初始化项目，由ModelHub XC社区提供模型

Model: mayacinka/chatty-djinn-14B Source: Original Platform
2026-04-11 15:44:05 +08:00
commit f72c8d752f
14 changed files with 91658 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/README.md
+++ b/README.md
@@ -0,0 +1,312 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- openchat/openchat-3.5-0106
+- teknium/OpenHermes-2.5-Mistral-7B
+base_model:
+- openchat/openchat-3.5-0106
+- teknium/OpenHermes-2.5-Mistral-7B
+model-index:
+- name: chatty-djinn-14B
+  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: 70.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
+      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: 86.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
+      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: 64.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
+      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: 67.57
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
+      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: 83.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
+      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: 60.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/chatty-djinn-14B
+      name: Open LLM Leaderboard
+---
+![thumbnail](djinn-14b.webp)
+# djinn
+
+
+djinn is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
+* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
+* bardsai/jaskier-7b-dpo-v6.1
+* senseable/WestLake-7B-v2
+* NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+* paulml/OGNO-7B
+* paulml/DPOB-INMTOB-7B
+* mlabonne/AlphaMonarch-7B
+
+# 🏆 Benchmarks
+Nous benchmarks, find more [details here](https://gist.github.com/majacinka/3f2a797c8872ca9bfdaa2bbf3369edb5)
+
+|                                Model                                |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
+|---------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
+|[chatty-djinn-14B](https://huggingface.co/mayacinka/chatty-djinn-14B)|  38.43|  76.29|     68.02|    47.6|  57.59|
+
+### AGIEval
+|             Task             |Version| Metric |Value|   |Stderr|
+|------------------------------|------:|--------|----:|---|-----:|
+|agieval_aqua_rat              |      0|acc     |23.62|±  |  2.67|
+|                              |       |acc_norm|21.65|±  |  2.59|
+|agieval_logiqa_en             |      0|acc     |32.26|±  |  1.83|
+|                              |       |acc_norm|33.79|±  |  1.86|
+|agieval_lsat_ar               |      0|acc     |23.04|±  |  2.78|
+|                              |       |acc_norm|23.04|±  |  2.78|
+|agieval_lsat_lr               |      0|acc     |38.82|±  |  2.16|
+|                              |       |acc_norm|39.22|±  |  2.16|
+|agieval_lsat_rc               |      0|acc     |59.48|±  |  3.00|
+|                              |       |acc_norm|54.65|±  |  3.04|
+|agieval_sat_en                |      0|acc     |75.73|±  |  2.99|
+|                              |       |acc_norm|74.27|±  |  3.05|
+|agieval_sat_en_without_passage|      0|acc     |35.92|±  |  3.35|
+|                              |       |acc_norm|34.47|±  |  3.32|
+|agieval_sat_math              |      0|acc     |31.36|±  |  3.14|
+|                              |       |acc_norm|26.36|±  |  2.98|
+
+Average: 38.43%
+
+### GPT4All
+|    Task     |Version| Metric |Value|   |Stderr|
+|-------------|------:|--------|----:|---|-----:|
+|arc_challenge|      0|acc     |62.12|±  |  1.42|
+|             |       |acc_norm|65.44|±  |  1.39|
+|arc_easy     |      0|acc     |83.88|±  |  0.75|
+|             |       |acc_norm|78.58|±  |  0.84|
+|boolq        |      1|acc     |88.07|±  |  0.57|
+|hellaswag    |      0|acc     |65.18|±  |  0.48|
+|             |       |acc_norm|86.45|±  |  0.34|
+|openbookqa   |      0|acc     |39.60|±  |  2.19|
+|             |       |acc_norm|48.60|±  |  2.24|
+|piqa         |      0|acc     |82.26|±  |  0.89|
+|             |       |acc_norm|83.62|±  |  0.86|
+|winogrande   |      0|acc     |83.27|±  |  1.05|
+
+Average: 76.29%
+
+### TruthfulQA
+|    Task     |Version|Metric|Value|   |Stderr|
+|-------------|------:|------|----:|---|-----:|
+|truthfulqa_mc|      1|mc1   |50.55|±  |  1.75|
+|             |       |mc2   |68.02|±  |  1.52|
+
+Average: 68.02%
+
+### Bigbench
+|                      Task                      |Version|       Metric        |Value|   |Stderr|
+|------------------------------------------------|------:|---------------------|----:|---|-----:|
+|bigbench_causal_judgement                       |      0|multiple_choice_grade|57.89|±  |  3.59|
+|bigbench_date_understanding                     |      0|multiple_choice_grade|64.50|±  |  2.49|
+|bigbench_disambiguation_qa                      |      0|multiple_choice_grade|32.56|±  |  2.92|
+|bigbench_geometric_shapes                       |      0|multiple_choice_grade|26.18|±  |  2.32|
+|                                                |       |exact_str_match      | 1.11|±  |  0.55|
+|bigbench_logical_deduction_five_objects         |      0|multiple_choice_grade|30.80|±  |  2.07|
+|bigbench_logical_deduction_seven_objects        |      0|multiple_choice_grade|22.86|±  |  1.59|
+|bigbench_logical_deduction_three_objects        |      0|multiple_choice_grade|57.67|±  |  2.86|
+|bigbench_movie_recommendation                   |      0|multiple_choice_grade|62.00|±  |  2.17|
+|bigbench_navigate                               |      0|multiple_choice_grade|56.20|±  |  1.57|
+|bigbench_reasoning_about_colored_objects        |      0|multiple_choice_grade|65.65|±  |  1.06|
+|bigbench_ruin_names                             |      0|multiple_choice_grade|64.73|±  |  2.26|
+|bigbench_salient_translation_error_detection    |      0|multiple_choice_grade|17.33|±  |  1.20|
+|bigbench_snarks                                 |      0|multiple_choice_grade|76.24|±  |  3.17|
+|bigbench_sports_understanding                   |      0|multiple_choice_grade|75.15|±  |  1.38|
+|bigbench_temporal_sequences                     |      0|multiple_choice_grade|48.90|±  |  1.58|
+|bigbench_tracking_shuffled_objects_five_objects |      0|multiple_choice_grade|22.32|±  |  1.18|
+|bigbench_tracking_shuffled_objects_seven_objects|      0|multiple_choice_grade|18.17|±  |  0.92|
+|bigbench_tracking_shuffled_objects_three_objects|      0|multiple_choice_grade|57.67|±  |  2.86|
+
+Average: 47.6%
+
+Average score: 57.59%
+## 🧩 Configuration
+Inspired by [theprofessor's config](https://huggingface.co/abacusai/TheProfessor-155b)
+
+```yaml
+merge_method: linear # use linear so we can include multiple models, albeit at a zero weight
+parameters:
+  weight: 1.0 # weight everything as 1 unless specified otherwise - linear with one model weighted at 1 is a no-op like passthrough
+slices:
+  - sources:
+      - model: openchat/openchat-3.5-0106
+        layer_range: [0, 1]
+      - model: teknium/OpenHermes-2.5-Mistral-7B 
+        layer_range: [0, 1]
+        parameters:
+          weight: 0
+  - sources:
+      - model: bardsai/jaskier-7b-dpo-v6.1
+        layer_range: [1, 10]
+  - sources:
+      - model: senseable/WestLake-7B-v2
+        layer_range: [10, 20]
+  - sources:
+      - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+        layer_range: [20, 30]
+  - sources:
+      - model: paulml/OGNO-7B
+        layer_range: [15, 25]
+  - sources:
+      - model: paulml/DPOB-INMTOB-7B
+        layer_range: [22, 32]
+  - sources:
+      - model: mlabonne/AlphaMonarch-7B
+        layer_range: [5, 15]
+  - sources: 
+      - model: openchat/openchat-3.5-0106
+        layer_range: [31, 32]
+      - model: teknium/OpenHermes-2.5-Mistral-7B
+        layer_range: [31, 32]
+        parameters:
+          weight: 0
+dtype: float16
+tokenizer_source: model:openchat/openchat-3.5-0106
+```
+
+## An example
+
+*User:* Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have? 
+Think step by step and the result MUST BE A NUMBER
+
+*djinn:*
+In this family structure, we know there are 4 aka '1 + 3-brothers' (1 being initially for Sally) existing individuals who are 
+also the siblings of the 3-brother-group. As each of the 3-brothers has 2-sisters each, that sums up to 6 total sister- roles. Since 
+we already accounted for one of the sisters (assuming to be the oldest or in alphabetical order, as names were not given) to be part 
+of the 3-brother group, we subtract one from the 6-sisters total. So, considering the provided information, Sally would have 6 - 1 = 5 
+remaining younger or alphabetically-wise- placed, biological-sisters. However, note that this problem statement might not perfectly align 
+with real-life complexities, such as same-sex twins, adoption, etc., but within the given context, the solution is 5.
+
+Remember, in more intricate or unclear family tree scenarios, it'd be best to directly ask for clarifications or consider additional data 
+points. In short, with the given constraints, Sally has 5 known, direct, biological, and likely-in-age-order, younger/alphabetically-placed,
+sister-siblings.(To reiterate the core result in a concise manner: 5).
+
+(Please excuse the verbosity, aiming for thoroughness and clarity.)
+
+This response maintains the initial request's numerical focus while providing a detailed explanation to ensure understanding.
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "mayacinka/djinn"
+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"])
+```
+# [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_mayacinka__chatty-djinn-14B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.08|
+|AI2 Reasoning Challenge (25-Shot)|70.39|
+|HellaSwag (10-Shot)              |86.45|
+|MMLU (5-Shot)                    |64.40|
+|TruthfulQA (0-shot)              |67.57|
+|Winogrande (5-shot)              |83.11|
+|GSM8k (5-shot)                   |60.58|
+
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "paulml/OGNO-7B",
+  "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": 61,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}
--- a/djinn-14b.webp
+++ b/djinn-14b.webp
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,39 @@
+
+merge_method: linear # use linear so we can include multiple models, albeit at a zero weight
+parameters:
+  weight: 1.0 # weight everything as 1 unless specified otherwise - linear with one model weighted at 1 is a no-op like passthrough
+slices:
+  - sources:
+      - model: openchat/openchat-3.5-0106
+        layer_range: [0, 1]
+      - model: teknium/OpenHermes-2.5-Mistral-7B 
+        layer_range: [0, 1]
+        parameters:
+          weight: 0
+  - sources:
+      - model: bardsai/jaskier-7b-dpo-v6.1
+        layer_range: [1, 10]
+  - sources:
+      - model: senseable/WestLake-7B-v2
+        layer_range: [10, 20]
+  - sources:
+      - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+        layer_range: [20, 30]
+  - sources:
+      - model: paulml/OGNO-7B
+        layer_range: [15, 25]
+  - sources:
+      - model: paulml/DPOB-INMTOB-7B
+        layer_range: [22, 32]
+  - sources:
+      - model: mlabonne/AlphaMonarch-7B
+        layer_range: [5, 15]
+  - sources: 
+      - model: openchat/openchat-3.5-0106
+        layer_range: [31, 32]
+      - model: teknium/OpenHermes-2.5-Mistral-7B
+        layer_range: [31, 32]
+        parameters:
+          weight: 0
+dtype: float16
+tokenizer_source: model:openchat/openchat-3.5-0106
--- a/model-00001-of-00003.safetensors
+++ b/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83bb3d0477fd708f308ec0c159276ccedfbf9410925bb13444f6d8b76b9875c
+size 9909427184
--- a/model-00002-of-00003.safetensors
+++ b/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a51182a3024ca9d4fb10eb7b24a8bd497369c3bac1bbc40fb8f222bcc68e4b
+size 9976576928
--- a/model-00003-of-00003.safetensors
+++ b/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b2b53ed0c90184919cdf8d7f4217be4be58b65a334eb352f310c0ed1531265
+size 7248052600
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "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 +1,62 @@
+{
+  "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": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "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": true
+}