Upload folder using huggingface_hub

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "unsloth/gemma-2-9b",
   "architectures": [
     "Gemma2ForCausalLM"
   ],
@@ -16,6 +15,50 @@
   "hidden_size": 3584,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
   "max_position_embeddings": 8192,
   "model_type": "gemma2",
   "num_attention_heads": 16,
@@ -31,7 +74,14 @@
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
+    "llm_int8_skip_modules": [
+      "embed_tokens",
+      "embedding",
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
     "llm_int8_threshold": 6.0,
     "load_in_4bit": true,
     "load_in_8bit": false,
@@ -43,7 +93,8 @@
   "sliding_window": 4096,
   "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.53.2",
+  "unsloth_fixed": true,
   "unsloth_version": "2024.9",
   "use_cache": true,
   "vocab_size": 256000

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 1,
   "max_length": 8192,
   "pad_token_id": 0,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.53.2"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
-size 17525357
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

tokenizer_config.json

@@ -2002,7 +2002,8 @@
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
-  "model_max_length": 1000000000000000019884624838656,
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
   "pad_token": "<pad>",
   "padding_side": "left",
   "sp_model_kwargs": {},
@@ -2010,4 +2011,4 @@
   "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
-}
+}