初始化项目，由ModelHub XC社区提供模型

Model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2 Source: Original Platform
2026-05-22 04:40:17 +08:00
commit 4e55a12d48
11 changed files with 91364 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 +1,79 @@
+---
+license: cc-by-nc-4.0
+language:
+- en
+tags:
+- merge
+base_model:
+- janai-hq/trinity-v1
+- EmbeddedLLM/Mistral-7B-Merge-14-v0
+---
+
+# Update 2023-12-19
+
+In light of [dataset contamination issue among the merged models](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/474)
+raised by the community in recent days, in particular
+[berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha),
+[Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling), and
+[janai-hq/trinity-v1](https://huggingface.co/janai-hq/trinity-v1),
+we decided to remake another model without the models mentioned.
+Additionally, their CC-by-NC-4.0 license is restrictive and thus are not suitable for an open model.
+
+# Open LLM Leaderboard
+For reference, this model obtained an average score of 72.88.
+
+| Average    | 72.88 |
+|------------|-------|
+| ARC        | 68.86 |
+| HellaSwag  | 87.01 |
+| MMLU       | 65.05 |
+| TruthfulQA | 64.19 |
+| Winogrande | 81.69 |
+| GSM8K      | 70.51  |
+
+
+# Model Description
+This is an experiment to test merging 14 models using DARE TIES 🦙
+
+The merged model is then merged again with [janai-hq/trinity-v1](https://huggingface.co/janai-hq/trinity-v1) using Gradient SLERP.
+The result is a base model that performs quite well but requires some further instruction fine-tuning.
+
+The 14 models are as follows:
+1. [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
+2. [ehartford/dolphin-2.2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b)
+3. [SciPhi/SciPhi-Mistral-7B-32k](https://huggingface.co/SciPhi/SciPhi-Mistral-7B-32k)
+4. [ehartford/samantha-1.2-mistral-7b](https://huggingface.co/ehartford/samantha-1.2-mistral-7b)
+5. [Arc53/docsgpt-7b-mistral](https://huggingface.co/Arc53/docsgpt-7b-mistral)
+6. [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha)
+7. [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
+8. [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
+9. [v1olet/v1olet_marcoroni-go-bruins-merge-7B](https://huggingface.co/v1olet/v1olet_marcoroni-go-bruins-merge-7B)
+10. [beowolx/MistralHermes-CodePro-7B-v1](https://huggingface.co/beowolx/MistralHermes-CodePro-7B-v1)
+11. [TIGER-Lab/MAmmoTH-7B-Mistral](https://huggingface.co/TIGER-Lab/MAmmoTH-7B-Mistral)
+12. [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
+13. [Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp)
+14. [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
+
+- base model: [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+
+The yaml config file for this model is here:
+
+```yaml
+slices:
+  - sources:
+      - model: janai-hq/trinity-v1
+        layer_range: [0, 32]
+      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: janai-hq/trinity-v1
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+
+```
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "GreenNode/GreenNodeLM-7B-v1olet",
+  "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": "4.36.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/merge.yml
+++ b/merge.yml
@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: /media/data5/hf_models/trinity-v1
+        layer_range: [0, 32]
+      - model: /media/data5/jh/S-merge-14-b
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: /media/data5/hf_models/trinity-v1
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+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 sha256:694de2b1006db623dd3621c13bb5e4c2ffa7d2776e6de07dafc1cebd42151d00
+size 9976544080
--- 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 sha256:35f899ae4463a09fd47ffe86e911760f6c8e3be51d3a20b768354ee2f611a94a
+size 4506953960
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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 +1,48 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}