Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+---
+license: mit
+datasets:
+- normster/RealGuardrails
+base_model:
+- allenai/OLMo-2-1124-7B
+---
+
+# RealGuardrails Models
+
+This model was trained on the [RealGuardrails](https://huggingface.co/datasets/normster/RealGuardrails) dataset, an instruction-tuning dataset focused on improving system prompt adherence and precedence. In particular, it was trained via SFT on the `simplemix` split of ~150K examples using our custom training library [torchllms](https://github.com/normster/torchllms).
+
+## Training Hyperparameters
+
+| Name | Value |
+| :--- | :--- |
+| optimizer | AdamW |
+| batch size | 128 |
+| learning rate | 2e-5 |
+| lr scheduler | cosine with 200 warmup steps |
+| betas | (0.9, 0.999) |
+| eps | 1e-8 |
+| weight decay | 0 |
+| epochs | 1 |
+| max grad norm | 1.0 |
+| precision | bf16 |
+| max length | 4096 |

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "Olmo2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 100352
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d646b12c91aa0f91da59a242a92ac3ca4995ecdec30d5addd1939386c718fed6
+size 14597352910

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"weight_map": {"model.embed_tokens.weight": "pytorch_model.bin", "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.0.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.0.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.0.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.1.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.1.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.1.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.2.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.2.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.2.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.3.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.3.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.3.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.4.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.4.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.4.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.5.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.5.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.5.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.6.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.6.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.6.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.7.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.7.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.7.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.8.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.8.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.8.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.9.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.9.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.9.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.10.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.10.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.10.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.11.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.11.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.11.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.12.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.12.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.12.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.13.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.13.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.13.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.14.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.14.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.14.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.15.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.15.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.15.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.16.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.16.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.16.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.17.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.17.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.17.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.18.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.18.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.18.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.19.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.19.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.19.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.20.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.20.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.20.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.21.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.21.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.21.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.22.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.22.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.22.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.23.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.23.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.23.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.24.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.24.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.24.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.25.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.25.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.25.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.26.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.26.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.26.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.27.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.27.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.27.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.28.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.28.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.28.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.29.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.29.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.29.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.30.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.30.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.30.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.31.self_attn.q_norm.weight": "pytorch_model.bin", "model.layers.31.self_attn.k_norm.weight": "pytorch_model.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.31.post_feedforward_layernorm.weight": "pytorch_model.bin", "model.norm.weight": "pytorch_model.bin", "lm_head.weight": "pytorch_model.bin"}, "metadata": {"total_size": 14597234688}}

tokenizer_config.json

@@ -0,0 +1,190 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "chat_template": "{%- if messages[0][\"role\"] == \"system\" %}\n    {%- set system_message = messages[0][\"content\"] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n\n{%- if system_message is defined %}\n    {{- \"<|system|>\\n\" + system_message.strip() + \"<|endoftext|>\" }}\n{%- endif %}\n\n{%- for message in loop_messages %}\n    {%- set content = message[\"content\"].strip() %}\n    {%- if message[\"role\"] == \"user\" %}\n        {{- \"<|user|>\\n\" + content + \"<|endoftext|>\" }}\n    {%- elif message[\"role\"] == \"assistant\" %}\n        {{- \"<|assistant|>\\n\" + content + \"<|endoftext|>\" }}\n    {%- elif message[\"role\"] == \"tool\" %}\n        {{- \"<|tool|>\\n\" + content + \"<|endoftext|>\" }}\n    {%- else %}\n        {{- raise_exception(\"Unknown message role: \" + message[\"role\"]) }}\n    {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- \"<|assistant|>\\n\" }}\n{%- endif %}"
+}