2bf244c5cef951f74413c29c57d3e3111658247b43c02f52e98bb9a59aede7b1

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.37.1",
+  "use_cache": false
+}

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e02d49f6f5f3c441de0cdb0d5d95c5a1e33daf35a4d23c7da16caf3a7e77b6e
+size 1723582192

smash_config.json

@@ -0,0 +1,31 @@
+{
+    "api_key": null,
+    "verify_url": "http://johnrachwan.pythonanywhere.com",
+    "smash_config": {
+        "pruners": "[]",
+        "pruning_ratio": 0.0,
+        "factorizers": "[]",
+        "quantizers": "['gptq']",
+        "n_quantization_bits": 8,
+        "output_deviation": 0.005,
+        "compilers": "[]",
+        "static_batch": true,
+        "static_shape": true,
+        "controlnet": "None",
+        "unet_dim": 4,
+        "device": "cuda",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelszka1vn5f",
+        "batch_size": 1,
+        "model_name": "mattshumer/Hermes-2-Pro-11B",
+        "max_batch_size": 1,
+        "save_dir": "/ceph/hdd/staff/charpent/.cache/modelsgvf954mf",
+        "qtype_weight": "torch.qint8",
+        "qtype_activation": "torch.quint8",
+        "qobserver": "<class 'torch.ao.quantization.observer.MinMaxObserver'>",
+        "qscheme": "torch.per_tensor_symmetric",
+        "qconfig": "x86",
+        "group_size": 128,
+        "damp_percent": 0.1,
+        "save_load_fn": "hf-gptq"
+    }
+}