初始化项目，由ModelHub XC社区提供模型

Model: chargoddard/piano-medley-7b
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 +1,58 @@
+---
+license: cc-by-nc-4.0
+datasets:
+- pankajmathur/orca_mini_v1_dataset
+- openai/summarize_from_feedback
+- PygmalionAI/PIPPA
+- chargoddard/rpguild
+- lemonilia/LimaRP
+- PKU-Alignment/PKU-SafeRLHF
+- Intel/orca_dpo_pairs
+- allenai/ultrafeedback_binarized_cleaned
+tags:
+- merge
+- mergekit
+---
+
+Another experiment in the line of [loyal-piano-m7](https://huggingface.co/chargoddard/loyal-piano-m7).
+
+Steps taken to produce this model:
+
+* Train loyal-piano-m7
+* cDPO with HuggingFaceH4/ultrafeedback_binarized to produce loyal-piano-m7-cdpo
+* Train another model with different sampling of the same source datasets as loyal-piano, let's call it servile-harpsichord
+* cDPO servile-harpsichord with allenai/ultrafeedback_binarized_cleaned, Intel/orca_dpo_pairs, and a helpfulness-only version of PKU-Alignment/PKU-SafeRLHF
+* TIES merge several checkpoints of servile-harpsichord-cdpo with loyal-piano-m7-cdpo
+
+Local benchmarks show the result to be better than any of the individual components. Let's see if that holds up!
+
+Trained using the Alpaca prompt format.
+
+
+Configuration for final merge:
+```yml
+models:
+  - model: chargoddard/loyal-piano-m7-cdpo
+    parameters:
+      density: 1.0
+      weight: 1.0
+  - model: /home/ubuntu/servile-harpsichord-cdpo/checkpoint-4186
+    parameters:
+      weight: 0.1
+  - model: /home/ubuntu/servile-harpsichord-cdpo/checkpoint-5796
+    parameters:
+      weight: 0.2
+  - model: /home/ubuntu/servile-harpsichord-cdpo/checkpoint-6118
+    parameters:
+      weight: 0.3
+  - model: /home/ubuntu/servile-harpsichord-cdpo/final
+    parameters:
+      weight: 0.4
+merge_method: ties
+base_model: mistralai/Mistral-7B-v0.1
+dtype: bfloat16
+parameters:
+  density: 0.4
+  normalize: true
+  int8_mask: true
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c402afa08e5a36881f4eba7bd403572965af1b6590ef892c49eb1b2b5ded5101
+size 9942981696

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd989d86c3b89fba1d22ade295653f4e95fd70bbfbe127bdec53566e039c78d
+size 4540516344

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 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}