Upload folder using huggingface_hub (#2)

- 3c04afac993e32df3f34cb20ffea540ea2a3f8de432ce27a11448ee87a0c5692 (4b87a0a936829d7d76fd9241c0b2377c37d404f4)
- dffc055384d798c24da3e3cff13366bbcd6e7a463fb21c4059642d55da04c548 (337a3cd0dbb0f0585cbccd86bcbc3bd2d5ce79e0)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/tmp8w9npacc",
+  "_name_or_path": "/tmp/tmptqw5iwk9",
   "architectures": [
     "LlamaForCausalLM"
   ],

results.json

@@ -1,30 +1,30 @@
 {
     "base_current_gpu_type": "NVIDIA A100-PCIE-40GB",
     "base_current_gpu_total_memory": 40339.3125,
-    "base_token_generation_latency_sync": 85.07037048339843,
-    "base_token_generation_latency_async": 84.67234391719103,
-    "base_token_generation_throughput_sync": 0.011754974079901897,
-    "base_token_generation_throughput_async": 0.011810231697116985,
-    "base_token_generation_CO2_emissions": 4.3299983519505644e-05,
-    "base_token_generation_energy_consumption": 0.015020053132557814,
-    "base_inference_latency_sync": 82.79797744750977,
-    "base_inference_latency_async": 80.90059757232666,
-    "base_inference_throughput_sync": 0.012077589704820453,
-    "base_inference_throughput_async": 0.012360848127308097,
-    "base_inference_CO2_emissions": 4.3285609592242674e-05,
-    "base_inference_energy_consumption": 0.00011979562850886179,
+    "base_token_generation_latency_sync": 54.95326919555664,
+    "base_token_generation_latency_async": 54.871915467083454,
+    "base_token_generation_throughput_sync": 0.018197279518374077,
+    "base_token_generation_throughput_async": 0.01822425901278915,
+    "base_token_generation_CO2_emissions": null,
+    "base_token_generation_energy_consumption": null,
+    "base_inference_latency_sync": 54.171545791625974,
+    "base_inference_latency_async": 52.81825065612793,
+    "base_inference_throughput_sync": 0.018459875666951772,
+    "base_inference_throughput_async": 0.01893284967937462,
+    "base_inference_CO2_emissions": null,
+    "base_inference_energy_consumption": null,
     "smashed_current_gpu_type": "NVIDIA A100-PCIE-40GB",
     "smashed_current_gpu_total_memory": 40339.3125,
-    "smashed_token_generation_latency_sync": 52.870144271850585,
-    "smashed_token_generation_latency_async": 52.96685267239809,
-    "smashed_token_generation_throughput_sync": 0.018914266525510988,
-    "smashed_token_generation_throughput_async": 0.01887973231456731,
-    "smashed_token_generation_CO2_emissions": 3.885417104719009e-05,
-    "smashed_token_generation_energy_consumption": 0.009796835913615097,
-    "smashed_inference_latency_sync": 58.50542030334473,
-    "smashed_inference_latency_async": 54.499125480651855,
-    "smashed_inference_throughput_sync": 0.0170924333987364,
-    "smashed_inference_throughput_async": 0.018348918284111136,
-    "smashed_inference_CO2_emissions": 3.4581847663784826e-05,
-    "smashed_inference_energy_consumption": 0.00010613908209762741
+    "smashed_token_generation_latency_sync": 41.98579063415527,
+    "smashed_token_generation_latency_async": 42.9755836725235,
+    "smashed_token_generation_throughput_sync": 0.023817581731722923,
+    "smashed_token_generation_throughput_async": 0.023269026608691564,
+    "smashed_token_generation_CO2_emissions": null,
+    "smashed_token_generation_energy_consumption": null,
+    "smashed_inference_latency_sync": 52.003635787963866,
+    "smashed_inference_latency_async": 42.94884204864502,
+    "smashed_inference_throughput_sync": 0.01922942472863499,
+    "smashed_inference_throughput_async": 0.023283514812049485,
+    "smashed_inference_CO2_emissions": null,
+    "smashed_inference_energy_consumption": null
 }

smash_config.json

@@ -2,19 +2,19 @@
     "api_key": null,
     "verify_url": "http://johnrachwan.pythonanywhere.com",
     "smash_config": {
-        "pruners": "[]",
+        "pruners": "None",
         "pruning_ratio": 0.0,
-        "factorizers": "[]",
+        "factorizers": "None",
         "quantizers": "['awq']",
         "weight_quantization_bits": 4,
-        "output_deviation": 0.01,
-        "compilers": "[]",
+        "output_deviation": 0.005,
+        "compilers": "None",
         "static_batch": true,
         "static_shape": true,
         "controlnet": "None",
         "unet_dim": 4,
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelspgasbvra",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models8pfyzfi3",
         "batch_size": 1,
         "model_name": "cognitivecomputations/dolphin-2.9-llama3-8b",
         "task": "text_text_generation",