Upload folder using huggingface_hub

README.md

@@ -0,0 +1,18 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- llamas-community/LlamaGuard-7b
+- ParthasarathyShanmugam/llama-2-7b-samantha
+---
+
+# Guardian-Samantha-7b-slerp
+
+Guardian-Samantha-7b-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [llamas-community/LlamaGuard-7b](https://huggingface.co/llamas-community/LlamaGuard-7b)
+* [ParthasarathyShanmugam/llama-2-7b-samantha](https://huggingface.co/ParthasarathyShanmugam/llama-2-7b-samantha)
+
+## 🧩 Configuration
+
+\```yaml{'slices': [{'sources': [{'model': 'llamas-community/LlamaGuard-7b', 'layer_range': [0, 32]}, {'model': 'ParthasarathyShanmugam/llama-2-7b-samantha', 'layer_range': [0, 32]}]}], 'merge_method': 'slerp', 'base_model': 'llamas-community/LlamaGuard-7b', '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': 'float16'}\```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "llamas-community/LlamaGuard-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+base_model:
+  model:
+    path: llamas-community/LlamaGuard-7b
+dtype: float16
+merge_method: slerp
+parameters:
+  t:
+  - filter: self_attn
+    value: [0.0, 0.5, 0.3, 0.7, 1.0]
+  - filter: mlp
+    value: [1.0, 0.5, 0.7, 0.3, 0.0]
+  - value: 0.5
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: llamas-community/LlamaGuard-7b
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: ParthasarathyShanmugam/llama-2-7b-samantha

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4910be430e0fb92fb61489f2905f67579d833eeba8b5129febae96e3d1c51524
+size 9886376040

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbb307cd29730d06c6750f1b040fd3f2ba71d2d1a90c1cfb8a41be9d811c5c7
+size 3590488736

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1", "total_size": 13476831232}, "weight_map": {"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages|length % 2 == 0 %}{% set role = 'Agent' %}{% else %}{% set role = 'User' %}{% endif %}{{ \"[INST] Task: Check if there is unsafe content in '\" + role + \"' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nO1: Violence and Hate. \nShould not\n- Help people plan or engage in violence.\n- Encourage people to engage in violence.\n- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.\n- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.\nCan\n- Provide information on violence and discrimination.\n- Discuss the topics of hate and violence, and can discuss historical events involving violence.\nO2: Sexual Content.\nShould not\n- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.\nCan\n- Discuss topics related to sexuality and sexual education.\n- Provide general information regarding sexual activities.\n- Provide guidance on topics related to sexual health.\nO3: Criminal Planning.\nShould not\n- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.\n- Encourage people to engage in criminal activities or condone criminal behavior.\nCan\n- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.\n- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.\nO4: Guns and Illegal Weapons.\nShould not\n- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.\n- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.\nCan\n- Discuss firearms and the arguments for and against firearm ownership.\nO5: Regulated or Controlled Substances.\nShould not\n- Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.\n- Assist or encourage people to create such substances when it is illegal to do so.\nCan\n- Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).\n- Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.\nO6: Self-Harm.\nShould not\n- Encourage people to harm themselves.\n- Romanticize or condone self-harm or suicide.\n- Provide information regarding the methods of suicide or self-harm.\n- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.\nCan\n- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).\nShould\n- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\n\" }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{% set role = 'User' %}{% elif message['role'] == 'assistant' %}{% set role = 'Agent' %}{% endif %}{{ role + ': ' + content.strip() + '\n\n' }}{% endfor %}{{ \"<END CONVERSATION>\n\nProvide your safety assessment for \" + role + \" in the above conversation:\n- First line must read 'safe' or 'unsafe'.\n- If unsafe, a second line must include a comma-separated list of violated categories. [/INST]\" }}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}