Add files using upload-large-folder tool

config.json

@@ -17,12 +17,34 @@
   "num_hidden_layers": 40,
   "num_key_value_heads": 8,
   "pad_token_id": 11,
+  "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": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection",
+      "model.layers.2.mlp",
+      "model.layers.39.mlp"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_theta": 100000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.2",
+  "transformers_version": "4.49.0.dev0",
   "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 131072

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "max_length": 32768,
   "pad_token_id": 11,
-  "transformers_version": "4.48.2"
+  "transformers_version": "4.49.0.dev0"
 }