Upload folder using huggingface_hub

config.json

@@ -3,17 +3,22 @@
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
+  "dtype": "bfloat16",
   "eos_token_id": 2,
+  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
+  "pad_token_id": null,
   "pretraining_tp": 1,
   "quantization_config": {
     "config_groups": {
@@ -25,13 +30,18 @@
           "Linear"
         ],
         "weights": {
+          "actorder": null,
+          "block_structure": null,
           "dynamic": false,
           "group_size": 128,
           "num_bits": 8,
           "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
           "strategy": "group",
           "symmetric": true,
-          "type": "int"
+          "type": "int",
+          "zp_dtype": null
         }
       }
     },
@@ -41,19 +51,19 @@
       "lm_head"
     ],
     "kv_cache_scheme": null,
-    "moe_sparsity_config": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.20.2a20261028"
+    "version": "0.17.1"
   },
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.0",
+  "transformers_version": "5.10.1",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "5.21.0"
+  "transformers_version": "5.10.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2b54c279240f1255e86ac91861b332b7b519dbc146c2378ddb413186e508ac
+oid sha256:8c8a700fc9f4d76ee8930434c3f7461ef7cd19c75bf888d27d2f91082c2a4748
 size 1246411368

recipe.yaml

@@ -5,7 +5,6 @@ default_stage:
       ignore: [lm_head, 're:.*mlp.gate[.].*']
       scheme: W8A16
       bypass_divisibility_checks: false
-      requires_calibration_data: true
       block_size: 128
       dampening_frac: 0.01
-      batched_quantization: auto
+      offload_hessians: false