Upload folder using huggingface_hub

README.md

@@ -0,0 +1,72 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- microsoft/Phi-3-medium-128k-instruct
+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
+---
+
+# Phi-3-medium-128k-27B-lingyang-v0.1
+
+Phi-3-medium-128k-27B-lingyang-v0.1 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)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [0, 10]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [0, 20]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [10, 20]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [20, 40]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [20, 40]
+
+merge_method: passthrough
+base_model: "microsoft/Phi-3-medium-128k-instruct"
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "wwe180/Phi-3-medium-128k-27B-lingyang-v0.1"
+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 +1,169 @@
+{
+  "_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": 80,
+  "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 +1,21 @@
+
+slices:
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [0, 10]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [0, 20]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [10, 20]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [20, 40]
+  - sources:
+      - model: "microsoft/Phi-3-medium-128k-instruct"
+        layer_range: [20, 40]
+
+merge_method: passthrough
+base_model: "microsoft/Phi-3-medium-128k-instruct"
+dtype: bfloat16

model-00001-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efff77b4f3d4f9bd443950e41f9736f577d650b0f84140dc60c986c35743a99
+size 840192560

model-00002-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8cac86bdc75423e4a122bae26e329038ee8ee22dc58e10b92ae1d59164cf799
+size 969954016

model-00003-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c79420a2b663f4f8d3b5c7a9728c53da28ce7871ea220652dfd3cc803374db
+size 943739824

model-00004-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2ddfb83d15ec17a40cd186c0c928a5210abc40fc3b166dec146422face8ab2
+size 996189464

model-00005-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2c74ca2539a3e938bb54f2286ffb0ddc965255a36e8704b4d58cfd7c452ffd
+size 996189352

model-00006-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2e00d53da5196d0d4f4b3e6b0ff618c4d67337bd8ee35e31856d460c85da74
+size 734003584

model-00007-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5ae5130d4cf24b2897f76d7e12e170be04713a296ff15f059496af034fc431
+size 996189464

model-00008-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da4ed88070ed6cd4d9c306f9f64af46fc398e01cc4715514b127397642f7bb48
+size 996189352

model-00009-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f16da964f728728f99d034b5cc5b0b0477e34d8ad704f3a2a76f17d9f5dfcc
+size 734003584

model-00010-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a53944d30be934893f3f14324d2f5c7f7c5df2e66646b9415c6fb6a13b7339
+size 996189464

model-00011-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5aebcf2276c3670f4213ff30a27f293d64f4675afa6381606ed353246767f0
+size 996189352

model-00012-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaf28f2187e51fcddab857a4268fb2978e974f9c8fb899bc819d7e381243f3a
+size 734003584

model-00013-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612e601443af02cd8a2df07c914812ba5249927932e01214a101e1c8fa0f97ef
+size 996189464

model-00014-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d541c49c10ca77a95c42a3f4e9753a3d922bc22620b71c87cd64bbc30676661
+size 996189352

model-00015-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da7c969ba97c19f8b613d9b6e5ad939fd94ba3be9643ad5528530de1daba019
+size 734003584

model-00016-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0bb5761daef80a20ce252745a0efb637824ef0b546fcfe2055c5a9a7c58099
+size 996189464

model-00017-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55365c9aaee8223c6a349be467744df317675912d651a70a0b231d7c1cf72781
+size 996189352

model-00018-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3c6db43a6d0574569fe445d48d682c18f224a5ecf37aa08332895a224d63fc
+size 734003584

model-00019-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3c83e3115fa904f87083495238c83e0d2975c9016da1eadb4c2ade3c7bd7c4
+size 996189456

model-00020-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e1b24f6d50ca197ce6422292213c943891c7d8f50d66a53282ba6f1173189f1
+size 996189352

model-00021-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa89f5fc5c51f5c4073b94d802ef53f69be90a3dcb5731906a84cd7714f012b
+size 734003584

model-00022-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de3b4ed47799fed8439c4a458d1dbf65ed06d68501b1abcc490baae4c9861b8
+size 996189464

model-00023-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305af8af038af2daba5d8584a0f77561e8440e30e0b36e13a02da72813285079
+size 996189352

model-00024-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915a7f5fd30df959e0979d35217537c369b1d73a413ea05df87a8f6802423914
+size 734003584

model-00025-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645dc1bb86840b420972a7a75b75958f5657f12e6a3c59d99eaff6b0215ff22d
+size 996189464

model-00026-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1efb46d094bdda436434930df25df2995e908de5240e58b10e004a8f992a67
+size 996189352

model-00027-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc253cc96e936a3cb53674e09134c10525856df3a475544731a4fcda6efd5658
+size 734003584

model-00028-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a561bb2f35d148a088626c3c440099db599b0003c61cd68079de0452e877db49
+size 996189464

model-00029-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5659ee6a61801b79e7886ea0a75a84bea4a78367f6d302860c443699718a9fb6
+size 996189352

model-00030-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e277ab0e243a35e08a6e85f7fb28b318c5b45eaa70f32208cedf282236df8e5e
+size 734003584

model-00031-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24cbce34865c671efc69eb28f307374c872897ade2f5b38272f7c6e8788efdd8
+size 996189464

model-00032-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf556cfd42438bd4519c85916f5631889d733415ea7656e7168a761db65481d5
+size 996189352

model-00033-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c9e053f352e1d3cc9d2a88a5efe7158838d0dec1e300552862a4fc84768847
+size 734003584

model-00034-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea406c241180f9f12bfccbea1860f906bfc0fabba70ffc0bd531a1fab81b02d
+size 996189464

model-00035-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe541f521fa6731a51763fc204310348a3b5cbe029e7492b41d1b0319b319a72
+size 996189336

model-00036-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf405dbfc1dc0358171a5cc8f8731a02490611f0e24dc43deb6520359e700b3
+size 734003576

model-00037-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb50b8e1e93985cc1c0462a9b7f7fbce9383c27347a192e9286001120cddd29
+size 996189456

model-00038-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701776bad018c09e0060db0be249f91a208d4abbc9b7af7b8c279a924e0054bd
+size 996189352

model-00039-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671d6c0cc31db56cfcd1336bd7d44c5f40c5ff6ce9f00236189475746965d9f2
+size 734003584

model-00040-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f80761a7349b6085ae45ecef682a13a4612e819509dd9ada1d7d3598fa8b677
+size 996189464

model-00041-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278e18506fc00f6ed3c30e43dd1735a65412b81cebf168ca29a00a7be5af8136
+size 996189352

model-00042-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4883538ae19f62d3f63e85e7a4aebc310057a5ef3a673afe8eb73519052851
+size 734003584

model-00043-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3427443043f1b18941b3cd26ff4d5b158c4a637105d20600022ba99a32abbc
+size 996189464

model-00044-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a15b0b45afc76bdd2abdb7a894dd71b9f07ee1424a11e9e2b5b38477a0bd32
+size 996189352

model-00045-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e2f882594d84cbf86057d98a38ca5dae98a22115024d4772152eb751dce8a5
+size 734003584

model-00046-of-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57b2e9f56c5a0c951860b1799262a66f1fb68125b1c03ee2a19c024e6f4e928
+size 996189464