(Trained with Unsloth)

config.json

@@ -7,7 +7,7 @@
   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
-  "dtype": "float16",
+  "torch_dtype": "float16",
   "eos_token_id": 106,
   "final_logit_softcapping": null,
   "head_dim": 256,
@@ -43,33 +43,14 @@
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "full_attention": {
-      "rope_theta": 1000000.0,
-      "rope_type": "default"
-    },
-    "sliding_attention": {
-      "rope_theta": 10000.0,
-      "rope_type": "default"
-    }
-  },
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
   "sliding_window": 512,
-  "transformers_version": "5.0.0.dev0",
+  "transformers_version": "4.57.3",
   "unsloth_fixed": true,
   "unsloth_version": "2026.1.2",
   "use_bidirectional_attention": false,
   "use_cache": true,
-  "vocab_size": 262144,
-  "transformers.js_config": {
-    "use_external_data_format": {
-      "model.onnx": 1,
-      "model_fp16.onnx": 1,
-      "model_q4.onnx": 1,
-      "model_q4f16.onnx": 1
-    },
-    "kv_cache_dtype": {
-      "q4f16": "float16",
-      "fp16": "float16"
-    }
-  }
-}
+  "vocab_size": 262144
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa00479b9f9d41a876e5cd1b369eea7af974fa0bdcc994c987972056d8ed5c2
-size 20323384
+oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
+size 33384899