初始化项目，由ModelHub XC社区提供模型

Model: 0arch-io/dolphin-v2-8b-abliterated Source: Original Platform
2026-06-10 13:58:17 +08:00
commit 3145c1d9b0
16 changed files with 402 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,38 @@
+*.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
+dolphin-v2-8b-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-v2-8b-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,174 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+tags:
+  - uncensored
+  - abliterated
+  - qwen3
+  - dolphin
+  - sft
+  - trc
+language:
+  - en
+pipeline_tag: text-generation
+model-index:
+  - name: dolphin-v2-8b-abliterated
+    results:
+      - task:
+          type: multiple-choice
+          name: ARC Challenge
+        dataset:
+          name: ARC Challenge
+          type: ai2_arc
+          config: ARC-Challenge
+          split: test
+        metrics:
+          - type: acc
+            value: 56.5
+            name: Accuracy
+          - type: acc_norm
+            value: 54.0
+            name: Normalized Accuracy
+      - task:
+          type: multiple-choice
+          name: HellaSwag
+        dataset:
+          name: HellaSwag
+          type: Rowan/hellaswag
+          split: validation
+        metrics:
+          - type: acc_norm
+            value: 64.5
+            name: Normalized Accuracy
+      - task:
+          type: multiple-choice
+          name: TruthfulQA MC2
+        dataset:
+          name: TruthfulQA
+          type: truthful_qa
+          config: multiple_choice
+          split: validation
+        metrics:
+          - type: acc
+            value: 48.8
+            name: Accuracy
+      - task:
+          type: multiple-choice
+          name: Winogrande
+        dataset:
+          name: Winogrande
+          type: winogrande
+          config: winogrande_xl
+          split: validation
+        metrics:
+          - type: acc
+            value: 57.0
+            name: Accuracy
+---
+
+# Dolphin V2 8B Abliterated
+
+An uncensored 8B parameter language model built on Qwen3-8B, fine-tuned on 1.35M high-quality instruction samples and abliterated to remove refusal behavior. Developed for TRC (TPU Research Cloud) research.
+
+## Model Details
+
+- **Architecture:** Qwen3ForCausalLM (36 layers, 4096 hidden, 32 attn heads, 8 KV heads)
+- **Parameters:** 8.2B
+- **Context Length:** 4096 (trained), 40960 (max supported)
+- **Precision:** bfloat16
+- **License:** Apache 2.0
+
+## Training
+
+### SFT Phase
+- **Base model:** Qwen/Qwen3-8B
+- **Hardware:** Google Cloud TPU v6e-16 (spot)
+- **Framework:** MaxText (JAX)
+- **Steps:** 130,000 (~3 epochs)
+- **Learning rate:** 5e-6 with cosine decay
+- **Warmup:** 200 steps
+- **Effective batch size:** 16
+- **Sequence length:** 4096
+
+### Training Dataset (1.35M samples)
+
+| Dataset | Samples | Purpose |
+|---------|---------|---------|
+| NousResearch/Hermes-3-Dataset | ~959K | Core uncensored assistant behavior |
+| allenai/tulu-3-sft-mixture | ~200K | Diverse instruction following |
+| HuggingFaceTB/smoltalk (magpie-ultra) | ~100K | High quality diverse tasks |
+| HuggingFaceTB/smoltalk (numina-cot) | ~50K | Math reasoning |
+| HuggingFaceTB/smoltalk (self-oss-instruct) | ~50K | Code generation |
+| LDJnr/Capybara | ~16K | Multi-turn conversations |
+
+All data was filtered to remove refusal patterns, safety-alignment subsets, and `<think>` reasoning tags.
+
+### Abliteration Phase
+
+After SFT, the model was abliterated using the weight orthogonalization technique from [Arditi et al. (2024)](https://arxiv.org/abs/2406.11717) to remove residual refusal behavior.
+
+- **Technique:** Multi-direction abliteration (weight orthogonalization)
+- **Directions removed:** 5
+- **Target layers:** 35, 34, 36, 33, 16 (selected by highest refusal direction scores)
+- **Samples used:** 256 harmful/harmless instruction pairs
+- **Method:** For each selected layer, the refusal direction was identified via mean difference between harmful and harmless activations, then orthogonalized out of the weight matrices.
+
+## Benchmark Results
+
+Evaluated using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) with 200 samples per task, 5-shot (except TruthfulQA which is 0-shot).
+
+| Benchmark | Metric | Score |
+|-----------|--------|-------|
+| ARC-Challenge | acc | 56.5% |
+| ARC-Challenge | acc_norm | 54.0% |
+| HellaSwag | acc_norm | 64.5% |
+| TruthfulQA MC2 | acc | 48.8% |
+| Winogrande | acc | 57.0% |
+
+## GGUF Quantizations
+
+| File | Quant | Size | Description |
+|------|-------|------|-------------|
+| `dolphin-v2-8b-abliterated-Q8_0.gguf` | Q8_0 | 8.3 GB | Best quality quantization |
+| `dolphin-v2-8b-abliterated-Q4_K_M.gguf` | Q4_K_M | 4.8 GB | Good balance of quality and size |
+
+### Usage with llama.cpp
+
+```bash
+llama-server -m dolphin-v2-8b-abliterated-Q8_0.gguf -ngl 99 -c 4096
+```
+
+### Usage with Ollama
+
+```bash
+# Create a Modelfile
+echo 'FROM ./dolphin-v2-8b-abliterated-Q8_0.gguf' > Modelfile
+ollama create dolphin-v2-abliterated -f Modelfile
+ollama run dolphin-v2-abliterated
+```
+
+### Usage with Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("0arch-io/dolphin-v2-8b-abliterated", torch_dtype="bfloat16", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("0arch-io/dolphin-v2-8b-abliterated")
+
+messages = [{"role": "user", "content": "Hello, how are you?"}]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
+outputs = model.generate(inputs, max_new_tokens=512, temperature=0.7)
+print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
+```
+
+## Disclaimer
+
+This is a research model with no content filters. It will comply with any request without refusing. The creators are not responsible for how this model is used. Use responsibly.
+
+## Acknowledgments
+
+- **Qwen team** for the Qwen3-8B base model
+- **Google TRC** for TPU compute
+- **NousResearch** for the Hermes-3 dataset
+- **Arditi et al.** for the abliteration technique
+- Built with [MaxText](https://github.com/AI-Hypercomputer/maxtext) on Google Cloud TPU
--- a/abliteration_metadata.json
+++ b/abliteration_metadata.json
@@ -0,0 +1,70 @@
+{
+  "base_model": "/Users/josephrodriguez/dolphin-v2-hf",
+  "technique": "abliteration_multi",
+  "n_directions": 5,
+  "selected_layers": [
+    [
+      35,
+      0.0120849609375
+    ],
+    [
+      34,
+      0.01190185546875
+    ],
+    [
+      36,
+      0.01165771484375
+    ],
+    [
+      33,
+      0.01153564453125
+    ],
+    [
+      16,
+      0.01141357421875
+    ]
+  ],
+  "n_samples": 256,
+  "top_scores": [
+    [
+      35,
+      0.0120849609375
+    ],
+    [
+      34,
+      0.01190185546875
+    ],
+    [
+      36,
+      0.01165771484375
+    ],
+    [
+      33,
+      0.01153564453125
+    ],
+    [
+      16,
+      0.01141357421875
+    ],
+    [
+      32,
+      0.0113525390625
+    ],
+    [
+      9,
+      0.01129150390625
+    ],
+    [
+      15,
+      0.01129150390625
+    ],
+    [
+      17,
+      0.01129150390625
+    ],
+    [
+      25,
+      0.01129150390625
+    ]
+  ]
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/dolphin-v2-8b-abliterated-Q4_K_M.gguf
+++ b/dolphin-v2-8b-abliterated-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14e78351d8a6fd04035f33b622ff9eaeb4a014163aeeb7ea3bd0dd6a38b508c3
+size 5027779168
--- a/dolphin-v2-8b-abliterated-Q8_0.gguf
+++ b/dolphin-v2-8b-abliterated-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c3959fe52d0a692255eb338f9364191f2b2d67a1908de4cb5d3471e65ce995
+size 8709513824
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "5.2.0",
+  "use_cache": true
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305f4dfbf58a6a58f036c93f739efb1e8a21051a8a6c74afa87c3185cbe3e91b
+size 16381517208
--- a/refusal_direction.pt
+++ b/refusal_direction.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8570da901ad8f98cde394667698ceb133a0ebaccb1e002697a303c21697302b2
+size 9839
--- a/refusal_direction_0_layer35.pt
+++ b/refusal_direction_0_layer35.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f34e224ec017dc628b8421ee39e1f315b46931ce9ec65e2018707e255946aa
+size 9973
--- a/refusal_direction_1_layer34.pt
+++ b/refusal_direction_1_layer34.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44566fda6a01653d54896f652d0fa5435e34ccbe7c892f2de4f6cc93647450d6
+size 9973
--- a/refusal_direction_2_layer36.pt
+++ b/refusal_direction_2_layer36.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f468ebff8d0848a86c8f9bb51839d138d08fd9acfca7c3f26023d1bb8fc7385b
+size 9973
--- a/refusal_direction_3_layer33.pt
+++ b/refusal_direction_3_layer33.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c21e1d44b87f2ce63e52c6bfb14486d61b1eb6a45bdadec39184023ffc68324
+size 9973
--- a/refusal_direction_4_layer16.pt
+++ b/refusal_direction_4_layer16.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa277d5ebbcd91ffb613d50df265ea0d6b941e1611dc57c682cdec400791b4d
+size 9973
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8311d68134751bc4a0981a69b77aadb19f5dc31828c6ce23878edd7d99ab6688
+size 11422915
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}