初始化项目，由ModelHub XC社区提供模型

Model: Undi95/MLewd-ReMM-L2-Chat-20B
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,130 @@
+---
+license: cc-by-nc-4.0
+tags:
+- not-for-all-audiences
+- nsfw
+---
+
+First :
+```shell
+layer_slices:
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 0
+    end: 16
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 8
+    end: 20
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 17
+    end: 32
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 21
+    end: 40
+```
+
+Inverted:
+```shell
+layer_slices:
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 0
+    end: 16
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 8
+    end: 20
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 17
+    end: 32
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 21
+    end: 40
+```
+
+Precise:
+```shell
+layer_slices:
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 0
+    end: 8
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 4
+    end: 12
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 9
+    end: 16
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 13
+    end: 22
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 17
+    end: 24
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 23
+    end: 32
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 25
+    end: 32
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 33
+    end: 40
+```
+
+PreciseInverted:
+```shell
+layer_slices:
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 0
+    end: 8
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 4
+    end: 12
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 9
+    end: 16
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 13
+    end: 22
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 17
+    end: 24
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 23
+    end: 32
+  - model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
+    start: 25
+    end: 32
+  - model: Undi95/MLewd-L2-Chat-13B
+    start: 33
+    end: 40
+```
+
+Part1 = ReMM v2.1 merged /w MLewd low weight to keep consistency. I call this "dilution" and result show consistency and coherency without repeat/loop beside the small amount of duplicated datas.
+
+The goal is to find the best way to interlace layers the best way possible to have a sweetspot between 13B and +30B.
+
+Normal/Inverted is by chunk of 16 layers and Precise/PreciseInverted is by chunk of 8 layers.
+
+All the models are made of 64(+1) layers. Need testing.
+
+## Prompt template: Alpaca
+
+```
+Below is an instruction that describes a task. Write a response that completes the request.
+
+### Instruction:
+{prompt}
+
+### Response:
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__MLewd-ReMM-L2-Chat-20B)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 53.33   |
+| ARC (25-shot)         | 62.46          |
+| HellaSwag (10-shot)   | 85.62    |
+| MMLU (5-shot)         | 59.13         |
+| TruthfulQA (0-shot)   | 55.63   |
+| Winogrande (5-shot)   | 77.19   |
+| GSM8K (5-shot)        | 10.92        |
+| DROP (3-shot)         | 22.33         |

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Undi95/MLewd-L2-Chat-13B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eed3a372e11f225e959ed6f98e41fb5d3f539ae6cd0afc29849b3e87627ff48
+size 9985398280

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8248722ec84c0889fb239917a6e3cee380a002cac71504f4f8da416fdbab0aa8
+size 9956563000

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d59662aed960916a584e0d077286d5ba513d92698eaf6ab8885f173018fda4a
+size 9993273312

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a67c9735625d38115bfebc80be8af32654aa478729de9d0ddfaf4aec38ffd94
+size 9725876168

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c585b4b9e15ed700bf6b26188072ab269c3ce98dd193a080b69a4ca689cdcb
+size 655360128

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}