初始化项目，由ModelHub XC社区提供模型

Model: SteelStorage/Aura-Llama-Abliterated Source: Original Platform
2026-06-01 04:09:17 +08:00
commit 31a5954901
11 changed files with 412927 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 +1,198 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+base_model:
+- failspy/Llama-3-8B-Instruct-abliterated
+model-index:
+- name: Aura-Llama-Abliterated
+  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: 49.23
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/Aura-Llama-Abliterated
+      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: 72.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/Aura-Llama-Abliterated
+      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: 55.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/Aura-Llama-Abliterated
+      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: 46.63
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/Aura-Llama-Abliterated
+      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: 69.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/Aura-Llama-Abliterated
+      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: 27.6
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/Aura-Llama-Abliterated
+      name: Open LLM Leaderboard
+---
+
+<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> 
+  <title>Aura-llama-3 Data Card</title> 
+  <link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet"> 
+  <style> body { font-family: 'Quicksand', sans-serif; background: linear-gradient(135deg, #2E3440 0%, #1A202C 100%); color: #D8DEE9; margin: 0; padding: 0; font-size: 16px; } 
+    .container { width: 100%; max-width: 1440px; margin: 20px auto; background-color: rgba(255, 255, 255, 0.02); padding: 20px; border-radius: 12px; box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2); backdrop-filter: blur(10px); border: 1px solid rgba(255, 255, 255, 0.1); } 
+    .header h1 { font-size: 28px; color: #ECEFF4; margin: 0 0 20px 0; text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3); } 
+    .update-section { margin-top: 30px; } .update-section h2 { font-size: 24px; color: #88C0D0; } 
+    .update-section p { font-size: 16px; line-height: 1.6; color: #ECEFF4; } 
+    .info img { width: 100%; border-radius: 10px; margin-bottom: 15px; } 
+    a { color: #88C0D0; text-decoration: none; } 
+    a:hover { color: #A3BE8C; } 
+    pre { background-color: rgba(255, 255, 255, 0.05); padding: 10px; border-radius: 5px; overflow-x: auto; } 
+    code { font-family: 'Courier New', monospace; color: #A3BE8C; } </style> </head> <body> <div class="container"> 
+      <div class="header"> 
+        <h1>Aura-llama-3-Abliterated</h1> </div> <div class="info"> 
+          <img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/AwLNDVB-GIY7k0wnVV_TX.png" alt="Aura-llama-Abliterated Image"> 
+          <p>Now that the cute anime girl has your attention.</p> 
+          <p>UPDATE: Model is now using the abliterated version of meta llama 3 8b </p>
+          <p>Aura-llama is using the methodology presented by SOLAR for scaling LLMs called depth up-scaling (DUS), which encompasses architectural modifications with continued pretraining. Using the solar paper as a base, I integrated Llama-3 weights into the upscaled layers, and In the future plan to continue training the model.</p> 
+          <p>Aura-llama is a merge of the following models to create a base model to work from:</p> 
+          <ul> 
+            <li><a href="https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated">failspy/Llama-3-8B-Instruct-abliterated</a></li> 
+            <li><a href="https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated">failspy/Llama-3-8B-Instruct-abliterated</a></li> 
+          </ul> 
+        </div> 
+      <div class="update-section"> 
+        <h2>Abliterated Merged Evals (Has Not Been Finetuned):</h2> 
+        <p>Aura-llama-Abliterated</p> 
+        <ul> 
+          <li>Avg: ?</li> 
+          <li>ARC: ?</li> 
+          <li>HellaSwag: ?</li> 
+          <li>MMLU: ?</li> 
+          <li>T-QA: ?</li> 
+          <li>Winogrande: ?</li> 
+          <li>GSM8K: ?</li> 
+        </ul> 
+        <h2>Non Abliterated Merged Evals (Has Not Been Finetuned):</h2> 
+        <p>Aura-llama-Original</p> 
+        <ul> 
+          <li>Avg: 63.13</li> 
+          <li>ARC: 58.02</li> 
+          <li>HellaSwag: 77.82</li> 
+          <li>MMLU: 65.61</li> 
+          <li>T-QA: 51.94</li> 
+          <li>Winogrande: 73.40</li> 
+          <li>GSM8K: 52.01</li> 
+        </ul> 
+      </div> 
+      <div class="update-section"> 
+        <h2>🧩 Configuration</h2> 
+        <pre><code>
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 12]
+    model: failspy/Llama-3-8B-Instruct-abliterated
+- sources:
+  - layer_range: [8, 20]
+    model: failspy/Llama-3-8B-Instruct-abliterated
+- sources:
+  - layer_range: [16, 28]
+    model: failspy/Llama-3-8B-Instruct-abliterated
+- sources:
+  - layer_range: [24, 32]
+    model: failspy/Llama-3-8B-Instruct-abliterated
+        </code></pre> 
+      </div> 
+    </div> 
+    </body> 
+    </html>
+
+# [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_TheSkullery__Aura-Llama-Abliterated)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |53.46|
+|AI2 Reasoning Challenge (25-Shot)|49.23|
+|HellaSwag (10-Shot)              |72.27|
+|MMLU (5-Shot)                    |55.71|
+|TruthfulQA (0-shot)              |46.63|
+|Winogrande (5-shot)              |69.30|
+|GSM8k (5-shot)                   |27.60|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "failspy/Llama-3-8B-Instruct-abliterated",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 44,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,15 @@
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 12]
+    model: failspy/Llama-3-8B-Instruct-abliterated
+- sources:
+  - layer_range: [8, 20]
+    model: failspy/Llama-3-8B-Instruct-abliterated
+- sources:
+  - layer_range: [16, 28]
+    model: failspy/Llama-3-8B-Instruct-abliterated
+- sources:
+  - layer_range: [24, 32]
+    model: failspy/Llama-3-8B-Instruct-abliterated
--- 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:b3f142d6cbb25a2b532664785051d36f3ff6d25f58e82444bd8541a7d998ca88
+size 9976501408
--- 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:a5c0ab88a4990964f477bdea7666d8b6702f33db09289e56e1751015ac52b1de
+size 9915718904
--- 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:a680e6db32c47f33e3578cb73ad01253a345be006a447f66d5342cb7b94bdd24
+size 1403036680
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json