Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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 +1,27 @@
+---
+license: mit
+datasets:
+- normster/RealGuardrails
+base_model:
+- Qwen/Qwen2.5-7B
+---
+
+# 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 `systemmix` 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 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f006a333d51c99ecc662b657ecfdb677617c0d3f2b26815c0d186a7b83cc3851
+size 15231345338

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.q_proj.bias": "pytorch_model.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.0.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.0.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.0.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.1.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.1.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.1.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.1.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.2.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.2.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.2.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.2.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.3.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.3.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.3.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.3.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.4.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.4.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.4.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.4.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.5.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.5.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.5.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.5.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.6.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.6.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.6.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.6.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.7.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.7.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.7.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.7.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.8.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.8.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.8.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.8.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.9.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.9.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.9.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.9.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.10.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.10.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.10.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.10.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.11.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.11.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.11.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.11.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.12.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.12.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.12.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.12.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.13.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.13.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.13.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.13.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.14.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.14.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.14.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.14.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.15.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.15.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.15.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.15.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.16.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.16.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.16.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.16.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.17.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.17.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.17.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.17.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.18.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.18.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.18.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.18.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.19.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.19.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.19.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.19.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.20.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.20.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.20.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.20.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.21.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.21.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.21.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.21.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.22.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.22.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.22.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.22.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.23.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.23.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.23.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.23.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.24.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.24.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.24.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.24.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.25.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.25.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.25.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.25.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.26.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.26.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.26.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.26.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.27.self_attn.q_proj.bias": "pytorch_model.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model.bin", "model.layers.27.self_attn.k_proj.bias": "pytorch_model.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model.bin", "model.layers.27.self_attn.v_proj.bias": "pytorch_model.bin", "model.layers.27.self_attn.o_proj.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.input_layernorm.weight": "pytorch_model.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model.bin", "model.norm.weight": "pytorch_model.bin", "lm_head.weight": "pytorch_model.bin"}, "metadata": {"total_size": 15231233024}}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "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{%- if system_message is defined %}\n    {{- \"<|im_start|>system<|im_start|>\\n\\n\" + system_message.strip() + \"<|im_end|>\" }}\n{%- endif %}\n\n{%- for message in loop_messages %}\n    {%- set content = message[\"content\"].strip() %}\n    {%- if message[\"role\"] == \"user\" %}\n        {{- \"<|im_start|>user<|im_start|>\\n\\n\" + content + \"<|im_end|>\" }}\n    {%- elif message[\"role\"] == \"assistant\" %}\n        {{- \"<|im_start|>assistant<|im_start|>\\n\\n\" + content + \"<|im_end|>\" }}\n    {%- elif message[\"role\"] == \"tool\" %}\n        {{- \"<|im_start|>ipython<|im_start|>\\n\\n\" + content + \"<|im_end|>\" }}\n    {%- else %}\n        {{- raise_exception(\"Unknown message role: \" + message[\"role\"]) }}\n    {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- \"<|im_start|>assistant<|im_start|>\\n\\n\" }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}