初始化项目，由ModelHub XC社区提供模型

Model: vicgalle/franken-SOLAR-18B-v1.0 Source: Original Platform
2026-04-23 09:22:07 +08:00
commit 102b0e4f54
13 changed files with 393 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 +1,200 @@
+---
+license: apache-2.0
+tags:
+- mergekit
+- merge
+- solar
+base_model:
+- upstage/SOLAR-10.7B-Instruct-v1.0
+- NousResearch/Nous-Hermes-2-SOLAR-10.7B
+model-index:
+- name: franken-SOLAR-18B-v1.0
+  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: 65.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0
+      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: 86.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0
+      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: 63.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0
+      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: 62.14
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0
+      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: 78.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0
+      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: 45.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0
+      name: Open LLM Leaderboard
+---
+# vicgalle/franken-SOLAR-18B-v1.0
+
+This is a SOLAR-like model upscaled to 18B. 
+It is a frankenmerge model created using mergekit, alternating layers of Nous-Hermes-2-SOLAR-10.7B and SOLAR-10.7B-Instruct.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5fad8602b8423e1d80b8a965/mMyHMuuftG71_o4at5suy.png)
+
+Evaluations coming soon! 
+
+This model has very good writing capabilities (compared to SOLAR-10.7B), specially for role-playing.
+
+Quantized GGUF variants here https://huggingface.co/vicgalle/franken-SOLAR-18B-v1.0-GGUF
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
+* [NousResearch/Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+      layer_range: [0, 12]
+  - sources:
+    - model: upstage/SOLAR-10.7B-Instruct-v1.0
+      layer_range: [6, 18]
+  - sources:
+    - model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+      layer_range: [13, 25]
+  - sources:
+    - model: upstage/SOLAR-10.7B-Instruct-v1.0
+      layer_range: [19, 31]
+  - sources:
+    - model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+      layer_range: [26, 38]
+  - sources:
+    - model: upstage/SOLAR-10.7B-Instruct-v1.0
+      layer_range: [32, 44]
+  - sources:
+    - model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+      layer_range: [39, 48]
+    
+merge_method: passthrough
+dtype: float16
+
+```
+
+
+### Usage
+
+You can use the provided template:
+
+```
+tokenizer = AutoTokenizer.from_pretrained("vicgalle/franken-SOLAR-18B-v1.0")
+model = AutoModelForCausalLM.from_pretrained("vicgalle/franken-SOLAR-18B-v1.0", torch_dtype=torch.float16, load_in_4bit=True)
+
+conversation = [ {'role': 'system', 'content': SYSTEM_PROMPT}, {'role': 'user', 'content': USER_PROMPT} ] 
+prompt = tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, use_cache=True, max_new_tokens=1024, do_sample=True, temperature=0.8)
+output_text = tokenizer.decode(outputs[0]) 
+```
+
+# [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_vicgalle__franken-SOLAR-18B-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.03|
+|AI2 Reasoning Challenge (25-Shot)|65.53|
+|HellaSwag (10-Shot)              |86.45|
+|MMLU (5-Shot)                    |63.72|
+|TruthfulQA (0-shot)              |62.14|
+|Winogrande (5-shot)              |78.53|
+|GSM8k (5-shot)                   |45.79|
+
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 81,
+  "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": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32002
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,25 @@
+slices:
+  - sources:
+    - model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+      layer_range: [0, 12]
+  - sources:
+    - model: upstage/SOLAR-10.7B-Instruct-v1.0
+      layer_range: [6, 18]
+  - sources:
+    - model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+      layer_range: [13, 25]
+  - sources:
+    - model: upstage/SOLAR-10.7B-Instruct-v1.0
+      layer_range: [19, 31]
+  - sources:
+    - model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+      layer_range: [26, 38]
+  - sources:
+    - model: upstage/SOLAR-10.7B-Instruct-v1.0
+      layer_range: [32, 44]
+  - sources:
+    - model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+      layer_range: [39, 48]
+    
+merge_method: passthrough
+dtype: float16
--- a/model-00001-of-00004.safetensors
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0e977d2ef6515f26ce5f5f3ee2984b615024242d0c2d0143ae80413107597e
+size 9892665400
--- a/model-00002-of-00004.safetensors
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b86043589fb446d85905cee90bcb84644739ec981aef85b5fdb0139fda10db0
+size 9999638496
--- a/model-00003-of-00004.safetensors
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec54ce87786492320c08e15ff4cabde9270aef79a9b0805f099dbbbb7657a282
+size 9949272800
--- a/model-00004-of-00004.safetensors
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a442cf3856071d011b15087027031369a0b7c5ab463992848c0704806a8ed3d
+size 6016980864
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,61 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}