Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+base_model:
+- microsoft/Phi-3-small-128k-instruct
+- microsoft/Phi-3-small-8k-instruct
+tags:
+- merge
+- mergekit
+- lazymergekit
+- microsoft/Phi-3-small-128k-instruct
+- microsoft/Phi-3-small-8k-instruct
+---
+
+# PRYMMAL-ECE-7B-SLERP-V1
+
+PRYMMAL-ECE-7B-SLERP-V1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [microsoft/Phi-3-small-128k-instruct](https://huggingface.co/microsoft/Phi-3-small-128k-instruct)
+* [microsoft/Phi-3-small-8k-instruct](https://huggingface.co/microsoft/Phi-3-small-8k-instruct)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: microsoft/Phi-3-small-128k-instruct
+        layer_range: [0, 32]
+      - model: microsoft/Phi-3-small-8k-instruct
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: microsoft/Phi-3-small-128k-instruct
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "LilRg/PRYMMAL-ECE-7B-SLERP-V1"
+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"])
+```

config.json

@@ -0,0 +1,187 @@
+{
+  "_name_or_path": "microsoft/Phi-3-small-128k-instruct",
+  "architectures": [
+    "Phi3SmallForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-small-128k-instruct--configuration_phi3_small.Phi3SmallConfig",
+    "AutoModelForCausalLM": "microsoft/Phi-3-small-128k-instruct--modeling_phi3_small.Phi3SmallForCausalLM",
+    "AutoTokenizer": "microsoft/Phi-3-small-128k-instruct--tokenization_phi3_small.Phi3SmallTokenizer"
+  },
+  "blocksparse_block_size": 64,
+  "blocksparse_homo_head_pattern": false,
+  "blocksparse_num_local_blocks": 16,
+  "blocksparse_triton_kernel_block_size": 64,
+  "blocksparse_vert_stride": 8,
+  "bos_token_id": 100257,
+  "dense_attention_every_n_layers": 2,
+  "embedding_dropout_prob": 0.1,
+  "eos_token_id": 100257,
+  "ff_dim_multiplier": null,
+  "ff_intermediate_size": 14336,
+  "ffn_dropout_prob": 0.1,
+  "gegelu_limit": 20.0,
+  "gegelu_pad_to_256": true,
+  "hidden_act": "gegelu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3small",
+  "mup_attn_multiplier": 1.0,
+  "mup_embedding_multiplier": 10.0,
+  "mup_use_scaling": true,
+  "mup_width_multiplier": 8.0,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 8192,
+  "pad_sequence_to_multiple_of_64": true,
+  "reorder_and_upcast_attn": false,
+  "rope_embedding_base": 1000000,
+  "rope_position_scale": 1.0,
+  "rope_scaling": {
+    "long_factor": [
+      1.0,
+      1.01,
+      1.01,
+      1.02,
+      1.04,
+      1.04,
+      1.04,
+      1.05,
+      1.05,
+      1.06,
+      1.07,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.09,
+      1.09,
+      1.2,
+      2.31,
+      3.76,
+      9.38,
+      10.1,
+      10.8,
+      18.1,
+      25.2,
+      25.3,
+      26.1,
+      26.6,
+      30.2,
+      33.0,
+      41.5,
+      44.4,
+      44.8,
+      50.2,
+      51.9,
+      59.3,
+      62.7,
+      66.1,
+      66.3,
+      85.8,
+      89.3,
+      90.0,
+      99.9,
+      107.0,
+      110.0,
+      111.0,
+      117.0,
+      118.0,
+      121.0,
+      122.0,
+      127.0,
+      127.0,
+      128.0,
+      128.0,
+      128.0,
+      128.0,
+      128.0,
+      128.0,
+      129.0,
+      129.0,
+      129.0
+    ],
+    "long_mscale": 1.1902380714238083,
+    "original_max_position_embeddings": 8192,
+    "short_factor": [
+      1.02,
+      1.02,
+      1.05,
+      1.05,
+      1.06,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.12,
+      1.1800000000000002,
+      1.1900000000000002,
+      1.1900000000000002,
+      1.2100000000000002,
+      1.2300000000000002,
+      1.2400000000000002,
+      1.2400000000000002,
+      1.2500000000000002,
+      1.3000000000000003,
+      1.3100000000000003,
+      1.4600000000000004,
+      1.5100000000000005,
+      1.7000000000000006,
+      1.9300000000000008,
+      2.080000000000001,
+      2.4399999999999933,
+      3.2199999999999767,
+      3.4499999999999718,
+      3.579999999999969,
+      4.669999999999946,
+      4.779999999999943,
+      5.999999999999917,
+      6.009999999999917,
+      6.4199999999999084,
+      6.619999999999904,
+      7.189999999999892,
+      7.3099999999998895,
+      7.339999999999889,
+      7.479999999999886,
+      9.749999999999837,
+      10.919999999999812,
+      11.219999999999805,
+      11.749999999999794,
+      11.979999999999789,
+      13.239999999999762,
+      13.579999999999755,
+      13.669999999999753,
+      13.82999999999975,
+      14.009999999999746,
+      14.679999999999731,
+      14.889999999999727,
+      15.769999999999708,
+      15.769999999999708,
+      15.819999999999707,
+      15.839999999999707,
+      15.919999999999705,
+      16.029999999999703,
+      16.12999999999972,
+      16.44999999999977,
+      16.44999999999977,
+      16.77999999999982,
+      16.83999999999983,
+      16.83999999999983,
+      16.889999999999837
+    ],
+    "short_mscale": 1.0,
+    "type": "su"
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 100352
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: microsoft/Phi-3-small-128k-instruct
+        layer_range: [0, 32]
+      - model: microsoft/Phi-3-small-8k-instruct
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: microsoft/Phi-3-small-128k-instruct
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a23c9ab1479aa4ac2209ed8adad413250eeba52cf71e83c0d285b36a68ddb0
+size 822083712

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27f87a6aa177be0cf900c6f9c44f25c7f06bfcae32e2ddb1c7619af39d523fb
+size 939623272

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98548c390b6b80525e8d86c636712d080974ca44f1d450b18f027c47c965517
+size 872655528

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193d4689c8e479b7b9cb7d75627d32935c75c7600cb2841470baac1ca89ee07e
+size 872655552

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bdae4d8c3f61b4e1fe58e0b798039482d31a8201d63d68d5619dacdb17930f
+size 872655552

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041c2b274190a9392d9b451f47f7a7927c00a9b427ab50823d33a3bb7e0b8076
+size 872655552

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f55b5223bc20e92ceea5abf29b765d8fade6fe06023ffff34c95a03ae68ae0
+size 872655552

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4797e7e17dd3fd41a89da1e558d35ed57b55462d5f16298753a823ce1b1340
+size 872655544

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d335ea056ec36ca8558d3965e4a9ee61a783f79ffa33c2ac4439c46d875461ed
+size 872655544

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d2794841c03b740e4ccf40bf0f260d95e77a333b6869f54664d0a19c33d406
+size 872655552

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d286dbf9be63f1ec842bea32d42ae1b0d5dbe5b329759672a2163cb9ce70c886
+size 872655552

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f126e531d330f1cc99ddbf665709d3c996f285594a8cc4e88fa169c6ce5f8e4
+size 872655552

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35911ae605e95bbb4b83e3fec2e597e027d47eed850f72d499ee56206a40e7d7
+size 872655552

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb7528c99ea141827bb220931acad54b41f53f63830f1b739b2315ad8c29a3a
+size 872655536

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103e51b9baead04dfae6b63110a3f842e8832f0eb9889663a932adf1cea9fbb4
+size 872655544

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556cf6496ec60a6ee4487c6e5fb4fb6594376ea601da3793e067d1a638381b09
+size 872655528

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ce15feea7c804e7af4714cd35bcbd2d84ff548ecdbb385478af7c800239c09
+size 872655528

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2dea660fb0e3579c77b84f82955106ac162207a078b015e62e43667607e76d9
+size 755132552

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 15606628352}, "weight_map": {"lm_head.weight": "model-00001-of-00018.safetensors", "model.embed_tokens.weight": "model-00002-of-00018.safetensors", "model.final_layernorm.bias": "model-00002-of-00018.safetensors", "model.final_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.0.input_layernorm.bias": "model-00002-of-00018.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.0.mlp.down_proj.bias": "model-00002-of-00018.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.0.mlp.up_proj.bias": "model-00002-of-00018.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.0.post_attention_layernorm.bias": "model-00003-of-00018.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.dense.bias": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.dense.weight": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.query_key_value.bias": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.query_key_value.weight": "model-00003-of-00018.safetensors", "model.layers.1.input_layernorm.bias": "model-00003-of-00018.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.1.mlp.down_proj.bias": "model-00003-of-00018.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.mlp.up_proj.bias": "model-00003-of-00018.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.post_attention_layernorm.bias": "model-00003-of-00018.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.dense.bias": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.dense.weight": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.query_key_value.bias": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.query_key_value.weight": "model-00003-of-00018.safetensors", "model.layers.10.input_layernorm.bias": "model-00003-of-00018.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.10.mlp.down_proj.bias": "model-00003-of-00018.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.10.mlp.up_proj.bias": "model-00003-of-00018.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.post_attention_layernorm.bias": "model-00004-of-00018.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.dense.bias": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.dense.weight": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.query_key_value.bias": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.query_key_value.weight": "model-00004-of-00018.safetensors", "model.layers.11.input_layernorm.bias": "model-00004-of-00018.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.11.mlp.down_proj.bias": "model-00004-of-00018.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.11.mlp.up_proj.bias": "model-00004-of-00018.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.11.post_attention_layernorm.bias": "model-00004-of-00018.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.11.self_attn.dense.bias": "model-00004-of-00018.safetensors", "model.layers.11.self_attn.dense.weight": "model-00004-of-00018.safetensors", "model.layers.11.self_attn.query_key_value.bias": "model-00004-of-00018.safetensors", "model.layers.11.self_attn.query_key_value.weight": "model-00004-of-00018.safetensors", "model.layers.12.input_layernorm.bias": "model-00004-of-00018.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.12.mlp.down_proj.bias": "model-00004-of-00018.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.12.mlp.up_proj.bias": "model-00004-of-00018.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.12.post_attention_layernorm.bias": "model-00005-of-00018.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.12.self_attn.dense.bias": "model-00005-of-00018.safetensors", "model.layers.12.self_attn.dense.weight": "model-00005-of-00018.safetensors", "model.layers.12.self_attn.query_key_value.bias": "model-00005-of-00018.safetensors", "model.layers.12.self_attn.query_key_value.weight": "model-00005-of-00018.safetensors", "model.layers.13.input_layernorm.bias": "model-00005-of-00018.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.13.mlp.down_proj.bias": "model-00005-of-00018.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.13.mlp.up_proj.bias": "model-00005-of-00018.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.13.post_attention_layernorm.bias": "model-00005-of-00018.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.13.self_attn.dense.bias": "model-00005-of-00018.safetensors", "model.layers.13.self_attn.dense.weight": "model-00005-of-00018.safetensors", "model.layers.13.self_attn.query_key_value.bias": "model-00005-of-00018.safetensors", "model.layers.13.self_attn.query_key_value.weight": "model-00005-of-00018.safetensors", "model.layers.14.input_layernorm.bias": "model-00005-of-00018.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.14.mlp.down_proj.bias": "model-00005-of-00018.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.14.mlp.up_proj.bias": "model-00005-of-00018.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.14.post_attention_layernorm.bias": "model-00006-of-00018.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.14.self_attn.dense.bias": "model-00006-of-00018.safetensors", "model.layers.14.self_attn.dense.weight": "model-00006-of-00018.safetensors", "model.layers.14.self_attn.query_key_value.bias": "model-00006-of-00018.safetensors", "model.layers.14.self_attn.query_key_value.weight": "model-00006-of-00018.safetensors", "model.layers.15.input_layernorm.bias": "model-00006-of-00018.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.15.mlp.down_proj.bias": "model-00006-of-00018.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.15.mlp.up_proj.bias": "model-00006-of-00018.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.15.post_attention_layernorm.bias": "model-00006-of-00018.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.15.self_attn.dense.bias": "model-00006-of-00018.safetensors", "model.layers.15.self_attn.dense.weight": "model-00006-of-00018.safetensors", "model.layers.15.self_attn.query_key_value.bias": "model-00006-of-00018.safetensors", "model.layers.15.self_attn.query_key_value.weight": "model-00006-of-00018.safetensors", "model.layers.16.input_layernorm.bias": "model-00006-of-00018.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.16.mlp.down_proj.bias": "model-00006-of-00018.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.16.mlp.up_proj.bias": "model-00006-of-00018.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.16.post_attention_layernorm.bias": "model-00007-of-00018.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.16.self_attn.dense.bias": "model-00007-of-00018.safetensors", "model.layers.16.self_attn.dense.weight": "model-00007-of-00018.safetensors", "model.layers.16.self_attn.query_key_value.bias": "model-00007-of-00018.safetensors", "model.layers.16.self_attn.query_key_value.weight": "model-00007-of-00018.safetensors", "model.layers.17.input_layernorm.bias": "model-00007-of-00018.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.17.mlp.down_proj.bias": "model-00007-of-00018.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.17.mlp.up_proj.bias": "model-00007-of-00018.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.17.post_attention_layernorm.bias": "model-00007-of-00018.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.17.self_attn.dense.bias": "model-00007-of-00018.safetensors", "model.layers.17.self_attn.dense.weight": "model-00007-of-00018.safetensors", "model.layers.17.self_attn.query_key_value.bias": "model-00007-of-00018.safetensors", "model.layers.17.self_attn.query_key_value.weight": "model-00007-of-00018.safetensors", "model.layers.18.input_layernorm.bias": "model-00007-of-00018.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.18.mlp.down_proj.bias": "model-00007-of-00018.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.18.mlp.up_proj.bias": "model-00007-of-00018.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.18.post_attention_layernorm.bias": "model-00008-of-00018.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.18.self_attn.dense.bias": "model-00008-of-00018.safetensors", "model.layers.18.self_attn.dense.weight": "model-00008-of-00018.safetensors", "model.layers.18.self_attn.query_key_value.bias": "model-00008-of-00018.safetensors", "model.layers.18.self_attn.query_key_value.weight": "model-00008-of-00018.safetensors", "model.layers.19.input_layernorm.bias": "model-00008-of-00018.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.19.mlp.down_proj.bias": "model-00008-of-00018.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.19.mlp.up_proj.bias": "model-00008-of-00018.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.19.post_attention_layernorm.bias": "model-00008-of-00018.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.19.self_attn.dense.bias": "model-00008-of-00018.safetensors", "model.layers.19.self_attn.dense.weight": "model-00008-of-00018.safetensors", "model.layers.19.self_attn.query_key_value.bias": "model-00008-of-00018.safetensors", "model.layers.19.self_attn.query_key_value.weight": "model-00008-of-00018.safetensors", "model.layers.2.input_layernorm.bias": "model-00008-of-00018.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.2.mlp.down_proj.bias": "model-00008-of-00018.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.2.mlp.up_proj.bias": "model-00008-of-00018.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.2.post_attention_layernorm.bias": "model-00009-of-00018.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.2.self_attn.dense.bias": "model-00009-of-00018.safetensors", "model.layers.2.self_attn.dense.weight": "model-00009-of-00018.safetensors", "model.layers.2.self_attn.query_key_value.bias": "model-00009-of-00018.safetensors", "model.layers.2.self_attn.query_key_value.weight": "model-00009-of-00018.safetensors", "model.layers.20.input_layernorm.bias": "model-00009-of-00018.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.20.mlp.down_proj.bias": "model-00009-of-00018.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.20.mlp.up_proj.bias": "model-00009-of-00018.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.20.post_attention_layernorm.bias": "model-00009-of-00018.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.20.self_attn.dense.bias": "model-00009-of-00018.safetensors", "model.layers.20.self_attn.dense.weight": "model-00009-of-00018.safetensors", "model.layers.20.self_attn.query_key_value.bias": "model-00009-of-00018.safetensors", "model.layers.20.self_attn.query_key_value.weight": "model-00009-of-00018.safetensors", "model.layers.21.input_layernorm.bias": "model-00009-of-00018.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.21.mlp.down_proj.bias": "model-00009-of-00018.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.21.mlp.up_proj.bias": "model-00009-of-00018.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.21.post_attention_layernorm.bias": "model-00010-of-00018.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.21.self_attn.dense.bias": "model-00010-of-00018.safetensors", "model.layers.21.self_attn.dense.weight": "model-00010-of-00018.safetensors", "model.layers.21.self_attn.query_key_value.bias": "model-00010-of-00018.safetensors", "model.layers.21.self_attn.query_key_value.weight": "model-00010-of-00018.safetensors", "model.layers.22.input_layernorm.bias": "model-00010-of-00018.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.22.mlp.down_proj.bias": "model-00010-of-00018.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.22.mlp.up_proj.bias": "model-00010-of-00018.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.22.post_attention_layernorm.bias": "model-00010-of-00018.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.22.self_attn.dense.bias": "model-00010-of-00018.safetensors", "model.layers.22.self_attn.dense.weight": "model-00010-of-00018.safetensors", "model.layers.22.self_attn.query_key_value.bias": "model-00010-of-00018.safetensors", "model.layers.22.self_attn.query_key_value.weight": "model-00010-of-00018.safetensors", "model.layers.23.input_layernorm.bias": "model-00010-of-00018.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.23.mlp.down_proj.bias": "model-00010-of-00018.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.23.mlp.up_proj.bias": "model-00010-of-00018.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.23.post_attention_layernorm.bias": "model-00011-of-00018.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.23.self_attn.dense.bias": "model-00011-of-00018.safetensors", "model.layers.23.self_attn.dense.weight": "model-00011-of-00018.safetensors", "model.layers.23.self_attn.query_key_value.bias": "model-00011-of-00018.safetensors", "model.layers.23.self_attn.query_key_value.weight": "model-00011-of-00018.safetensors", "model.layers.24.input_layernorm.bias": "model-00011-of-00018.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.24.mlp.down_proj.bias": "model-00011-of-00018.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.24.mlp.up_proj.bias": "model-00011-of-00018.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.24.post_attention_layernorm.bias": "model-00011-of-00018.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.24.self_attn.dense.bias": "model-00011-of-00018.safetensors", "model.layers.24.self_attn.dense.weight": "model-00011-of-00018.safetensors", "model.layers.24.self_attn.query_key_value.bias": "model-00011-of-00018.safetensors", "model.layers.24.self_attn.query_key_value.weight": "model-00011-of-00018.safetensors", "model.layers.25.input_layernorm.bias": "model-00011-of-00018.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.25.mlp.down_proj.bias": "model-00011-of-00018.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.25.mlp.up_proj.bias": "model-00011-of-00018.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.25.post_attention_layernorm.bias": "model-00012-of-00018.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.25.self_attn.dense.bias": "model-00012-of-00018.safetensors", "model.layers.25.self_attn.dense.weight": "model-00012-of-00018.safetensors", "model.layers.25.self_attn.query_key_value.bias": "model-00012-of-00018.safetensors", "model.layers.25.self_attn.query_key_value.weight": "model-00012-of-00018.safetensors", "model.layers.26.input_layernorm.bias": "model-00012-of-00018.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.26.mlp.down_proj.bias": "model-00012-of-00018.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.26.mlp.up_proj.bias": "model-00012-of-00018.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.26.post_attention_layernorm.bias": "model-00012-of-00018.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.26.self_attn.dense.bias": "model-00012-of-00018.safetensors", "model.layers.26.self_attn.dense.weight": "model-00012-of-00018.safetensors", "model.layers.26.self_attn.query_key_value.bias": "model-00012-of-00018.safetensors", "model.layers.26.self_attn.query_key_value.weight": "model-00012-of-00018.safetensors", "model.layers.27.input_layernorm.bias": "model-00012-of-00018.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.27.mlp.down_proj.bias": "model-00012-of-00018.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.27.mlp.up_proj.bias": "model-00012-of-00018.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.27.post_attention_layernorm.bias": "model-00013-of-00018.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.27.self_attn.dense.bias": "model-00013-of-00018.safetensors", "model.layers.27.self_attn.dense.weight": "model-00013-of-00018.safetensors", "model.layers.27.self_attn.query_key_value.bias": "model-00013-of-00018.safetensors", "model.layers.27.self_attn.query_key_value.weight": "model-00013-of-00018.safetensors", "model.layers.28.input_layernorm.bias": "model-00013-of-00018.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.28.mlp.down_proj.bias": "model-00013-of-00018.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.28.mlp.up_proj.bias": "model-00013-of-00018.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.28.post_attention_layernorm.bias": "model-00013-of-00018.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.28.self_attn.dense.bias": "model-00013-of-00018.safetensors", "model.layers.28.self_attn.dense.weight": "model-00013-of-00018.safetensors", "model.layers.28.self_attn.query_key_value.bias": "model-00013-of-00018.safetensors", "model.layers.28.self_attn.query_key_value.weight": "model-00013-of-00018.safetensors", "model.layers.29.input_layernorm.bias": "model-00013-of-00018.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.29.mlp.down_proj.bias": "model-00013-of-00018.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.29.mlp.up_proj.bias": "model-00013-of-00018.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.29.post_attention_layernorm.bias": "model-00014-of-00018.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.29.self_attn.dense.bias": "model-00014-of-00018.safetensors", "model.layers.29.self_attn.dense.weight": "model-00014-of-00018.safetensors", "model.layers.29.self_attn.query_key_value.bias": "model-00014-of-00018.safetensors", "model.layers.29.self_attn.query_key_value.weight": "model-00014-of-00018.safetensors", "model.layers.3.input_layernorm.bias": "model-00014-of-00018.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.3.mlp.down_proj.bias": "model-00014-of-00018.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.mlp.up_proj.bias": "model-00014-of-00018.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.post_attention_layernorm.bias": "model-00014-of-00018.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.dense.bias": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.dense.weight": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.query_key_value.bias": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.query_key_value.weight": "model-00014-of-00018.safetensors", "model.layers.30.input_layernorm.bias": "model-00014-of-00018.safetensors", "model.layers.30.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.30.mlp.down_proj.bias": "model-00014-of-00018.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.30.mlp.up_proj.bias": "model-00014-of-00018.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.30.post_attention_layernorm.bias": "model-00015-of-00018.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.30.self_attn.dense.bias": "model-00015-of-00018.safetensors", "model.layers.30.self_attn.dense.weight": "model-00015-of-00018.safetensors", "model.layers.30.self_attn.query_key_value.bias": "model-00015-of-00018.safetensors", "model.layers.30.self_attn.query_key_value.weight": "model-00015-of-00018.safetensors", "model.layers.31.input_layernorm.bias": "model-00015-of-00018.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.31.mlp.down_proj.bias": "model-00015-of-00018.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.31.mlp.up_proj.bias": "model-00015-of-00018.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.31.post_attention_layernorm.bias": "model-00015-of-00018.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.31.self_attn.dense.bias": "model-00015-of-00018.safetensors", "model.layers.31.self_attn.dense.weight": "model-00015-of-00018.safetensors", "model.layers.31.self_attn.query_key_value.bias": "model-00015-of-00018.safetensors", "model.layers.31.self_attn.query_key_value.weight": "model-00015-of-00018.safetensors", "model.layers.4.input_layernorm.bias": "model-00015-of-00018.safetensors", "model.layers.4.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.4.mlp.down_proj.bias": "model-00015-of-00018.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.4.mlp.up_proj.bias": "model-00015-of-00018.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.4.post_attention_layernorm.bias": "model-00016-of-00018.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.4.self_attn.dense.bias": "model-00016-of-00018.safetensors", "model.layers.4.self_attn.dense.weight": "model-00016-of-00018.safetensors", "model.layers.4.self_attn.query_key_value.bias": "model-00016-of-00018.safetensors", "model.layers.4.self_attn.query_key_value.weight": "model-00016-of-00018.safetensors", "model.layers.5.input_layernorm.bias": "model-00016-of-00018.safetensors", "model.layers.5.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.5.mlp.down_proj.bias": "model-00016-of-00018.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.5.mlp.up_proj.bias": "model-00016-of-00018.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.5.post_attention_layernorm.bias": "model-00016-of-00018.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.5.self_attn.dense.bias": "model-00016-of-00018.safetensors", "model.layers.5.self_attn.dense.weight": "model-00016-of-00018.safetensors", "model.layers.5.self_attn.query_key_value.bias": "model-00016-of-00018.safetensors", "model.layers.5.self_attn.query_key_value.weight": "model-00016-of-00018.safetensors", "model.layers.6.input_layernorm.bias": "model-00016-of-00018.safetensors", "model.layers.6.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.6.mlp.down_proj.bias": "model-00016-of-00018.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.6.mlp.up_proj.bias": "model-00016-of-00018.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.6.post_attention_layernorm.bias": "model-00017-of-00018.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.dense.bias": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.dense.weight": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.query_key_value.bias": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.query_key_value.weight": "model-00017-of-00018.safetensors", "model.layers.7.input_layernorm.bias": "model-00017-of-00018.safetensors", "model.layers.7.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.7.mlp.down_proj.bias": "model-00017-of-00018.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.7.mlp.up_proj.bias": "model-00017-of-00018.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.7.post_attention_layernorm.bias": "model-00017-of-00018.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.dense.bias": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.dense.weight": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.query_key_value.bias": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.query_key_value.weight": "model-00017-of-00018.safetensors", "model.layers.8.input_layernorm.bias": "model-00017-of-00018.safetensors", "model.layers.8.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.8.mlp.down_proj.bias": "model-00017-of-00018.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.mlp.up_proj.bias": "model-00017-of-00018.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.8.post_attention_layernorm.bias": "model-00018-of-00018.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.dense.bias": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.dense.weight": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.query_key_value.bias": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.query_key_value.weight": "model-00018-of-00018.safetensors", "model.layers.9.input_layernorm.bias": "model-00018-of-00018.safetensors", "model.layers.9.input_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.9.mlp.down_proj.bias": "model-00018-of-00018.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.mlp.up_proj.bias": "model-00018-of-00018.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.post_attention_layernorm.bias": "model-00018-of-00018.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.dense.bias": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.dense.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.query_key_value.bias": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.query_key_value.weight": "model-00018-of-00018.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "_commit_hash": "ad85cab62be398dc90203c4377a4ccbf090fbb36",
+  "_from_auto": true,
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_phi3_small.Phi3SmallTokenizer",
+      "tokenization_phi3_small.Phi3SmallTokenizer"
+    ]
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "revision": null,
+  "tokenizer_class": "Phi3SmallTokenizer",
+  "trust_remote_code": true
+}