Adding `safetensors` variant of this model

config.json

@@ -1,15 +1,16 @@
 {
+  "_name_or_path": "notzero/qwen1_5b",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
   "max_position_embeddings": 32768,
-  "max_window_layers": 21,
+  "max_window_layers": 28,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
@@ -21,10 +22,11 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "float16",
-  "transformers_version": "4.51.0",
+  "transformers_version": "4.47.1",
   "unsloth_fixed": true,
-  "unsloth_version": "2025.3.19",
+  "unsloth_version": "2025.1.8",
   "use_cache": true,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,15 +1,8 @@
 {
   "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
+  "eos_token_id": 151643,
   "max_length": 32768,
+  "max_new_tokens": 2048,
   "pad_token_id": 151654,
-  "repetition_penalty": 1.1,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
-  "transformers_version": "4.51.0"
+  "transformers_version": "4.47.1"
 }

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0dd43060cdaaf732b9ee526feffb3d9d71d74387f098c6f6351f111fe29512d9
-size 3087542290

special_tokens_map.json

@@ -21,5 +21,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|vision_pad|>"
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

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

tokenizer_config.json

@@ -200,9 +200,8 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
-  "pad_token": "<|vision_pad|>",
-  "padding_side": "left",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null