初始化项目，由ModelHub XC社区提供模型

Model: NeverSleep/Mistral-11B-SynthIAirOmniMix Source: Original Platform
2026-07-07 23:38:46 +08:00
commit d931b98108
12 changed files with 91388 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 +1,134 @@
+---
+license: cc-by-nc-4.0
+---
+
+Replaced Zephyr by Airoboros 2.2 and OpenOrca by SynthIA in the mix, the reason why is to see if using merged Mistral models using all the same prompt format would be a better step or not.
+
+## Description
+
+This repo contains fp16 files of Mistral-11B-SynthIAirOmniMix.
+
+## Model used
+- [SynthIA-7B-v1.5](https://huggingface.co/migtissera/SynthIA-7B-v1.5)
+- [Mistral-7B-v0.1-Open-Platypus](https://huggingface.co/akjindal53244/Mistral-7B-v0.1-Open-Platypus)
+- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
+- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b)
+
+## Prompt template
+
+3 out of 4 models use the same prompting format in this merge.
+
+The best one should be this one, since Zephyr and OpenOrca is out of the merge:
+
+```
+(SYSTEM: {context}) - Not mandatory
+USER: {prompt}
+ASSISTANT:
+```
+
+But this one (maybe) work too:
+
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+{prompt}
+
+### Response:
+
+```
+
+## The secret sauce
+
+Mistral-11B-SynthIAOpenPlatypus :
+```
+slices:
+  - sources:
+    - model: "/content/drive/MyDrive/SynthIA-7B-v1.5-bf16"
+      layer_range: [0, 24]
+  - sources:
+    - model: akjindal53244/Mistral-7B-v0.1-Open-Platypus
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: bfloat16
+```
+
+Mistral-11B-CC-Airo :
+```
+slices:
+  - sources:
+    - model: "/content/drive/MyDrive/CC-v1.1-7B-bf16"
+      layer_range: [0, 24]
+  - sources:
+    - model: "/content/drive/MyDrive/Mistral-7B-Airoboros-2.2-bf16"
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: bfloat16
+```
+
+Mistral-11B-SynthIAirOmniMix :
+```
+slices:
+  - sources:
+      - model: Mistral-11B-SynthIAOpenPlatypus
+        layer_range: [0, 48]
+      - model: Mistral-11B-CC-Airo
+        layer_range: [0, 48]
+merge_method: slerp
+base_model: Mistral-11B-OpenOrcaPlatypus
+parameters:
+  t:
+    - filter: lm_head 
+      value: [0.75]
+    - filter: embed_tokens
+      value: [0.75]
+    - filter: self_attn
+      value: [0.75, 0.25]
+    - filter: mlp
+      value:  [0.25, 0.75]
+    - filter: layernorm
+      value: [0.5, 0.5]
+    - filter: modelnorm
+      value: [0.75]
+    - value: 0.5 # fallback for rest of tensors
+dtype: bfloat16
+```
+I use [mergekit](https://github.com/cg123/mergekit) for all the manipulation told here.
+
+## Some scoring I done myself
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/rnraBZz-I9CUD1GVNVF00.png)
+
+|    Task     |Version| Metric |Value |   |Stderr|
+|-------------|------:|--------|-----:|---|-----:|
+|arc_challenge|      0|acc     |0.5410|±  |0.0146|
+|             |       |acc_norm|0.5640|±  |0.0145|
+|arc_easy     |      0|acc     |0.8228|±  |0.0078|
+|             |       |acc_norm|0.8068|±  |0.0081|
+|hellaswag    |      0|acc     |0.6274|±  |0.0048|
+|             |       |acc_norm|0.8167|±  |0.0039|
+|piqa         |      0|acc     |0.8052|±  |0.0092|
+|             |       |acc_norm|0.8232|±  |0.0089|
+|truthfulqa_mc|      1|mc1     |0.3905|±  |0.0171|
+|             |       |mc2     |0.5592|±  |0.0155|
+|winogrande   |      0|acc     |0.7364|±  |0.0124|
+
+## Others
+
+Special thanks to Sushi, [Henky](https://github.com/KoboldAI/KoboldAI-Client) for the machine he give me for big task, and [Charles Goddard](https://github.com/cg123) for his amazing tool.
+
+If you want to support me, you can [here](https://ko-fi.com/undiai).
+# [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_NeverSleep__Mistral-11B-SynthIAirOmniMix)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 54.56   |
+| ARC (25-shot)         | 62.46          |
+| HellaSwag (10-shot)   | 83.13    |
+| MMLU (5-shot)         | 63.47         |
+| TruthfulQA (0-shot)   | 55.69   |
+| Winogrande (5-shot)   | 76.4   |
+| GSM8K (5-shot)        | 11.9        |
+| DROP (3-shot)         | 28.88         |
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/content/SynthIAOpenPlatypus-11B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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": "4.35.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- 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:f3ecc1204bc8a08e6f6ea02d5b8edac246ed5e5436b6dc2ce7f2a5bb93a6cff7
+size 9976544144
--- 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:e415332b6d1255ecc60b7349ef604916f126d3e55b50106a75c1ccd5faf7369d
+size 9976535776
--- 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 sha256:7648667ad67a2d1f6f733ca43ef13c8cf20978e16b2e5b3caaf7499037e4a2cb
+size 1510018920
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,44 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": true
+}