初始化项目，由ModelHub XC社区提供模型

Model: EmbeddedLLM/Mistral-7B-Merge-02-v0 Source: Original Platform
2026-04-13 02:28:58 +08:00
commit eda27b5731
11 changed files with 91331 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 +1,57 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- merge
+base_model:
+- teknium/OpenHermes-2.5-Mistral-7B
+- Intel/neural-chat-7b-v3-3
+---
+
+# Model Description
+This is an experiment to compare merging 2 models using DARE TIES versus SLERP 🦙
+
+We are mainly interested to compare against [Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp)
+
+The 2 models involved in the merge as follows:
+1. [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
+2. [Intel/neural-chat-7b-v3-3](https://huggingface.co/Intel/neural-chat-7b-v3-3)
+
+- base model: [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+
+The yaml config file for the merge is:
+
+```yaml
+models:
+  - model: mistralai/Mistral-7B-v0.1
+    # no parameters necessary for base model
+  - model: teknium/OpenHermes-2.5-Mistral-7B
+    parameters:
+      weight: 0.5
+      density: 0.5
+  - model: Intel/neural-chat-7b-v3-3
+    parameters:
+      weight: 0.5
+      density: 0.5
+merge_method: dare_ties
+base_model: mistralai/Mistral-7B-v0.1
+parameters:
+  int8_mask: true
+dtype: bfloat16
+```
+
+# Open LLM Leaderboard
+
+Note that with more tuning DARE TIES might achieve better results.
+
+|            | DARE TIES | SLERP |
+|------------|-----------|-------|
+| Average    | 70.69     | 71.38 |
+| ARC        | 67.49     | 68.09 |
+| HellaSwag  | 85.78     | 86.2  |
+| MMLU       | 64.1      | 64.26 |
+| TruthfulQA | 60.52     | 62.78 |
+| Winogrande | 79.01     | 79.16 |
+| GSM8K      | 67.25     | 67.78 |
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/media/data5/hf_models/Mistral-7B-v0.1",
+  "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": "4.36.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/merge.yml
+++ b/merge.yml
@@ -0,0 +1,16 @@
+models:
+  - model: /media/data5/hf_models/Mistral-7B-v0.1
+    # no parameters necessary for base model
+  - model: /media/data5/hf_models/OpenHermes-2.5-Mistral-7B
+    parameters:
+      weight: 0.5
+      density: 0.5
+  - model: /media/data5/hf_models/neural-chat-7b-v3-3
+    parameters:
+      weight: 0.5
+      density: 0.5
+merge_method: dare_ties
+base_model: /media/data5/hf_models/Mistral-7B-v0.1
+parameters:
+  int8_mask: true
+dtype: bfloat16
--- 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 sha256:560ab501e23b8c2a0e2875a12969de51f83331368146b04eaf065b179e10a9c2
+size 9942981696
--- 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 sha256:4b21580b525b2a88f4d0211defe6d3783b35c8b55b1b2bcff2bf778a7f77ff7e
+size 4540516344
--- 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
+}