors", "model.layers.25.input_layernorm.weight": "model-00022-of-00032.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00022-of-00032.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00023-of-00032.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00023-of-00032.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00023-of-00032.safetensors", "model.layers.25.self_attn.qkv_proj.weight": "model-00023-of-00032.safetensors", "model.layers.26.input_layernorm.weight": "model-00023-of-00032.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00023-of-00032.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00024-of-00032.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00024-of-00032.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00024-of-00032.safetensors", "model.layers.26.self_attn.qkv_proj.weight": "model-00024-of-00032.safetensors", "model.layers.27.input_layernorm.weight": "model-00024-of-00032.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00024-of-00032.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00025-of-00032.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00025-of-00032.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00025-of-00032.safetensors", "model.layers.27.self_attn.qkv_proj.weight": "model-00025-of-00032.safetensors", "model.layers.28.input_layernorm.weight": "model-00025-of-00032.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00025-of-00032.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00026-of-00032.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00026-of-00032.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00026-of-00032.safetensors", "model.layers.28.self_attn.qkv_proj.weight": "model-00026-of-00032.safetensors", "model.layers.29.input_layernorm.weight": "model-00026-of-00032.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00026-of-00032.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00027-of-00032.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00027-of-00032.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00027-of-00032.safetensors", "model.layers.29.self_attn.qkv_proj.weight": "model-00027-of-00032.safetensors", "model.layers.30.input_layernorm.weight": "model-00027-of-00032.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00027-of-00032.safetensors", "model.layers.30.mlp.gate_up_proj.weight": "model-00028-of-00032.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00028-of-00032.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00028-of-00032.safetensors", "model.layers.30.self_attn.qkv_proj.weight": "model-00028-of-00032.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00032.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00028-of-00032.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00029-of-00032.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00029-of-00032.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00029-of-00032.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00029-of-00032.safetensors", "model.layers.5.input_layernorm.weight": "model-00029-of-00032.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00029-of-00032.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00030-of-00032.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00030-of-00032.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00030-of-00032.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00030-of-00032.safetensors", "model.layers.6.input_layernorm.weight": "model-00030-of-00032.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00030-of-00032.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00031-of-00032.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00031-of-00032.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00031-of-00032.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00031-of-00032.safetensors", "model.layers.7.input_layernorm.weight": "model-00031-of-00032.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00031-of-00032.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00032-of-00032.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00032-of-00032.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00032-of-00032.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00032-of-00032.safetensors", "model.norm.weight": "model-00032-of-00032.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 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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|>",
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}