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": null,
           "num_bits": 4,
           "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
           "strategy": "channel",
           "symmetric": true,
-          "type": "int"
+          "type": "int",
+          "zp_dtype": null
         }
       }
     },
@@ -41,26 +51,32 @@
       "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"
+      "type": "float",
+      "zp_dtype": null
     },
-    "moe_sparsity_config": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.20.2.dev3+g6c0f906d"
+    "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 sha256:0173995cdff85432f48e729cbed61fd57af9b08639b9400677aed45c3b5bc1b7
+oid sha256:b2bf1ff384f476bd3b75d061e2282ecf3dc8ed62167bfb527c30d636dbeaf392
 size 747622872

recipe.yaml

@@ -4,17 +4,38 @@ quant_stage:
       config_groups:
         group_0:
           targets: [Linear]
-          weights: {num_bits: 4, type: int, symmetric: true, group_size: null, strategy: channel,
-            dynamic: false, observer: memoryless_minmax}
+          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: {}
           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,
-        dynamic: false}
+      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: {}
       bypass_divisibility_checks: false
-      requires_calibration_data: true
       block_size: 128
       dampening_frac: 0.01
-      batched_quantization: auto
+      offload_hessians: false