初始化项目，由ModelHub XC社区提供模型

Model: sethuiyer/CodeCalc-Mistral-7B
Source: Original Platform

.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

README.md

@@ -0,0 +1,190 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- uukuguy/speechless-code-mistral-7b-v1.0
+- upaya07/Arithmo2-Mistral-7B
+pipeline_tag: text-generation
+model-index:
+- name: sethuiyer/CodeCalc-Mistral-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: 61.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-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: 83.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-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: 62.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-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: 47.49
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-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: 78.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-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: 63.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
+      name: Open LLM Leaderboard
+---
+# CodeCalc-Mistral-7B
+
+<p align="center">
+  <img src="https://huggingface.co/sethuiyer/CodeCalc-Mistral-7B/resolve/main/codecalc.webp" height="128px" alt="CodeCalc">
+</p>
+
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+base_model: uukuguy/speechless-code-mistral-7b-v1.0
+dtype: bfloat16
+merge_method: ties
+models:
+- model: uukuguy/speechless-code-mistral-7b-v1.0
+- model: upaya07/Arithmo2-Mistral-7B
+  parameters:
+    density:  [0.25, 0.35, 0.45, 0.35, 0.25]
+    weight: [0.1, 0.25, 0.5, 0.25, 0.1]
+parameters:
+  int8_mask: true
+
+```
+
+
+### Evaluation
+
+| T  | Model                                       | Average | ARC  | HellaSwag | MMLU  | TruthfulQA | Winogrande | GSM8K |
+|----|---------------------------------------------|---------|------|-----------|-------|------------|------------|-------|
+| 🔍  | sethuiyer/CodeCalc-Mistral-7B               | 66.33   | 61.95| 83.64     | 62.78 | 47.79      | 78.3       | 63.53 |
+| 📉  | uukuguy/speechless-code-mistral-7b-v1.0     | 63.6    | 61.18| 83.77     | 63.4  | 47.9       | 78.37      | 47.01 |
+
+The merge appears to be successful, especially considering the substantial improvement in the GSM8K benchmark while maintaining comparable performance on other metrics.
+
+
+## Usage
+
+Alpaca Instruction Format and [Divine Intellect](https://raw.githubusercontent.com/oobabooga/text-generation-webui/ae8cd449ae3e0236ecb3775892bb1eea23f9ed68/presets/Divine%20Intellect.yaml) preset.
+
+```
+You are an intelligent programming assistant.
+
+### Instruction:
+Implement a linked list in C++
+
+### Response:
+```
+
+Preset:
+
+```text
+temperature: 1.31
+top_p: 0.14
+repetition_penalty: 1.17
+top_k: 49
+```
+
+
+# [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__CodeCalc-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.33|
+|AI2 Reasoning Challenge (25-Shot)|61.95|
+|HellaSwag (10-Shot)              |83.64|
+|MMLU (5-Shot)                    |62.78|
+|TruthfulQA (0-shot)              |47.79|
+|Winogrande (5-shot)              |78.30|
+|GSM8k (5-shot)                   |63.53|
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "uukuguy/speechless-code-mistral-7b-v1.0",
+  "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": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+
+base_model: uukuguy/speechless-code-mistral-7b-v1.0
+dtype: bfloat16
+merge_method: ties
+models:
+- model: uukuguy/speechless-code-mistral-7b-v1.0
+- model: upaya07/Arithmo2-Mistral-7B
+  parameters:
+    density:  [0.25, 0.35, 0.45, 0.35, 0.25]
+    weight: [0.1, 0.25, 0.5, 0.25, 0.1]
+parameters:
+  int8_mask: true

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a752d6923dfce068119f7bdc26c724a0e19d1158a3f304d8126f48b8f85d91
+size 1979773128

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3aacd03d655ef83429caa7f785feebbe80ece057ea767f06e0afa3b67cee190
+size 1946235640

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1d1ef984d21d775a9801d544b6747cc69547adb227578b627c05c80bd45223
+size 1973490216

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1d045db3ecd7e66780246077d626bf5d088afccbff7a177320ecaf9c017571
+size 1979781464

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bc153200f04d3b7cfe4323f57bf1116b37075c222264682863b6bc111b792b
+size 1946243984

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9856125c437ad9398a185ec5ecb44fc486fc5486d496ed4f1bbc6eb6e8147a
+size 1923166040

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c810aeb94c64dcc0ff7ebe76f08bc596834d6ee9ee1d73bde8c2723706918110
+size 1946243984

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ecc8b07c5bbb486778a392600cab581f57005336e169bd0ce272cf9c3a4a44
+size 788563544

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}