初始化项目，由ModelHub XC社区提供模型

Model: mlabonne/Marcoro14-7B-slerp Source: Original Platform
2026-05-31 13:35:12 +08:00
commit 133bf64695
11 changed files with 91549 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,47 @@
+*.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
+*.model 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
+*.safetensors 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,272 @@
+---
+license: cc-by-nc-4.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- AIDC-ai-business/Marcoroni-7B-v3
+- EmbeddedLLM/Mistral-7B-Merge-14-v0.1
+model-index:
+- name: Marcoro14-7B-slerp
+  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: 69.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Marcoro14-7B-slerp
+      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: 87.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Marcoro14-7B-slerp
+      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: 65.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Marcoro14-7B-slerp
+      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: 63.54
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Marcoro14-7B-slerp
+      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: 81.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Marcoro14-7B-slerp
+      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: 70.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Marcoro14-7B-slerp
+      name: Open LLM Leaderboard
+---
+
+![](https://i.imgur.com/FSKtmRc.png)
+
+# Marcoro14-7B-slerp
+
+This model is a merge of the following models made with [mergekit](https://github.com/cg123/mergekit):
+ * [AIDC-ai-business/Marcoroni-7B-v3](https://huggingface.co/AIDC-ai-business/Marcoroni-7B-v3)
+ * [EmbeddedLLM/Mistral-7B-Merge-14-v0.1](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1)
+
+## 🏆 Evaluation
+
+Marcoro14-7B-slerp is the best-performing 7B LLM on the Open LLM Leaderboard (rank 1 below is 9B):
+
+![](https://i.imgur.com/5XUuP7g.png)
+
+I also evaluated it using Nous' benchmark suite and obtained the following results:
+
+|          Model          |AGIEval|GPT4ALL|TruthfulQA|Bigbench|Average|
+|-------------------------|------:|------:|---------:|-------:|------:|
+|Marcoro14-7B-slerp       |  44.66|  76.24|     64.15|   45.64|  57.67|
+|OpenHermes-2.5-Mistral-7B|  43.07|  73.12|     53.04|   40.96|  52.57|
+|Change                   |  +1.59|  +3.12|    +11.11|   +4.68|   +5.1|
+
+### AGIEval
+|             Task             |Version| Metric |Value|   |Stderr|
+|------------------------------|------:|--------|----:|---|-----:|
+|agieval_aqua_rat              |      0|acc     |26.38|±  |  2.77|
+|                              |       |acc_norm|24.41|±  |  2.70|
+|agieval_logiqa_en             |      0|acc     |38.25|±  |  1.91|
+|                              |       |acc_norm|39.32|±  |  1.92|
+|agieval_lsat_ar               |      0|acc     |24.35|±  |  2.84|
+|                              |       |acc_norm|25.22|±  |  2.87|
+|agieval_lsat_lr               |      0|acc     |50.00|±  |  2.22|
+|                              |       |acc_norm|50.59|±  |  2.22|
+|agieval_lsat_rc               |      0|acc     |62.83|±  |  2.95|
+|                              |       |acc_norm|62.08|±  |  2.96|
+|agieval_sat_en                |      0|acc     |79.61|±  |  2.81|
+|                              |       |acc_norm|79.61|±  |  2.81|
+|agieval_sat_en_without_passage|      0|acc     |45.15|±  |  3.48|
+|                              |       |acc_norm|45.63|±  |  3.48|
+|agieval_sat_math              |      0|acc     |33.18|±  |  3.18|
+|                              |       |acc_norm|30.45|±  |  3.11|
+
+Average: 44.66%
+
+### GPT4ALL
+|    Task     |Version| Metric |Value|   |Stderr|
+|-------------|------:|--------|----:|---|-----:|
+|arc_challenge|      0|acc     |63.91|±  |  1.40|
+|             |       |acc_norm|64.93|±  |  1.39|
+|arc_easy     |      0|acc     |86.07|±  |  0.71|
+|             |       |acc_norm|83.75|±  |  0.76|
+|boolq        |      1|acc     |88.56|±  |  0.56|
+|hellaswag    |      0|acc     |67.31|±  |  0.47|
+|             |       |acc_norm|85.28|±  |  0.35|
+|openbookqa   |      0|acc     |36.40|±  |  2.15|
+|             |       |acc_norm|48.20|±  |  2.24|
+|piqa         |      0|acc     |82.59|±  |  0.88|
+|             |       |acc_norm|84.39|±  |  0.85|
+|winogrande   |      0|acc     |78.53|±  |  1.15|
+
+Average: 76.24%
+
+### TruthfulQA
+|    Task     |Version|Metric|Value|   |Stderr|
+|-------------|------:|------|----:|---|-----:|
+|truthfulqa_mc|      1|mc1   |46.88|±  |  1.75|
+|             |       |mc2   |64.15|±  |  1.52|
+
+Average: 64.15%
+
+### Bigbench
+|                      Task                      |Version|       Metric        |Value|   |Stderr|
+|------------------------------------------------|------:|---------------------|----:|---|-----:|
+|bigbench_causal_judgement                       |      0|multiple_choice_grade|56.32|±  |  3.61|
+|bigbench_date_understanding                     |      0|multiple_choice_grade|66.40|±  |  2.46|
+|bigbench_disambiguation_qa                      |      0|multiple_choice_grade|45.35|±  |  3.11|
+|bigbench_geometric_shapes                       |      0|multiple_choice_grade|20.33|±  |  2.13|
+|                                                |       |exact_str_match      | 4.74|±  |  1.12|
+|bigbench_logical_deduction_five_objects         |      0|multiple_choice_grade|30.00|±  |  2.05|
+|bigbench_logical_deduction_seven_objects        |      0|multiple_choice_grade|21.43|±  |  1.55|
+|bigbench_logical_deduction_three_objects        |      0|multiple_choice_grade|52.33|±  |  2.89|
+|bigbench_movie_recommendation                   |      0|multiple_choice_grade|39.20|±  |  2.19|
+|bigbench_navigate                               |      0|multiple_choice_grade|53.90|±  |  1.58|
+|bigbench_reasoning_about_colored_objects        |      0|multiple_choice_grade|72.15|±  |  1.00|
+|bigbench_ruin_names                             |      0|multiple_choice_grade|52.46|±  |  2.36|
+|bigbench_salient_translation_error_detection    |      0|multiple_choice_grade|25.75|±  |  1.38|
+|bigbench_snarks                                 |      0|multiple_choice_grade|72.38|±  |  3.33|
+|bigbench_sports_understanding                   |      0|multiple_choice_grade|73.63|±  |  1.40|
+|bigbench_temporal_sequences                     |      0|multiple_choice_grade|45.70|±  |  1.58|
+|bigbench_tracking_shuffled_objects_five_objects |      0|multiple_choice_grade|23.44|±  |  1.20|
+|bigbench_tracking_shuffled_objects_seven_objects|      0|multiple_choice_grade|18.51|±  |  0.93|
+|bigbench_tracking_shuffled_objects_three_objects|      0|multiple_choice_grade|52.33|±  |  2.89|
+
+Average: 45.64%
+
+Average score: 57.67%
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: AIDC-ai-business/Marcoroni-7B-v3
+        layer_range: [0, 32]
+      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: AIDC-ai-business/Marcoroni-7B-v3
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "mlabonne/Marcoro14-7B-slerp"
+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"])
+```
+
+Output:
+
+> A large language model is a type of artificial intelligence (AI) system that has been trained on vast amounts of text data. It's designed to understand and generate human-like language, making predictions on what words or phrases might come next in a sentence or document. These models use complex algorithms and neural network architectures to learn from the data and improve their performance over time. Some well-known large language models include GPT-3 from OpenAI and BERT from Google.
+# [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_mlabonne__Marcoro14-7B-slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.01|
+|AI2 Reasoning Challenge (25-Shot)|69.80|
+|HellaSwag (10-Shot)              |87.13|
+|MMLU (5-Shot)                    |65.11|
+|TruthfulQA (0-shot)              |63.54|
+|Winogrande (5-shot)              |81.61|
+|GSM8k (5-shot)                   |70.89|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "AIDC-ai-business/Marcoroni-7B-v3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- 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 sha256:261f02536712b3dbda1b118774d36669041e70a2cfa2498bd48a0bba39e359e2
+size 9859095144
--- 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 sha256:5c2000a8d3ffa96db99fc541d138f025c44e0e61f6fce9cd2876d8ca8d783ff6
+size 4624402896
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "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
+  },
+  "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 +1,44 @@
+{
+  "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": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`