初始化项目，由ModelHub XC社区提供模型

Model: louisbrulenaudet/Pearl-3x7B
Source: Original Platform

.gitattributes

@@ -0,0 +1,69 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+ 
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+model-00012-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00014-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00016-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00015-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00010-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00018-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00013-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00017-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00019-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00011-of-00019.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,146 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- dvilasuero/DistilabelBeagle14-7B
+- beowolx/CodeNinja-1.0-OpenChat-7B
+- WizardLM/WizardMath-7B-V1.1
+- Maths
+- Code
+- Python
+base_model:
+- dvilasuero/DistilabelBeagle14-7B
+- beowolx/CodeNinja-1.0-OpenChat-7B
+- WizardLM/WizardMath-7B-V1.1
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+<center><img src='https://i.imgur.com/0xFTuAX.png' width='450px'></center>
+
+# Pearl-3x7B, an xtraordinary Mixture of Experts (MoE) for data science
+
+Pearl-3x7B is a Mixture of Experts (MoE) made with the following models :
+* [dvilasuero/DistilabelBeagle14-7B](https://huggingface.co/dvilasuero/DistilabelBeagle14-7B)
+* [beowolx/CodeNinja-1.0-OpenChat-7B](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B)
+* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
+
+A Mixture of Experts (MoE) model represents a sophisticated architecture that amalgamates the capabilities of multiple specialized models to address a wide array of tasks within a unified framework. Within the realm of a MoE model tailored for a chat application, the integration of expertise spanning three distinct domains - chat, code, and mathematics - substantially enhances its capacity to furnish nuanced and precise responses to a diverse spectrum of user inquiries.
+
+The initial expert model, honed for chat applications, exhibits prowess in comprehending natural language nuances, conversational dynamics, and contextual cues. Drawing upon extensive conversational data, it adeptly generates engaging and contextually pertinent responses, thereby fostering meaningful interactions with users.
+
+The subsequent expert model, centered on code, brings to the fore proficiency in programming languages, algorithms, and software engineering principles. Possessing a deep-seated understanding of syntax, logical constructs, and problem-solving methodologies, it deftly tackles queries spanning coding challenges, debugging assistance, and software development inquiries.
+
+Lastly, the third expert model, specializing in mathematics, boasts expertise in mathematical reasoning, problem-solving strategies, and analytical techniques. Armed with a breadth of knowledge encompassing arithmetic, algebra, calculus, and beyond, it offers precise solutions, lucid explanations, and profound insights for mathematical queries, equations, and proofs.
+  
+## Configuration
+
+```yaml
+base_model: argilla/CapybaraHermes-2.5-Mistral-7B
+experts:
+  - source_model: dvilasuero/DistilabelBeagle14-7B
+    positive_prompts:
+      - "chat"
+      - "assistant"
+      - "tell me"
+      - "explain"
+      - "help"
+      - "guide"
+      - "assist"
+      - "answer"
+      - "support"
+      - "clarify"
+      - "elaborate"
+      - "educate"
+      - "inform"
+      - "advise"
+      - "instruct"
+  - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
+    positive_prompts:
+      - "code"
+      - "python"
+      - "javascript"
+      - "programming"
+      - "algorithm"
+      - "develop"
+      - "debug"
+      - "optimize"
+      - "software"
+      - "engineer"
+      - "web"
+      - "application"
+      - "framework"
+      - "library"
+      - "syntax"
+      - "logic"
+      - "compile"
+      - "execute"
+  - source_model: WizardLM/WizardMath-7B-V1.1
+    positive_prompts:
+      - "reason"
+      - "math"
+      - "mathematics"
+      - "solve"
+      - "count"
+      - "calculate"
+      - "analyze"
+      - "derive"
+      - "compute"
+      - "numbers"
+      - "equation"
+      - "theorem"
+      - "proof"
+      - "geometry"
+      - "trigonometry"
+      - "statistics"
+      - "probability"
+      - "algebra"
+      - "integral"
+```
+
+## Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "louisbrulenaudet/Pearl-3x7B"
+
+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"])
+```
+
+## Citing & Authors
+
+If you use this code in your research, please use the following BibTeX entry.
+
+```BibTeX
+@misc{louisbrulenaudet2023,
+  author =       {Louis Brulé Naudet},
+  title =        {Pearl-3x7B, an xtraordinary Mixture of Experts (MoE) for data science},
+  year =         {2023}
+  howpublished = {\url{https://huggingface.co/louisbrulenaudet/Pearl-3x7B}},
+}
+```
+
+## Feedback
+
+If you have any feedback, please reach out at [louisbrulenaudet@icloud.com](mailto:louisbrulenaudet@icloud.com).

added_tokens.json

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

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "argilla/CapybaraHermes-2.5-Mistral-7B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 3,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "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": false,
+  "vocab_size": 32002
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

mergekit_moe_config.yml

@@ -0,0 +1,61 @@
+
+base_model: argilla/CapybaraHermes-2.5-Mistral-7B
+experts:
+  - source_model: dvilasuero/DistilabelBeagle14-7B
+    positive_prompts:
+      - "chat"
+      - "assistant"
+      - "tell me"
+      - "explain"
+      - "help"
+      - "guide"
+      - "assist"
+      - "answer"
+      - "support"
+      - "clarify"
+      - "elaborate"
+      - "educate"
+      - "inform"
+      - "advise"
+      - "instruct"
+  - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
+    positive_prompts:
+      - "code"
+      - "python"
+      - "javascript"
+      - "programming"
+      - "algorithm"
+      - "develop"
+      - "debug"
+      - "optimize"
+      - "software"
+      - "engineer"
+      - "web"
+      - "application"
+      - "framework"
+      - "library"
+      - "syntax"
+      - "logic"
+      - "compile"
+      - "execute"
+  - source_model: WizardLM/WizardMath-7B-V1.1
+    positive_prompts:
+      - "reason"
+      - "math"
+      - "mathematics"
+      - "solve"
+      - "count"
+      - "calculate"
+      - "analyze"
+      - "derive"
+      - "compute"
+      - "numbers"
+      - "equation"
+      - "theorem"
+      - "proof"
+      - "geometry"
+      - "trigonometry"
+      - "statistics"
+      - "probability"
+      - "algebra"
+      - "integral"

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd98130c520239927ba4fb3eec2ac5db398482fa64085bc73e0b53e5710c620
+size 1933882656

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f582751fd1e3f380a5261210a9bd303604065d6d38f10d468805ddc755986521
+size 1996490936

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e072b7a97d69997a61aeaec63f7b8bc1470cd68a3bd1d1c786889b45413b75a
+size 1996490952

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5225a7fe639cccbd1aff1d85be606583d5c7fc363e8d062a1c79a5ea25cac7c9
+size 1996490952

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f308145891966075878f1b5f37cd8c3e5a193f4a82b09ef384e2310fa7b46a7
+size 1996490952

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609237bb2ba0bdc1a0c2528b681bbc1d463f3de3d04c687177f154f928b46a2a
+size 1996490952

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96d41d9c04c32231e3f431f9aeabb79a1bae6c64380c94ac4021cd77dbc17fbd
+size 1996490936

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1442748cdd7cc9bc39bd068f5119f9481800008ed34402a10b083a7ab6796e54
+size 1996490936

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a2e9de2c2509a207edd82115af511f122c7abfdf0758501867b1118e6391d41
+size 1996490952

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2ab43dac0f23b30731f0b36ed7feceabe0a692baef03c5c57fb9dc431043de
+size 1996490952

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad78496cc40362f784b50e7962d43d251ab2585ac7d29a05512863671d72e9f0
+size 1996490952

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baed25bf28aa66c718aaa6b541b62a49abb09099bc0569a634c05a14a188453d
+size 1996490944

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86739adf7f1c0d8e2e3d686d4e76b1d7aca41087b4656b958643b8b8beba8f4
+size 1996490936

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b346100083a795825011b0330ff289055e23cf4fcd75d3ad2011b9ac5d4922d1
+size 1996490944

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9281a5a7cd4d0578a482bfb54e86a49881f582994fe57b2329b96e46305abb3f
+size 1996490952

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb67656a258659da37da4c06c887208396967780d4cacd2bd41302a3a49ff91e
+size 1996490952

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dafa2241d8db920255bb5be263a4bf6752ff6e913d31cbb17b0246e48e8c20a
+size 1996490952

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb423411a57d2058bfe0270425cfbde22939f7c06dc1c2d8fdfc29dd85a29a1
+size 1996765088

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ccf1aff3a6c89117a4fbc0096db353e3389a01bf38bc0bdb9693f41ccbc70e
+size 1158422928

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cf57dadebd4785143c06f48ffeec2ec498062ef26c5c527152805cbaac14d8
+size 1795829

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}