Upload folder using huggingface_hub

config.json

@@ -39,9 +39,8 @@
         }
       },
       "format": "int-quantized",
-      "global_compression_ratio": 1.454005842904474,
+      "global_compression_ratio": 1.4583332397611055,
       "ignore": [
-        "model.layers.0.mlp.down_proj",
         "lm_head"
       ],
       "quant_method": "sparseml",
@@ -49,7 +48,7 @@
     },
     "sparsity_config": {
       "format": "dense",
-      "global_sparsity": 7.713156824200198,
+      "global_sparsity": 7.8259900429979625,
       "registry_requires_subclass": false,
       "sparsity_structure": "0:0"
     }
@@ -69,7 +68,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.39.0",
   "use_cache": true,
   "vocab_size": 32000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2904d1e37d759d31bbdec6c0b5c226d8ca1db1bc487dd69eb3f49c75ecdcb640
-size 1242839118
+oid sha256:e50b56978024a9aed7179f00aabd8689c07912534fa25058fd873c39f3e687bd
+size 1231304860

recipe.yaml

@@ -1,7 +1,7 @@
-quant_stage:
+test_stage:
   quant_modifiers:
     vLLMQuantizationModifier:
-      ignore: [lm_head, model.layers.0.mlp.down_proj]
+      ignore: [lm_head]
       config_groups:
         group_0:
           weights: {num_bits: 8, type: int, symmetric: true, strategy: tensor}