初始化项目，由ModelHub XC社区提供模型

Model: nfaheem/SOLAR-10.7B-Instruct-ties Source: Original Platform
2026-05-26 10:00:17 +08:00
commit 5d7dc1279b
12 changed files with 91382 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 +1,91 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP
+- VAGOsolutions/SauerkrautLM-SOLAR-Instruct
+---
+
+# SOLAR-10.7B-Instruct-ties
+
+SOLAR-10.7B-Instruct-ties is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP](https://huggingface.co/kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP)
+* [VAGOsolutions/SauerkrautLM-SOLAR-Instruct](https://huggingface.co/VAGOsolutions/SauerkrautLM-SOLAR-Instruct)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: upstage/SOLAR-10.7B-Instruct-v1.0
+    # no parameters necessary for base model
+  - model: kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: VAGOsolutions/SauerkrautLM-SOLAR-Instruct
+    parameters:
+      density: 0.5
+      weight: 0.3
+merge_method: ties
+base_model: upstage/SOLAR-10.7B-Instruct-v1.0
+parameters:
+  normalize: true
+dtype: float16
+```
+## 💻 Example Python Code
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+model_name_or_path = "nfaheem/SOLAR-10.7B-Instruct-ties"
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
+                                             device_map="auto",
+                                             revision="main")
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+prompt = "Write a story about llamas"
+system_message = "You are a story writing assistant"
+prompt_template=f'''{prompt}
+'''
+
+print("\n\n*** Generate:")
+
+input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
+output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
+print(tokenizer.decode(output[0]))
+
+# Inference can also be done using transformers' pipeline
+
+print("*** Pipeline:")
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    repetition_penalty=1.1
+)
+
+print(pipe(prompt_template)[0]['generated_text'])
+```
+## 📋 Summary Eval:
+
+| Average |  ARC  | HellaSwag |  MMLU  | TruthfulQA | Winogrande | GSM8K |
+|---------|-------|-----------|--------|------------|------------|-------|
+|  74.24  | 70.9  |   88.58   |  66.34 |    71.88   |    83.5    | 64.06 |
+
+
+
+## 📈 Huggingface Leaderboard
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b6cc785fd617abdfec6bed/yFGDhunmwne1T6roFVDKg.png)
+
+
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,19 @@
+base_model: upstage/SOLAR-10.7B-Instruct-v1.0
+dtype: float16
+merge_method: ties
+parameters:
+  normalize: 1.0
+slices:
+- sources:
+  - layer_range: [0, 48]
+    model: upstage/SOLAR-10.7B-Instruct-v1.0
+  - layer_range: [0, 48]
+    model: kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - layer_range: [0, 48]
+    model: VAGOsolutions/SauerkrautLM-SOLAR-Instruct
+    parameters:
+      density: 0.5
+      weight: 0.3
--- a/model-00001-of-00003.safetensors
+++ b/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade83568ed52e6d3156175fc8a69e4f91a3986b556f96c55be694bb9f38cfc03
+size 9942989800
--- a/model-00002-of-00003.safetensors
+++ b/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2283fac8a842f9ebdebf1e1b86d553e4ff025aca9ed68a0d1b19daa93c146b6b
+size 9831823880
--- a/model-00003-of-00003.safetensors
+++ b/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77ee07d982e0761617a130d52b2c66abdd98013d7d22f81c20bb5ef72ef2a01
+size 1688284744
--- 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": "</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 +1,43 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}