初始化项目，由ModelHub XC社区提供模型

Model: macadeliccc/piccolo-math-2x7b
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+piccolo.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,260 @@
+---
+license: mit
+model-index:
+- name: piccolo-math-2x7b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 69.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/piccolo-math-2x7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 87.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/piccolo-math-2x7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/piccolo-math-2x7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 63.86
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/piccolo-math-2x7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 79.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/piccolo-math-2x7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 70.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/piccolo-math-2x7b
+      name: Open LLM Leaderboard
+---
+# Piccolo-math-2x7b
+
+
+  **In loving memory of my dog Klaus (Piccolo)**
+    
+  _~ Piccolo (Italian): the little one ~_
+
+ ![piccolo.png](piccolo.png)
+
+
+# Code Example
+
+Inference and Evaluation colab available [here](https://colab.research.google.com/drive/1ZqLNvVvtFHC_4v2CgcMVh7pP9Fvx0SbI?usp=sharing)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+def generate_response(prompt):
+    """
+    Generate a response from the model based on the input prompt.
+    Args:
+    prompt (str): Prompt for the model.
+
+    Returns:
+    str: The generated response from the model.
+    """
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=256, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id)
+
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    return response
+
+model_id = "macadeliccc/piccolo-math-2x7b"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id,load_in_4bit=True)
+
+prompt = "What is the best way to train Cane Corsos?"
+
+print("Response:")
+print(generate_response(prompt), "\n")
+```
+
+The model is capable of quality code, math, and logical reasoning. Try whatever questions you think of.
+
+# Evaluations
+
+|                                  Model                                  |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
+|-------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
+|[piccolo-math-2x7b](https://huggingface.co/macadeliccc/piccolo-math-2x7b)|  43.89|  74.98|     63.96|   44.99|  56.96|
+
+### EQ Bench
+
+#### Benchmark Complete:
++ 2024-01-24 00:00:40
++ Time taken: 183.3 mins
++ Prompt Format: Mistral
++ Model: macadeliccc/piccolo-math-2x7b
++ Score (v2): 70.74
++ Parseable: 167.0
+---------------
+Batch completed
+Time taken: 183.3 mins
+
+### AGIEval
+|             Task             |Version| Metric |Value|   |Stderr|
+|------------------------------|------:|--------|----:|---|-----:|
+|agieval_aqua_rat              |      0|acc     |24.41|±  |  2.70|
+|                              |       |acc_norm|24.80|±  |  2.72|
+|agieval_logiqa_en             |      0|acc     |35.79|±  |  1.88|
+|                              |       |acc_norm|36.71|±  |  1.89|
+|agieval_lsat_ar               |      0|acc     |23.48|±  |  2.80|
+|                              |       |acc_norm|23.91|±  |  2.82|
+|agieval_lsat_lr               |      0|acc     |49.22|±  |  2.22|
+|                              |       |acc_norm|50.00|±  |  2.22|
+|agieval_lsat_rc               |      0|acc     |63.94|±  |  2.93|
+|                              |       |acc_norm|64.31|±  |  2.93|
+|agieval_sat_en                |      0|acc     |77.18|±  |  2.93|
+|                              |       |acc_norm|76.70|±  |  2.95|
+|agieval_sat_en_without_passage|      0|acc     |45.15|±  |  3.48|
+|                              |       |acc_norm|44.66|±  |  3.47|
+|agieval_sat_math              |      0|acc     |33.64|±  |  3.19|
+|                              |       |acc_norm|30.00|±  |  3.10|
+
+Average: 43.89%
+
+### GPT4All
+|    Task     |Version| Metric |Value|   |Stderr|
+|-------------|------:|--------|----:|---|-----:|
+|arc_challenge|      0|acc     |61.86|±  |  1.42|
+|             |       |acc_norm|62.88|±  |  1.41|
+|arc_easy     |      0|acc     |84.34|±  |  0.75|
+|             |       |acc_norm|80.47|±  |  0.81|
+|boolq        |      1|acc     |86.88|±  |  0.59|
+|hellaswag    |      0|acc     |68.56|±  |  0.46|
+|             |       |acc_norm|85.16|±  |  0.35|
+|openbookqa   |      0|acc     |37.00|±  |  2.16|
+|             |       |acc_norm|47.80|±  |  2.24|
+|piqa         |      0|acc     |82.21|±  |  0.89|
+|             |       |acc_norm|83.68|±  |  0.86|
+|winogrande   |      0|acc     |77.98|±  |  1.16|
+
+Average: 74.98%
+
+### TruthfulQA
+|    Task     |Version|Metric|Value|   |Stderr|
+|-------------|------:|------|----:|---|-----:|
+|truthfulqa_mc|      1|mc1   |47.37|±  |  1.75|
+|             |       |mc2   |63.96|±  |  1.57|
+
+Average: 63.96%
+
+### Bigbench
+|                      Task                      |Version|       Metric        |Value|   |Stderr|
+|------------------------------------------------|------:|---------------------|----:|---|-----:|
+|bigbench_causal_judgement                       |      0|multiple_choice_grade|55.26|±  |  3.62|
+|bigbench_date_understanding                     |      0|multiple_choice_grade|63.14|±  |  2.51|
+|bigbench_disambiguation_qa                      |      0|multiple_choice_grade|42.64|±  |  3.08|
+|bigbench_geometric_shapes                       |      0|multiple_choice_grade|22.84|±  |  2.22|
+|                                                |       |exact_str_match      | 3.34|±  |  0.95|
+|bigbench_logical_deduction_five_objects         |      0|multiple_choice_grade|36.60|±  |  2.16|
+|bigbench_logical_deduction_seven_objects        |      0|multiple_choice_grade|25.57|±  |  1.65|
+|bigbench_logical_deduction_three_objects        |      0|multiple_choice_grade|56.00|±  |  2.87|
+|bigbench_movie_recommendation                   |      0|multiple_choice_grade|42.40|±  |  2.21|
+|bigbench_navigate                               |      0|multiple_choice_grade|54.70|±  |  1.57|
+|bigbench_reasoning_about_colored_objects        |      0|multiple_choice_grade|62.90|±  |  1.08|
+|bigbench_ruin_names                             |      0|multiple_choice_grade|53.35|±  |  2.36|
+|bigbench_salient_translation_error_detection    |      0|multiple_choice_grade|24.35|±  |  1.36|
+|bigbench_snarks                                 |      0|multiple_choice_grade|62.43|±  |  3.61|
+|bigbench_sports_understanding                   |      0|multiple_choice_grade|70.28|±  |  1.46|
+|bigbench_temporal_sequences                     |      0|multiple_choice_grade|41.30|±  |  1.56|
+|bigbench_tracking_shuffled_objects_five_objects |      0|multiple_choice_grade|22.32|±  |  1.18|
+|bigbench_tracking_shuffled_objects_seven_objects|      0|multiple_choice_grade|17.77|±  |  0.91|
+|bigbench_tracking_shuffled_objects_three_objects|      0|multiple_choice_grade|56.00|±  |  2.87|
+
+Average: 44.99%
+
+Average score: 56.96%
+
+Elapsed time: 01:51:53
+
+# [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_macadeliccc__piccolo-math-2x7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.32|
+|AI2 Reasoning Challenge (25-Shot)|69.11|
+|HellaSwag (10-Shot)              |87.27|
+|MMLU (5-Shot)                    |63.69|
+|TruthfulQA (0-shot)              |63.86|
+|Winogrande (5-shot)              |79.87|
+|GSM8k (5-shot)                   |70.13|
+

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "mlabonne/NeuralBeagle14-7B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "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": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "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": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4fca1e86bb8ac034e3e6e737a839fa2cb13977ccc10ed4872b7fd6aacb02ef
+size 9919813704

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337156d06c28f781c29e19bd59d1128299c7daccae816eb54705b76f54d06d86
+size 9982454736

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b005b783fd9813faed981b7c910e170c8b55600109226c8092a0c111ea96c3cc
+size 5856061008

piccolo.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17541944c663a41d6e2dd5edf563e8c0e18f4c8b7d11ce2b49296fad15d18a7
+size 1581254

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}