初始化项目，由ModelHub XC社区提供模型

Model: NaniDAO/Meta-Llama-3.1-8B-Instruct-ablated
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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct-ablated",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

direction.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03b0ade42731c2c5e87c145db111310c405effea28221b1be47716876ac864f
+size 5244070

direction_metadata.json

@@ -0,0 +1,4 @@
+{
+    "pos": -2,
+    "layer": 12
+}

generate_directions/mean_diffs.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5675bf91ace106199ca3c6e0376fe66e541beef6e3eead2d140c004abc734f5a
+size 5244075

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d95b3683b2e1ca91a9e854553003bd023cb774e0f37c1730e223c0c381c9a5
+size 32121079000

select_direction/direction_evaluations_filtered.json

@@ -0,0 +1,128 @@
+[
+    {
+        "position": -2,
+        "layer": 12,
+        "refusal_score": -9.75497817993164,
+        "steering_score": 6.006311893463135,
+        "kl_div_score": 0.031104022506242827
+    },
+    {
+        "position": -3,
+        "layer": 12,
+        "refusal_score": -9.373048782348633,
+        "steering_score": 3.060147523880005,
+        "kl_div_score": 0.0867584559325129
+    },
+    {
+        "position": -2,
+        "layer": 11,
+        "refusal_score": -9.023905754089355,
+        "steering_score": 8.601274490356445,
+        "kl_div_score": 0.04104435475014729
+    },
+    {
+        "position": -1,
+        "layer": 12,
+        "refusal_score": -8.680732727050781,
+        "steering_score": 4.7956414222717285,
+        "kl_div_score": 0.01707359135099005
+    },
+    {
+        "position": -5,
+        "layer": 11,
+        "refusal_score": -8.539012908935547,
+        "steering_score": 8.075133323669434,
+        "kl_div_score": 0.06541798089942039
+    },
+    {
+        "position": -1,
+        "layer": 11,
+        "refusal_score": -8.494709014892578,
+        "steering_score": 7.610245227813721,
+        "kl_div_score": 0.014720118389356012
+    },
+    {
+        "position": -1,
+        "layer": 10,
+        "refusal_score": -7.331896781921387,
+        "steering_score": 4.227353096008301,
+        "kl_div_score": 0.08309234215185003
+    },
+    {
+        "position": -5,
+        "layer": 14,
+        "refusal_score": -6.636038303375244,
+        "steering_score": 4.687836170196533,
+        "kl_div_score": 0.0141100183367428
+    },
+    {
+        "position": -5,
+        "layer": 15,
+        "refusal_score": -5.5487470626831055,
+        "steering_score": 2.144282102584839,
+        "kl_div_score": 0.02395068876429188
+    },
+    {
+        "position": -5,
+        "layer": 16,
+        "refusal_score": -5.478135108947754,
+        "steering_score": 1.0938483476638794,
+        "kl_div_score": 0.012701942605351556
+    },
+    {
+        "position": -5,
+        "layer": 10,
+        "refusal_score": -5.376955032348633,
+        "steering_score": 7.028485298156738,
+        "kl_div_score": 0.08796039998349871
+    },
+    {
+        "position": -3,
+        "layer": 14,
+        "refusal_score": -0.7610650062561035,
+        "steering_score": 2.843015193939209,
+        "kl_div_score": 0.01738917049392854
+    },
+    {
+        "position": -2,
+        "layer": 13,
+        "refusal_score": -0.7074866890907288,
+        "steering_score": 2.2404544353485107,
+        "kl_div_score": 0.029380356415469547
+    },
+    {
+        "position": -3,
+        "layer": 15,
+        "refusal_score": -0.5506424307823181,
+        "steering_score": 3.8185596466064453,
+        "kl_div_score": 0.0688840249624754
+    },
+    {
+        "position": -4,
+        "layer": 13,
+        "refusal_score": 1.1747349500656128,
+        "steering_score": 1.4116528034210205,
+        "kl_div_score": 0.026868538149248188
+    },
+    {
+        "position": -4,
+        "layer": 12,
+        "refusal_score": 3.0150375366210938,
+        "steering_score": 5.0643134117126465,
+        "kl_div_score": 0.04881445734757695
+    },
+    {
+        "position": -4,
+        "layer": 10,
+        "refusal_score": 4.0028791427612305,
+        "steering_score": 4.6848249435424805,
+        "kl_div_score": 0.03246775216125604
+    },
+    {
+        "position": -4,
+        "layer": 11,
+        "refusal_score": 4.505997657775879,
+        "steering_score": 3.1285815238952637,
+        "kl_div_score": 0.03856063620648774
+    }
+]

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
+  }
+}