初始化项目，由ModelHub XC社区提供模型

Model: sethuiyer/Nandine-7b Source: Original Platform
2026-04-13 14:30:05 +08:00
commit c4de12762a
13 changed files with 91594 additions and 0 deletions
--- a/.gitattributes
+++ b/.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
--- a/EVAL.md
+++ b/EVAL.md
@@ -0,0 +1,82 @@
+## Nous Benchmark
+
+|                          Model                          |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
+|---------------------------------------------------------|------:|------:|---------:|-------:|------:|
+|[Nandine-7b](https://huggingface.co/sethuiyer/Nandine-7b)|  43.54|  76.41|     61.73|   45.27|  56.74|
+
+### AGIEval
+|             Task             |Version| Metric |Value|   |Stderr|
+|------------------------------|------:|--------|----:|---|-----:|
+|agieval_aqua_rat              |      0|acc     |23.62|±  |  2.67|
+|                              |       |acc_norm|22.05|±  |  2.61|
+|agieval_logiqa_en             |      0|acc     |37.94|±  |  1.90|
+|                              |       |acc_norm|38.71|±  |  1.91|
+|agieval_lsat_ar               |      0|acc     |26.09|±  |  2.90|
+|                              |       |acc_norm|22.61|±  |  2.76|
+|agieval_lsat_lr               |      0|acc     |47.45|±  |  2.21|
+|                              |       |acc_norm|50.00|±  |  2.22|
+|agieval_lsat_rc               |      0|acc     |60.97|±  |  2.98|
+|                              |       |acc_norm|59.85|±  |  2.99|
+|agieval_sat_en                |      0|acc     |77.18|±  |  2.93|
+|                              |       |acc_norm|77.67|±  |  2.91|
+|agieval_sat_en_without_passage|      0|acc     |45.63|±  |  3.48|
+|                              |       |acc_norm|45.15|±  |  3.48|
+|agieval_sat_math              |      0|acc     |35.91|±  |  3.24|
+|                              |       |acc_norm|32.27|±  |  3.16|
+
+Average: 43.54%
+
+### GPT4All
+|    Task     |Version| Metric |Value|   |Stderr|
+|-------------|------:|--------|----:|---|-----:|
+|arc_challenge|      0|acc     |63.74|±  |  1.40|
+|             |       |acc_norm|63.99|±  |  1.40|
+|arc_easy     |      0|acc     |85.94|±  |  0.71|
+|             |       |acc_norm|83.50|±  |  0.76|
+|boolq        |      1|acc     |87.80|±  |  0.57|
+|hellaswag    |      0|acc     |67.50|±  |  0.47|
+|             |       |acc_norm|85.31|±  |  0.35|
+|openbookqa   |      0|acc     |38.20|±  |  2.18|
+|             |       |acc_norm|49.40|±  |  2.24|
+|piqa         |      0|acc     |82.97|±  |  0.88|
+|             |       |acc_norm|84.33|±  |  0.85|
+|winogrande   |      0|acc     |80.51|±  |  1.11|
+
+Average: 76.41%
+
+### TruthfulQA
+|    Task     |Version|Metric|Value|   |Stderr|
+|-------------|------:|------|----:|---|-----:|
+|truthfulqa_mc|      1|mc1   |45.78|±  |  1.74|
+|             |       |mc2   |61.73|±  |  1.54|
+
+Average: 61.73%
+
+### Bigbench
+|                      Task                      |Version|       Metric        |Value|   |Stderr|
+|------------------------------------------------|------:|---------------------|----:|---|-----:|
+|bigbench_causal_judgement                       |      0|multiple_choice_grade|57.89|±  |  3.59|
+|bigbench_date_understanding                     |      0|multiple_choice_grade|65.58|±  |  2.48|
+|bigbench_disambiguation_qa                      |      0|multiple_choice_grade|38.76|±  |  3.04|
+|bigbench_geometric_shapes                       |      0|multiple_choice_grade|20.06|±  |  2.12|
+|                                                |       |exact_str_match      | 5.85|±  |  1.24|
+|bigbench_logical_deduction_five_objects         |      0|multiple_choice_grade|30.20|±  |  2.06|
+|bigbench_logical_deduction_seven_objects        |      0|multiple_choice_grade|20.71|±  |  1.53|
+|bigbench_logical_deduction_three_objects        |      0|multiple_choice_grade|52.67|±  |  2.89|
+|bigbench_movie_recommendation                   |      0|multiple_choice_grade|43.60|±  |  2.22|
+|bigbench_navigate                               |      0|multiple_choice_grade|50.50|±  |  1.58|
+|bigbench_reasoning_about_colored_objects        |      0|multiple_choice_grade|73.15|±  |  0.99|
+|bigbench_ruin_names                             |      0|multiple_choice_grade|46.65|±  |  2.36|
+|bigbench_salient_translation_error_detection    |      0|multiple_choice_grade|25.25|±  |  1.38|
+|bigbench_snarks                                 |      0|multiple_choice_grade|75.14|±  |  3.22|
+|bigbench_sports_understanding                   |      0|multiple_choice_grade|73.12|±  |  1.41|
+|bigbench_temporal_sequences                     |      0|multiple_choice_grade|47.20|±  |  1.58|
+|bigbench_tracking_shuffled_objects_five_objects |      0|multiple_choice_grade|23.04|±  |  1.19|
+|bigbench_tracking_shuffled_objects_seven_objects|      0|multiple_choice_grade|18.69|±  |  0.93|
+|bigbench_tracking_shuffled_objects_three_objects|      0|multiple_choice_grade|52.67|±  |  2.89|
+
+Average: 45.27%
+
+Average score: 56.74%
+
+Elapsed time: 01:47:54
--- a/README.md
+++ b/README.md
@@ -0,0 +1,235 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- merge
+- mergekit
+- lazymergekit
+inference: false
+base_model:
+- senseable/Westlake-7B
+- Guilherme34/Samantha-v2
+- uukuguy/speechless-mistral-six-in-one-7b
+pipeline_tag: text-generation
+model-index:
+- name: sethuiyer/Nandine-7b
+  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: 69.28
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Nandine-7b
+      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: 87.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Nandine-7b
+      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: 64.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Nandine-7b
+      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: 62.1
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Nandine-7b
+      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: 83.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Nandine-7b
+      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: 62.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Nandine-7b
+      name: Open LLM Leaderboard
+---
+
+# Nandine-7b
+
+<p align="center">
+  <img src="https://huggingface.co/sethuiyer/Nandine-7b/resolve/main/nandine.webp" height="128px" alt="Nandine">
+</p>
+
+This is Nandine-7b, rated **87.47/100** by GPT-4 on a collection of 30 synthetic prompts generated by GPT-4.
+
+Nandine-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [senseable/Westlake-7B](https://huggingface.co/senseable/Westlake-7B)
+* [Guilherme34/Samantha-v2](https://huggingface.co/Guilherme34/Samantha-v2)
+* [uukuguy/speechless-mistral-six-in-one-7b](https://huggingface.co/uukuguy/speechless-mistral-six-in-one-7b)
+
+Nandine-7b represents a harmonious amalgamation of narrative skill, empathetic interaction, intellectual depth, and eloquent communication.
+
+## OpenLLM Benchmark
+
+| Model                          | Average ⬆️ | ARC    | HellaSwag | MMLU  | TruthfulQA | Winogrande | GSM8K | 
+|--------------------------------|------------|-------|-----------|-------|------------|------------|-------| 
+| sethuiyer/Nandine-7b 📑       | 71.47      | 69.28 | 87.01     | 64.83 | 62.1       | 83.19      | 62.4  | 
+
+
+## Nous Benchmark
+|                          Model                          |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
+|---------------------------------------------------------|------:|------:|---------:|-------:|------:|
+|[Nandine-7b](https://huggingface.co/sethuiyer/Nandine-7b)|  43.54|  76.41|     61.73|   45.27|  56.74|
+
+For more details, refer [here](https://huggingface.co/sethuiyer/Nandine-7b/blob/main/EVAL.md)
+
+
+**Pros:**
+1. **Strong Narrative Skills:** Excels in storytelling, creating engaging and imaginative narratives.
+2. **Accurate Information Delivery:** Provides factual and detailed information across various topics.
+3. **Comprehensive Analysis:** Capable of well-rounded discussions on complex and ethical topics.
+4. **Emotional Intelligence:** Shows empathy and understanding in responses requiring emotional sensitivity.
+5. **Clarity and Structure:** Maintains clear and well-structured communication.
+
+**Cons:**
+1. **Language Translation Limitations:** Challenges in providing fluent and natural translations.
+2. **Incomplete Problem Solving:** Some logical or mathematical problems are not solved accurately.
+3. **Lack of Depth in Certain Areas:** Needs deeper exploration in some responses for a more comprehensive understanding.
+4. **Occasional Imbalance in Historical Context:** Some historical explanations could be more balanced.
+5. **Room for Enhanced Creativity:** While creative storytelling is strong, there's potential for more varied responses in hypothetical scenarios.
+
+**Intended Use:**
+Ideal for users seeking a versatile AI companion for creative writing, thoughtful discussions, and general assistance.
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: senseable/Westlake-7B
+    parameters:
+      weight: 0.55
+      density: 0.6
+  - model: Guilherme34/Samantha-v2
+    parameters:
+      weight: 0.10
+      density: 0.3
+  - model: uukuguy/speechless-mistral-six-in-one-7b
+    parameters:
+      weight: 0.35
+      density: 0.6
+merge_method: dare_ties
+base_model: mistralai/Mistral-7B-v0.1
+parameters:
+  int8_mask: true
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "sethuiyer/Nandine-7b"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+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"])
+```
+
+## GGUF
+GGUF files are available at [Nandine-7b-GGUF](https://huggingface.co/sethuiyer/Nandine-7b-GGUF/tree/main)
+
+## Ollama
+Nandine is now available on Ollama. You can use it by running the command ```ollama run stuehieyr/nandine``` in your 
+terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on 
+a Google Colab backend.
+# [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_sethuiyer__Nandine-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.47|
+|AI2 Reasoning Challenge (25-Shot)|69.28|
+|HellaSwag (10-Shot)              |87.01|
+|MMLU (5-Shot)                    |64.83|
+|TruthfulQA (0-shot)              |62.10|
+|Winogrande (5-shot)              |83.19|
+|GSM8k (5-shot)                   |62.40|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,19 @@
+
+models:
+  - model: senseable/Westlake-7B
+    parameters:
+      weight: 0.55
+      density: 0.6
+  - model: Guilherme34/Samantha-v2
+    parameters:
+      weight: 0.10
+      density: 0.3
+  - model: uukuguy/speechless-mistral-six-in-one-7b
+    parameters:
+      weight: 0.35
+      density: 0.6
+merge_method: dare_ties
+base_model: mistralai/Mistral-7B-v0.1
+parameters:
+  int8_mask: true
+dtype: bfloat16
--- a/model-00001-of-00002.safetensors
+++ b/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c422ee5cc15e68ddc41073b73b7d748762c784e0f5bb713b713e30cf9d18a66b
+size 9942981696
--- a/model-00002-of-00002.safetensors
+++ b/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc40d87248b982aa68a1c855bfd1cd93f710caa8325c41583769f0a4e3a8da24
+size 4540516344
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/nandine.webp
+++ b/nandine.webp
--- a/special_tokens_map.json
+++ b/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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/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
+}