Add files using upload-large-folder tool

.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

added_tokens.json

@@ -1,7 +1,6 @@
 {
   "</tool_call>": 151658,
   "<tool_call>": 151657,
-  "<|PAD_TOKEN|>": 151665,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

config.json

@@ -4,7 +4,6 @@
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 3584,
@@ -16,13 +15,14 @@
   "num_attention_heads": 28,
   "num_hidden_layers": 28,
   "num_key_value_heads": 4,
-  "pad_token_id": 151665,
+  "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.49.0.dev0",
   "unsloth_fixed": true,
   "use_cache": true,
   "use_sliding_window": false,

generation_config.json

@@ -6,10 +6,10 @@
     151643
   ],
   "max_length": 32768,
-  "pad_token_id": 151665,
+  "pad_token_id": 151654,
   "repetition_penalty": 1.05,
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.49.0.dev0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6315c6a8d58c954d1b330fa791d5838ac6d29091f2156fe11693943551b4a235
-size 3945426872
+oid sha256:9ff3b270cb6b8ce8a059a43678cebaefb7aa2a3b587aadc5a4e2f6c1e4d13a28
+size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a625d7395b65b97d837f4ae3761d297381ce2cb1c5672f93966105379456f0f
-size 3864726352
+oid sha256:854698ca4d7581b9fd40f5da9176b010422194ec26cab3abd907ff21e477d1ca
+size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b147c46b0dc0695df95b8ad26c9996d5a125995c382d4aa85849d76a73f6fe81
-size 3864726408
+oid sha256:6295baeb13806b95509f86175dd3a298bf39630071a4dc2b2d31441c9230b011
+size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f689f5660de2ef3a64faf4888dd8570be75cbff1e7dda403ccff933e6bdce8
-size 3556392240
+oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
+size 1089994880

model.safetensors.index.json

@@ -77,11 +77,11 @@
     "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
@@ -89,54 +89,54 @@
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -185,11 +185,11 @@
     "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
@@ -197,66 +197,66 @@
     "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -293,11 +293,11 @@
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
@@ -305,30 +305,30 @@
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -341,6 +341,6 @@
     "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.norm.weight": "model-00004-of-00004.safetensors"
+    "model.norm.weight": "model-00003-of-00004.safetensors"
   }
 }

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|PAD_TOKEN|>",
+    "content": "<|vision_pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -177,14 +177,6 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "151665": {
-      "content": "<|PAD_TOKEN|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
@@ -207,8 +199,9 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 131072,
-  "pad_token": "<|PAD_TOKEN|>",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
   "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",