Upload folder using huggingface_hub (#2)

- 13ddc92e6403318238dc0ba08029d13e17ee4e590fa7f58d903223f502a5616b (cbdb9c2579962a00b2cb3758f826bf34831ab5d0)
- ddc110f21c55262db75d4b2b4cfa85273f147dd374fdccace31c91410d92602b (de6221a61514daf47e02aa67eca1bde0cabe75b3)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/tmp9sxcc8dm",
+  "_name_or_path": "/tmp/tmpls270se6",
   "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": 77.57367630004883,
-    "base_token_generation_latency_async": 77.46337354183197,
-    "base_token_generation_throughput_sync": 0.012890970851143876,
-    "base_token_generation_throughput_async": 0.012909326747304356,
-    "base_token_generation_CO2_emissions": 4.053060495387316e-05,
-    "base_token_generation_energy_consumption": 0.013849622710902646,
-    "base_inference_latency_sync": 75.81122741699218,
-    "base_inference_latency_async": 74.6903657913208,
-    "base_inference_throughput_sync": 0.013190658350637149,
-    "base_inference_throughput_async": 0.013388607612311391,
-    "base_inference_CO2_emissions": 4.126205610105293e-05,
-    "base_inference_energy_consumption": 0.00011312198092062262,
+    "base_token_generation_latency_sync": 56.28690795898437,
+    "base_token_generation_latency_async": 56.298492290079594,
+    "base_token_generation_throughput_sync": 0.017766120688823207,
+    "base_token_generation_throughput_async": 0.01776246502033254,
+    "base_token_generation_CO2_emissions": null,
+    "base_token_generation_energy_consumption": null,
+    "base_inference_latency_sync": 55.02095375061035,
+    "base_inference_latency_async": 53.02169322967529,
+    "base_inference_throughput_sync": 0.01817489396008347,
+    "base_inference_throughput_async": 0.018860204929108487,
+    "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": 49.07923049926758,
-    "smashed_token_generation_latency_async": 48.95127713680267,
-    "smashed_token_generation_throughput_sync": 0.020375217578338423,
-    "smashed_token_generation_throughput_async": 0.020428476201046396,
-    "smashed_token_generation_CO2_emissions": 3.559633476824905e-05,
-    "smashed_token_generation_energy_consumption": 0.00914676739443409,
-    "smashed_inference_latency_sync": 51.80733413696289,
-    "smashed_inference_latency_async": 49.51908588409424,
-    "smashed_inference_throughput_sync": 0.019302286378146828,
-    "smashed_inference_throughput_async": 0.020194233842293213,
-    "smashed_inference_CO2_emissions": 3.5450395516021004e-05,
-    "smashed_inference_energy_consumption": 9.43633613009706e-05
+    "smashed_token_generation_latency_sync": 42.081617736816405,
+    "smashed_token_generation_latency_async": 40.63092991709709,
+    "smashed_token_generation_throughput_sync": 0.023763344989589576,
+    "smashed_token_generation_throughput_async": 0.024611792101248708,
+    "smashed_token_generation_CO2_emissions": null,
+    "smashed_token_generation_energy_consumption": null,
+    "smashed_inference_latency_sync": 51.81982650756836,
+    "smashed_inference_latency_async": 40.34445285797119,
+    "smashed_inference_throughput_sync": 0.019297633114498145,
+    "smashed_inference_throughput_async": 0.024786555007212635,
+    "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/modelsw3xt7y12",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelskfqi18ew",
         "batch_size": 1,
         "model_name": "aaditya/Llama3-OpenBioLLM-8B",
         "task": "text_text_generation",