Add files using upload-large-folder tool

config.json

@@ -20,6 +20,34 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "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.0.self_attn",
+      "model.layers.0.self_attn.q_proj",
+      "model.layers.0.self_attn.k_proj",
+      "model.layers.0.self_attn.v_proj",
+      "model.layers.0.mlp.gate_proj",
+      "model.layers.0.mlp.up_proj",
+      "model.layers.3.mlp.gate_proj",
+      "model.layers.55.self_attn.o_proj"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,
@@ -31,7 +59,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.1",
+  "transformers_version": "4.49.0.dev0",
   "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 128256

generation_config.json

@@ -7,5 +7,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.48.1"
+  "transformers_version": "4.49.0.dev0"
 }