(Trained with Unsloth)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/gemma-2-9b",
+  "_name_or_path": "./gemma-2-9b",
   "architectures": [
     "Gemma2ForCausalLM"
   ],
@@ -22,28 +22,15 @@
   "num_hidden_layers": 42,
   "num_key_value_heads": 8,
   "pad_token_id": 0,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "sliding_window_size": 4096,
-  "torch_dtype": "float16",
-  "transformers_version": "4.47.0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "unsloth_version": "2024.12.4",
   "use_cache": true,
   "vocab_size": 256000
 }

generation_config.json

@@ -3,6 +3,7 @@
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
   "eos_token_id": 1,
+  "max_length": 8192,
   "pad_token_id": 0,
-  "transformers_version": "4.47.0"
+  "transformers_version": "4.46.3"
 }

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552e80f8b30b0338443fb888639401659c53fc75005333b62ba3e0d50d33ca8e
+size 4903351912

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a6002c445aedd3e4d4127e822c417766a1ff2e13e2f1e900ee3146d77ef785
+size 4947570872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc9039149071382cd309c1b29ad4209094f26abb373729ec111784f68e0bc64
+size 4962221464

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a26ef574f5a0229a63d316510fe24740545d0ff27dc0626f67991448beea673e
+size 3670322200

tokenizer_config.json

@@ -2002,9 +2002,9 @@
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
-  "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 8192,
   "pad_token": "<pad>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",