初始化项目，由ModelHub XC社区提供模型

Model: nbeerbower/A0l-12B-heretic
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,48 @@
+---
+library_name: transformers
+license: apache-2.0
+datasets:
+- schneewolflabs/Athanorlite-DPO
+base_model:
+- nbeerbower/Schreiber-mistral-nemo-12B
+tags:
+- heretic
+- uncensored
+- decensored
+- abliterated
+---
+# This is a decensored version of [schneewolflabs/A0l-12B](https://huggingface.co/schneewolflabs/A0l-12B), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0
+
+## Abliteration parameters
+
+| Parameter | Value |
+| :-------- | :---: |
+| **direction_index** | per layer |
+| **attn.o_proj.max_weight** | 1.24 |
+| **attn.o_proj.max_weight_position** | 33.41 |
+| **attn.o_proj.min_weight** | 0.89 |
+| **attn.o_proj.min_weight_distance** | 22.95 |
+| **mlp.down_proj.max_weight** | 1.47 |
+| **mlp.down_proj.max_weight_position** | 25.98 |
+| **mlp.down_proj.min_weight** | 0.00 |
+| **mlp.down_proj.min_weight_distance** | 12.82 |
+
+## Performance
+
+| Metric | This model | Original model ([schneewolflabs/A0l-12B](https://huggingface.co/schneewolflabs/A0l-12B)) |
+| :----- | :--------: | :---------------------------: |
+| **KL divergence** | 0.0364 | 0 *(by definition)* |
+| **Refusals** | 10/100 | 40/100 |
+
+-----
+
+
+# A0l-12B
+
+Same training run as [schneewolflabs/A0-12B](https://huggingface.co/schneewolflabs/A0-12B), but using [schneewolflabs/Athanorlite-DPO](https://huggingface.co/schneewolflabs/Athanorlite-DPO) as the dataset.
+
+Preliminary tests have shown this model has superior writing capabilities to A0-12B.
+
+## Configuration
+
+![image/png](https://raw.githubusercontent.com/Schneewolf-Labs/Merlina/refs/heads/main/frontend/madewithmerlina_smol.png)

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 4,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 4,
+  "transformers_version": "5.2.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db5dd5b175762a31bb9e8369d4e839a891193b5483fbe081b50ec251e857033
+size 24495607560

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699c0464871a74475719218faf11600f6078f0d2bcaf1fef71dfa1eeac7b91d0
+size 17078470