Upload folder using huggingface_hub

config.json

@@ -9,6 +9,7 @@
     "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
   },
   "bos_token_id": 1,
+  "dtype": "bfloat16",
   "embd_pdrop": 0.0,
   "eos_token_id": 32000,
   "hidden_act": "silu",
@@ -27,154 +28,26 @@
     "config_groups": {},
     "format": "dense",
     "global_compression_ratio": null,
-    "ignore": [
-      "model.layers.0.self_attn.o_proj",
-      "model.layers.0.self_attn.qkv_proj",
-      "model.layers.0.mlp.gate_up_proj",
-      "model.layers.0.mlp.down_proj",
-      "model.layers.1.self_attn.o_proj",
-      "model.layers.1.self_attn.qkv_proj",
-      "model.layers.1.mlp.gate_up_proj",
-      "model.layers.1.mlp.down_proj",
-      "model.layers.2.self_attn.o_proj",
-      "model.layers.2.self_attn.qkv_proj",
-      "model.layers.2.mlp.gate_up_proj",
-      "model.layers.2.mlp.down_proj",
-      "model.layers.3.self_attn.o_proj",
-      "model.layers.3.self_attn.qkv_proj",
-      "model.layers.3.mlp.gate_up_proj",
-      "model.layers.3.mlp.down_proj",
-      "model.layers.4.self_attn.o_proj",
-      "model.layers.4.self_attn.qkv_proj",
-      "model.layers.4.mlp.gate_up_proj",
-      "model.layers.4.mlp.down_proj",
-      "model.layers.5.self_attn.o_proj",
-      "model.layers.5.self_attn.qkv_proj",
-      "model.layers.5.mlp.gate_up_proj",
-      "model.layers.5.mlp.down_proj",
-      "model.layers.6.self_attn.o_proj",
-      "model.layers.6.self_attn.qkv_proj",
-      "model.layers.6.mlp.gate_up_proj",
-      "model.layers.6.mlp.down_proj",
-      "model.layers.7.self_attn.o_proj",
-      "model.layers.7.self_attn.qkv_proj",
-      "model.layers.7.mlp.gate_up_proj",
-      "model.layers.7.mlp.down_proj",
-      "model.layers.8.self_attn.o_proj",
-      "model.layers.8.self_attn.qkv_proj",
-      "model.layers.8.mlp.gate_up_proj",
-      "model.layers.8.mlp.down_proj",
-      "model.layers.9.self_attn.o_proj",
-      "model.layers.9.self_attn.qkv_proj",
-      "model.layers.9.mlp.gate_up_proj",
-      "model.layers.9.mlp.down_proj",
-      "model.layers.10.self_attn.o_proj",
-      "model.layers.10.self_attn.qkv_proj",
-      "model.layers.10.mlp.gate_up_proj",
-      "model.layers.10.mlp.down_proj",
-      "model.layers.11.self_attn.o_proj",
-      "model.layers.11.self_attn.qkv_proj",
-      "model.layers.11.mlp.gate_up_proj",
-      "model.layers.11.mlp.down_proj",
-      "model.layers.12.self_attn.o_proj",
-      "model.layers.12.self_attn.qkv_proj",
-      "model.layers.12.mlp.gate_up_proj",
-      "model.layers.12.mlp.down_proj",
-      "model.layers.13.self_attn.o_proj",
-      "model.layers.13.self_attn.qkv_proj",
-      "model.layers.13.mlp.gate_up_proj",
-      "model.layers.13.mlp.down_proj",
-      "model.layers.14.self_attn.o_proj",
-      "model.layers.14.self_attn.qkv_proj",
-      "model.layers.14.mlp.gate_up_proj",
-      "model.layers.14.mlp.down_proj",
-      "model.layers.15.self_attn.o_proj",
-      "model.layers.15.self_attn.qkv_proj",
-      "model.layers.15.mlp.gate_up_proj",
-      "model.layers.15.mlp.down_proj",
-      "model.layers.16.self_attn.o_proj",
-      "model.layers.16.self_attn.qkv_proj",
-      "model.layers.16.mlp.gate_up_proj",
-      "model.layers.16.mlp.down_proj",
-      "model.layers.17.self_attn.o_proj",
-      "model.layers.17.self_attn.qkv_proj",
-      "model.layers.17.mlp.gate_up_proj",
-      "model.layers.17.mlp.down_proj",
-      "model.layers.18.self_attn.o_proj",
-      "model.layers.18.self_attn.qkv_proj",
-      "model.layers.18.mlp.gate_up_proj",
-      "model.layers.18.mlp.down_proj",
-      "model.layers.19.self_attn.o_proj",
-      "model.layers.19.self_attn.qkv_proj",
-      "model.layers.19.mlp.gate_up_proj",
-      "model.layers.19.mlp.down_proj",
-      "model.layers.20.self_attn.o_proj",
-      "model.layers.20.self_attn.qkv_proj",
-      "model.layers.20.mlp.gate_up_proj",
-      "model.layers.20.mlp.down_proj",
-      "model.layers.21.self_attn.o_proj",
-      "model.layers.21.self_attn.qkv_proj",
-      "model.layers.21.mlp.gate_up_proj",
-      "model.layers.21.mlp.down_proj",
-      "model.layers.22.self_attn.o_proj",
-      "model.layers.22.self_attn.qkv_proj",
-      "model.layers.22.mlp.gate_up_proj",
-      "model.layers.22.mlp.down_proj",
-      "model.layers.23.self_attn.o_proj",
-      "model.layers.23.self_attn.qkv_proj",
-      "model.layers.23.mlp.gate_up_proj",
-      "model.layers.23.mlp.down_proj",
-      "model.layers.24.self_attn.o_proj",
-      "model.layers.24.self_attn.qkv_proj",
-      "model.layers.24.mlp.gate_up_proj",
-      "model.layers.24.mlp.down_proj",
-      "model.layers.25.self_attn.o_proj",
-      "model.layers.25.self_attn.qkv_proj",
-      "model.layers.25.mlp.gate_up_proj",
-      "model.layers.25.mlp.down_proj",
-      "model.layers.26.self_attn.o_proj",
-      "model.layers.26.self_attn.qkv_proj",
-      "model.layers.26.mlp.gate_up_proj",
-      "model.layers.26.mlp.down_proj",
-      "model.layers.27.self_attn.o_proj",
-      "model.layers.27.self_attn.qkv_proj",
-      "model.layers.27.mlp.gate_up_proj",
-      "model.layers.27.mlp.down_proj",
-      "model.layers.28.self_attn.o_proj",
-      "model.layers.28.self_attn.qkv_proj",
-      "model.layers.28.mlp.gate_up_proj",
-      "model.layers.28.mlp.down_proj",
-      "model.layers.29.self_attn.o_proj",
-      "model.layers.29.self_attn.qkv_proj",
-      "model.layers.29.mlp.gate_up_proj",
-      "model.layers.29.mlp.down_proj",
-      "model.layers.30.self_attn.o_proj",
-      "model.layers.30.self_attn.qkv_proj",
-      "model.layers.30.mlp.gate_up_proj",
-      "model.layers.30.mlp.down_proj",
-      "model.layers.31.self_attn.o_proj",
-      "model.layers.31.self_attn.qkv_proj",
-      "model.layers.31.mlp.gate_up_proj",
-      "model.layers.31.mlp.down_proj",
-      "lm_head"
-    ],
+    "ignore": [],
     "kv_cache_scheme": {
       "actorder": null,
       "block_structure": null,
       "dynamic": false,
       "group_size": null,
       "num_bits": 8,
-      "observer": "minmax",
+      "observer": "memoryless_minmax",
       "observer_kwargs": {},
+      "scale_dtype": null,
       "strategy": "tensor",
       "symmetric": true,
-      "type": "float"
+      "type": "float",
+      "zp_dtype": null
     },
     "quant_method": "compressed-tensors",
     "quantization_status": "frozen",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.11.0"
+    "version": "0.14.0.1"
   },
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
@@ -182,8 +55,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 2047,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.2",
+  "transformers_version": "4.57.6",
   "use_cache": true,
   "vocab_size": 32064
 }

generation_config.json

@@ -7,5 +7,5 @@
     32007
   ],
   "pad_token_id": 32000,
-  "transformers_version": "4.55.2"
+  "transformers_version": "4.57.6"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a019bc9c9f03ee35b821f024704cdde9e9034ab5061e254e6092c8ee02d6b4
+oid sha256:c4e7401a2294820680d12d92693eca67123317ebe631720eb831a03dbd716175
 size 4972493960

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6fc59e16719e1415bfd49f557a26b6ecaf2ad1a1c05b23525b2b57a3dcc6bcd
+oid sha256:495ff095f0e52fbadffc667850f95b1a232a8d5983cb5dbd7a4e02d68b3d12e6
 size 2669694664

recipe.yaml

@@ -12,5 +12,8 @@ quant_stage:
         block_structure: null
         dynamic: false
         actorder: null
-        observer: minmax
+        scale_dtype: null
+        zp_dtype: null
+        observer: memoryless_minmax
         observer_kwargs: {}
+      bypass_divisibility_checks: false