Upload folder using huggingface_hub

config.json

@@ -56,6 +56,21 @@
   "image_token_id": 258880,
   "initializer_range": 0.02,
   "model_type": "gemma4",
+  "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": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "text_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.6.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69351ef8f41c3455cb110d54431ab23e63875754a0b7750bbf36f2fbb119b4d6
-size 6991185214
+oid sha256:ff94698ef32d3e5b60815e275338bb3b0e3a682eeebbf6ef5d09a750a7ab785e
+size 6742125105

quantization_info.json

@@ -0,0 +1,5 @@
+{
+  "quantization": "bitsandbytes-nf4",
+  "base_model": "/gpfs/home2/overven/Anthropic-x-Whale-Hackathon-backend/models/gemma-4-E2B-it",
+  "dtype": "bfloat16"
+}