Upload folder using huggingface_hub

config.json

@@ -29,11 +29,9 @@
           "num_bits": 4,
           "observer": "static_minmax",
           "observer_kwargs": {},
-          "scale_dtype": "torch.float8_e4m3fn",
           "strategy": "tensor_group",
           "symmetric": true,
-          "type": "float",
-          "zp_dtype": null
+          "type": "float"
         },
         "output_activations": null,
         "targets": [
@@ -47,11 +45,9 @@
           "num_bits": 4,
           "observer": "static_minmax",
           "observer_kwargs": {},
-          "scale_dtype": "torch.float8_e4m3fn",
           "strategy": "tensor_group",
           "symmetric": true,
-          "type": "float",
-          "zp_dtype": null
+          "type": "float"
         }
       }
     },
@@ -67,11 +63,11 @@
     "transform_config": {},
     "version": "0.13.0"
   },
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 0.00001,
   "rope_theta": 1000000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "transformers_version": "4.57.3",
   "use_cache": false,
   "vocab_size": 131072
-}
+}

config.json.orig

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 54,
+  "num_key_value_heads": 8,
+  "pad_token_id": 11,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "nvfp4-pack-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": "local",
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "nvfp4-pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.13.0"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 131072
+}