初始化项目，由ModelHub XC社区提供模型

Model: Gille/StrangeMerges_45-7B-dare_ties Source: Original Platform
2026-05-12 15:45:26 +08:00
commit 97f2f64355
11 changed files with 91363 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 +1,74 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Q-bert/MetaMath-Cybertron-Starling
+- ozayezerceli/BetterSaul-7B-slerp
+- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
+- EmbeddedLLM/Mistral-7B-Merge-14-v0.2
+base_model:
+- Q-bert/MetaMath-Cybertron-Starling
+- ozayezerceli/BetterSaul-7B-slerp
+- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
+- EmbeddedLLM/Mistral-7B-Merge-14-v0.2
+---
+
+# StrangeMerges_45-7B-dare_ties
+
+StrangeMerges_45-7B-dare_ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
+* [ozayezerceli/BetterSaul-7B-slerp](https://huggingface.co/ozayezerceli/BetterSaul-7B-slerp)
+* [chihoonlee10/T3Q-Mistral-Orca-Math-DPO](https://huggingface.co/chihoonlee10/T3Q-Mistral-Orca-Math-DPO)
+* [EmbeddedLLM/Mistral-7B-Merge-14-v0.2](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.2)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: Q-bert/MetaMath-Cybertron-Starling
+    parameters:
+      weight: 0.3
+      density: 0.53
+  - model: ozayezerceli/BetterSaul-7B-slerp
+    parameters:
+      weight: 0.2
+      density: 0.53
+  - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
+    parameters:
+      weight: 0.4
+      density: 0.53
+  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
+    parameters:
+      weight: 0.1
+      density: 0.53
+base_model: Gille/StrangeMerges_44-7B-dare_ties
+merge_method: dare_ties
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Gille/StrangeMerges_45-7B-dare_ties"
+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"])
+```
--- a/config.json
+++ b/config.json
@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Gille/StrangeMerges_44-7B-dare_ties",
+  "add_gates": false,
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,21 @@
+
+models:
+  - model: Q-bert/MetaMath-Cybertron-Starling
+    parameters:
+      weight: 0.3
+      density: 0.53
+  - model: ozayezerceli/BetterSaul-7B-slerp
+    parameters:
+      weight: 0.2
+      density: 0.53
+  - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
+    parameters:
+      weight: 0.4
+      density: 0.53
+  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
+    parameters:
+      weight: 0.1
+      density: 0.53
+base_model: Gille/StrangeMerges_44-7B-dare_ties
+merge_method: dare_ties
+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 sha256:08e2fe48c02a2847a59ef090d3941789659a9acc3f37c6809c0e97dd28157b24
+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:fc6eacc85d218e45b8c6c02aa43e85670def335910ba623b833cdd10317004b9
+size 4540516344
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}