初始化项目，由ModelHub XC社区提供模型

Model: jtatman/TinyDolphin-3x-MoE
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 +1,80 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- cognitivecomputations/TinyDolphin-2.8.1-1.1b
+
+base_model:
+- cognitivecomputations/TinyDolphin-2.8.1-1.1b
+- cognitivecomputations/TinyDolphin-2.8.1-1.1b
+- cognitivecomputations/TinyDolphin-2.8.1-1.1b
+---
+
+# TinyDolphin-3x-MoE
+
+TinyDolphin-3x-MoE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [cognitivecomputations/TinyDolphin-2.8.1-1.1b](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8.1-1.1b)
+* [cognitivecomputations/TinyDolphin-2.8.1-1.1b](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8.1-1.1b)
+* [cognitivecomputations/TinyDolphin-2.8.1-1.1b](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8.1-1.1b)
+
+## 🧩 Configuration
+
+```yaml
+base_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+gate_mode: hidden
+dtype: float16
+experts:
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts: 
+    - "think step-by-step and follow these instructions"
+    - "read the following passage, and summarize it in less than 30 words."
+    - "please answer this question, consider the options carefully, and return the most likely answer."
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts: ["produce python code"]
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts: ["What is 2 x 22?"]
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "jtatman/TinyDolphin-3x-MoE"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+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"])
+```
+
+Eval:
+
+hf ({'pretrained': 'jtatman/TinyDolphin-3x-MoE'}), gen_kwargs: ({}), limit: None, num_fewshot: 0, batch_size: auto (64)
+|    Tasks    |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
+|-------------|------:|------|-----:|--------|---|-----:|---|-----:|
+|arc_challenge|      1|none  |     0|acc     |↑  |0.3063|±  |0.0135|
+|             |       |none  |     0|acc_norm|↑  |0.3285|±  |0.0137|
+|arc_easy     |      1|none  |     0|acc     |↑  |0.5981|±  |0.0101|
+|             |       |none  |     0|acc_norm|↑  |0.5467|±  |0.0102|
+|hellaswag    |      1|none  |     0|acc     |↑  |0.4656|±  |0.0050|
+|             |       |none  |     0|acc_norm|↑  |0.6004|±  |0.0049|
+|openbookqa   |      1|none  |     0|acc     |↑  |0.2300|±  |0.0188|
+|             |       |none  |     0|acc_norm|↑  |0.3640|±  |0.0215|
+|piqa         |      1|none  |     0|acc     |↑  |0.7318|±  |0.0103|
+|             |       |none  |     0|acc_norm|↑  |0.7296|±  |0.0104|

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "cognitivecomputations/TinyDolphin-2.8.1-1.1b",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 3,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}

mergekit_moe_config.yml

@@ -0,0 +1,14 @@
+
+base_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+gate_mode: hidden
+dtype: float16
+experts:
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts: 
+    - "think step-by-step and follow these instructions"
+    - "read the following passage, and summarize it in less than 30 words."
+    - "please answer this question, consider the options carefully, and return the most likely answer."
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts: ["produce python code"]
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts: ["What is 2 x 22?"]

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510d9daabf8eb016eaa0d5283d65b3bdedaef51f9a95b3a0cae4f4e6a0dc3231
+size 1992417376

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb39e56d2f8953cb8c7269e0dbb3edb49f656d6c1a12e0d6f585fb1873c632ed
+size 1983916864

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439104e9a95b94de573eec1aba7fa8c0f466c0e0dbaaef24d8a818a953e94006
+size 1269157440

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}