aerdna
/

quantize_v0.2

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

aerdna commited on Jun 5, 2024

Commit

7815a41

·

verified ·

1 Parent(s): 09612cd

Upload GemmaForCausalLM

Files changed (2) hide show

config.json +6 -6
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -20,18 +20,18 @@
   "num_key_value_heads": 1,
   "pad_token_id": 0,
   "quantization_config": {
-    "_load_in_4bit": false,
-    "_load_in_8bit": true,
-    "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
-    "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": false,
-    "load_in_8bit": true,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,

   "num_key_value_heads": 1,
   "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": "fp4",
+    "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"
   },
   "rms_norm_eps": 1e-06,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1c65f8ece2d3a46dd098ae7bcdfc3a631cecc220a7a7e61bdcb61dcbf2c816
-size 3033420294

 version https://git-lfs.github.com/spec/v1
+oid sha256:4040bc6b243c5f03879433264e624388b290ce64e12ea3723939665a2c051473
+size 2071334054