Automatic quantization of Sambhavnoobcoder/gpt2-test-quantization

README.md

@@ -78,4 +78,4 @@ This model was automatically quantized by the [Auto-Quantization Service](https:
 
 ---
 
-*Generated on 2026-01-10 21:05:21 by [Auto-Quantization MVP](https://huggingface.co/spaces/Sambhavnoobcoder/quantization-mvp)*
+*Generated on 2026-01-11 01:42:45 by [Auto-Quantization MVP](https://huggingface.co/spaces/Sambhavnoobcoder/quantization-mvp)*

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "Sambhavnoobcoder/gpt2-test-quantization",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "dtype": "float32",
+  "dtype": "float16",
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
@@ -33,8 +32,7 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.57.3",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.57.3"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac3cf6080417201754ff956cda02211d24ea0095319554adf726a897a30fe55
-size 287625002
+oid sha256:e46adcd3334bf8e8c9e026f65f7ce989c51cdbdd189bdef2732361f2b9550d83
+size 287625347