Upload folder using huggingface_hub

config.json

@@ -3,22 +3,17 @@
     "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": {
@@ -30,18 +25,13 @@
           "Linear"
         ],
         "weights": {
-          "actorder": null,
-          "block_structure": null,
           "dynamic": false,
           "group_size": null,
           "num_bits": 4,
           "observer": "memoryless_minmax",
-          "observer_kwargs": {},
-          "scale_dtype": null,
           "strategy": "channel",
           "symmetric": true,
-          "type": "int",
-          "zp_dtype": null
+          "type": "int"
         }
       }
     },
@@ -51,32 +41,26 @@
       "lm_head"
     ],
     "kv_cache_scheme": {
-      "actorder": null,
-      "block_structure": null,
       "dynamic": false,
       "group_size": null,
       "num_bits": 8,
-      "observer": "memoryless_minmax",
-      "observer_kwargs": {},
-      "scale_dtype": null,
       "strategy": "tensor",
       "symmetric": true,
-      "type": "float",
-      "zp_dtype": null
+      "type": "float"
     },
+    "moe_sparsity_config": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.17.1"
+    "version": "0.20.2a20261028"
   },
   "rms_norm_eps": 1e-05,
-  "rope_parameters": {
-    "rope_theta": 10000.0,
-    "rope_type": "default"
-  },
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "transformers_version": "5.10.1",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
   "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": "5.10.1"
+  "transformers_version": "5.21.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2bf1ff384f476bd3b75d061e2282ecf3dc8ed62167bfb527c30d636dbeaf392
+oid sha256:9f06b8534817843c404a0b35bf2acfb944d3278365b4282f855ce44baf6efc62
 size 747622872

recipe.yaml

@@ -4,38 +4,17 @@ quant_stage:
       config_groups:
         group_0:
           targets: [Linear]
-          weights:
-            num_bits: 4
-            type: int
-            symmetric: true
-            group_size: null
-            strategy: channel
-            block_structure: null
-            dynamic: false
-            actorder: null
-            scale_dtype: null
-            zp_dtype: null
-            observer: memoryless_minmax
-            observer_kwargs: {}
+          weights: {num_bits: 4, type: int, symmetric: true, group_size: null, strategy: channel,
+            dynamic: false, observer: memoryless_minmax}
           input_activations: null
           output_activations: null
           format: null
       targets: [Linear]
       ignore: [lm_head]
-      kv_cache_scheme:
-        num_bits: 8
-        type: float
-        symmetric: true
-        group_size: null
-        strategy: tensor
-        block_structure: null
-        dynamic: false
-        actorder: null
-        scale_dtype: null
-        zp_dtype: null
-        observer: memoryless_minmax
-        observer_kwargs: {}
+      kv_cache_scheme: {num_bits: 8, type: float, symmetric: true, group_size: null, strategy: tensor,
+        dynamic: false}
       bypass_divisibility_checks: false
+      requires_calibration_data: true
       block_size: 128
       dampening_frac: 0.01
-      offload_hessians: false
+      batched_quantization: auto