初始化项目，由ModelHub XC社区提供模型

Model: seyf1elislam/WestKunai-Hermes-10.7b-test Source: Original Platform
2026-05-13 00:32:59 +08:00
commit 042977788c
21 changed files with 91503 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 +1,196 @@
+---
+license: cc-by-nc-4.0
+tags: 
+- merge
+- mergekit
+base_model:
+- seyf1elislam/WestKunai-Hermes-7b
+model-index:
+- name: WestKunai-Hermes-10.7b-test
+  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: 68.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      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: 87.10
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      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=seyf1elislam/WestKunai-Hermes-10.7b-test
+      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: 64.28
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      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: 82.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      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: 51.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-7b
+      name: Open LLM Leaderboard
+---
+
+# WestKunai-Hermes-10.7b-test
+
+Replicate the configuration utilized in the [froggeric/WestLake-10.7B-v2](https://huggingface.co/froggeric/WestLake-10.7B-v2/) model to extend the [WestKunai-Hermes-7b](https://huggingface.co/seyf1elislam/WestKunai-Hermes-7b) model to 10.7b.
+
+# Quantized versions : 
+- [**GGUF**](https://huggingface.co/seyf1elislam/WestKunai-Hermes-10.7b-test-GGUF)
+
+# comparison 
+|             Metric              | diff    |Current(10.7b)|Origin(7b)|
+|---------------------------------|----:|----:|----:|
+|Avg.                             |<span style="color:red">-3.76</span>|69.75|73.51|
+|AI2 Reasoning Challenge (25-Shot)|<span style="color:red">-3.07</span>|68.09|71.16|
+|HellaSwag (10-Shot)              |<span style="color:red">-0.66</span>|87.10|87.76|
+|MMLU (5-Shot)                    |<span style="color:red">-0.34</span>|64.43|64.77|
+|TruthfulQA (0-shot)              |<span style="color:red">-0.97</span>|64.28|65.25|
+|Winogrande (5-shot)              |<span style="color:red">-0.31</span>|82.72|83.03|
+|GSM8k (5-shot)                   |<span style="color:red">-17.21</span>|51.86|69.07|
+
+
+## Merge Details
+
+
+### Models Merged
+The following models were included in the merge:
+* [seyf1elislam/WestKunai-Hermes-7b](https://huggingface.co/seyf1elislam/WestKunai-Hermes-7b)
+
+##  Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+slices:
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [0,9]
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [5,14]
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [10,19]
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [15,24]
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [20,32]
+merge_method: passthrough
+dtype: bfloat16
+```
+## Usage Example
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "seyf1elislam/WestKunai-Hermes-10.7b-test"
+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_seyf1elislam__WestKunai-Hermes-10.7b-test)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.75|
+|AI2 Reasoning Challenge (25-Shot)|68.09|
+|HellaSwag (10-Shot)              |87.10|
+|MMLU (5-Shot)                    |64.43|
+|TruthfulQA (0-shot)              |64.28|
+|Winogrande (5-shot)              |82.72|
+|GSM8k (5-shot)                   |51.86|
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "seyf1elislam/WestKunai-Hermes-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": 48,
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,19 @@
+
+slices:
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [0,9]
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [5,14]
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [10,19]
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [15,24]
+  - sources:
+    - model: seyf1elislam/WestKunai-Hermes-7b
+      layer_range: [20,32]
+merge_method: passthrough
+dtype: bfloat16
--- a/model-00001-of-00012.safetensors
+++ b/model-00001-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ff8060816ad077c76024bc0d96d20307d73f5d0c6702fd1b788d452cfab6d7
+size 1979765296
--- a/model-00002-of-00012.safetensors
+++ b/model-00002-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0153f71978f324ae69f4ed16431231949a660419504cf54c3fe5e8316cf71a12
+size 1979799336
--- a/model-00003-of-00012.safetensors
+++ b/model-00003-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6798d636dc47c33d7032ff39e04a912d219a25a679010105dbcaf267b11e0404
+size 1895886560
--- a/model-00004-of-00012.safetensors
+++ b/model-00004-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a0e1e784da3407b59e7888b0619cbdaa301351090935e50a5a4e05819bbe4e
+size 1895895824
--- a/model-00005-of-00012.safetensors
+++ b/model-00005-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc624a067a3316bf353d9ae0bbed6633165afb8f6fc7caa60ed7054228d796b
+size 1889611984
--- a/model-00006-of-00012.safetensors
+++ b/model-00006-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b65a3e4b6a18a5ede9da0014f4b7539d3368ba8b18a3c31f57dfac7ec87337
+size 1979781456
--- a/model-00007-of-00012.safetensors
+++ b/model-00007-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e6554b1bfc888edf3cdfb18aed22e9ca692853b6267bf6e84ae5e4a2681a946
+size 1946243968
--- a/model-00008-of-00012.safetensors
+++ b/model-00008-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24096e65c810d12ef2b33b5ed3a6453745e628c9b21b8f4c5184a9ceac6ca11
+size 1979781456
--- a/model-00009-of-00012.safetensors
+++ b/model-00009-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec86c048e3de7a76ffff7f7f485043deb5a13006a2f8e6b5a784733cdbd8cea8
+size 1889603656
--- a/model-00010-of-00012.safetensors
+++ b/model-00010-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e23c4c4ae9f80d2150f1ee1d3d66a0b18e13a919f60ccab07531ea12e7d2e3
+size 1895928120
--- a/model-00011-of-00012.safetensors
+++ b/model-00011-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a82ac6867347b8996f082cac4dcf4038f32335dd927f35fd766573637fce0a
+size 1895903224
--- a/model-00012-of-00012.safetensors
+++ b/model-00012-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa86484ac6dbe9999ebdbfc485fcbac4d84250b0ab8086459b56858e881c3da
+size 234897880
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- 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
+}