初始化项目，由ModelHub XC社区提供模型

Model: Aryanne/Westest-7B
Source: Original Platform

.gitattributes

@@ -0,0 +1,39 @@
+*.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
+q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+f16.gguf filter=lfs diff=lfs merge=lfs -text
+clean-baselise-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+WestLake-7B-v2-base-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,162 @@
+---
+license: cc-by-sa-4.0
+tags:
+- mergekit
+- merge
+base_model:
+- chargoddard/piano-medley-7b
+- senseable/WestLake-7B-v2
+model-index:
+- name: Westest-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: 72.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/Westest-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: 88.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/Westest-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: 64.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/Westest-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: 66.72
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/Westest-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: 86.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/Westest-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: 65.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/Westest-7B
+      name: Open LLM Leaderboard
+---
+# merged
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the task_anysize merge method using [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [chargoddard/piano-medley-7b](https://huggingface.co/chargoddard/piano-medley-7b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model:
+  model:
+    path: senseable/WestLake-7B-v2
+dtype: bfloat16
+merge_method: task_anysize
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: chargoddard/piano-medley-7b
+    parameters:
+      weight: 0.55
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: senseable/WestLake-7B-v2
+```
+# [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_Aryanne__Westest-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.03|
+|AI2 Reasoning Challenge (25-Shot)|72.18|
+|HellaSwag (10-Shot)              |88.52|
+|MMLU (5-Shot)                    |64.43|
+|TruthfulQA (0-shot)              |66.72|
+|Winogrande (5-shot)              |86.58|
+|GSM8k (5-shot)                   |65.73|
+

WestLake-7B-v2-base-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413b28f41e3d72dd8ebeff43397d6ab58b3ebf8d7b17835897b25825f65859b3
+size 3518985984

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "senseable/WestLake-7B-v2",
+  "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,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67131db08cf3deb3d78ed5f1e2ae8d3cf5ca52a8953f0be4e8c4167a34a1fcc7
+size 14484731520

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.1"
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+base_model:
+  model:
+    path: senseable/WestLake-7B-v2
+dtype: bfloat16
+merge_method: task_anysize
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: chargoddard/piano-medley-7b
+    parameters:
+      weight: 0.55
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: senseable/WestLake-7B-v2

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8687027704521638b0287e783fee9c1e231ab3b73d094ccccb1e20e75de021
+size 1946219040

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ce2cf4c442a2cc8b9e8fb7bc4511b1468ed45df7c6c6272201d8280fd2f6cc
+size 1946243920

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911500ac752a041f3a8b7a58017da05e1f76c91db4b087f945cbb9525f274924
+size 1889587064

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb5d42e71d472117793ea52f1520748988d916e4a4fbdf7b0c20a1d5af3b31d
+size 1946243960

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47eac09ea7081ac9c86cb4ce3467804fd8189d8296baa86137c8fa0d745cdd2c
+size 1979781456

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891182316e6ba46b8345814c7765bd5c0abccf71455f7db2dc7b7590f10dfe3d
+size 1889628568

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac3ce338a4bdfb124ff52b1f52d77d5bcb7d5ba0d4d446a7eac1dd8f5202334
+size 1979781456

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf52c0f90237a69dfe4bbf908c3ad7d4a3585b3c8762fde15985d427470ed4c0
+size 906012472

q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ace3e380595c7af150766506fb2a1ffe74ba25f9f32c91f3308f684ef1a2915
+size 3518985888

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "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": {
+    "content": "<unk>",
+    "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 +1,45 @@
+{
+  "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": 255,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}