Upload folder using huggingface_hub (#2)

- 3da9ead840dec3a4475c63dd639a286917bf89bc63a289e6bcec83c742cf74a4 (52ba8491a0c94be2e9e2cbdbf8de92ba153710e9)
- 13caa366ee9dac6a1f0966b3a160015e3d5d496e6832888a6d94de2f7c9b224c (4e86d60a1b43d9ac01ff65dbf63575f817ae42b4)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/tmp6tqwsht_",
+  "_name_or_path": "/tmp/tmpoau7b4ew",
   "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": 76.91910247802734,
-    "base_token_generation_latency_async": 76.82386375963688,
-    "base_token_generation_throughput_sync": 0.013000671715919452,
-    "base_token_generation_throughput_async": 0.013016788678173697,
-    "base_token_generation_CO2_emissions": 3.9930267542867864e-05,
-    "base_token_generation_energy_consumption": 0.013695786831045186,
-    "base_inference_latency_sync": 75.31489334106445,
-    "base_inference_latency_async": 74.6358871459961,
-    "base_inference_throughput_sync": 0.013277586352960592,
-    "base_inference_throughput_async": 0.013398380299866857,
-    "base_inference_CO2_emissions": 4.072261623993283e-05,
-    "base_inference_energy_consumption": 0.00011265253741674144,
+    "base_token_generation_latency_sync": 57.667279434204104,
+    "base_token_generation_latency_async": 58.03066436201334,
+    "base_token_generation_throughput_sync": 0.017340856198027464,
+    "base_token_generation_throughput_async": 0.017232268680601154,
+    "base_token_generation_CO2_emissions": null,
+    "base_token_generation_energy_consumption": null,
+    "base_inference_latency_sync": 56.35584030151367,
+    "base_inference_latency_async": 55.629873275756836,
+    "base_inference_throughput_sync": 0.017744389838742956,
+    "base_inference_throughput_async": 0.017975953226479737,
+    "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": 49.13712501525879,
-    "smashed_token_generation_latency_async": 48.9015968516469,
-    "smashed_token_generation_throughput_sync": 0.02035121101793125,
-    "smashed_token_generation_throughput_async": 0.02044922997164503,
-    "smashed_token_generation_CO2_emissions": 3.524599859739772e-05,
-    "smashed_token_generation_energy_consumption": 0.009180102018160505,
-    "smashed_inference_latency_sync": 52.06343727111816,
-    "smashed_inference_latency_async": 49.8340368270874,
-    "smashed_inference_throughput_sync": 0.019207337287250974,
-    "smashed_inference_throughput_async": 0.0200666063531993,
-    "smashed_inference_CO2_emissions": 3.379301910600281e-05,
-    "smashed_inference_energy_consumption": 9.774841757057516e-05
+    "smashed_token_generation_latency_sync": 41.73652305603027,
+    "smashed_token_generation_latency_async": 41.733165830373764,
+    "smashed_token_generation_throughput_sync": 0.02395983006676249,
+    "smashed_token_generation_throughput_async": 0.023961757515941703,
+    "smashed_token_generation_CO2_emissions": null,
+    "smashed_token_generation_energy_consumption": null,
+    "smashed_inference_latency_sync": 51.78419189453125,
+    "smashed_inference_latency_async": 42.34201908111572,
+    "smashed_inference_throughput_sync": 0.01931091252783664,
+    "smashed_inference_throughput_async": 0.023617201581348155,
+    "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/models8o3cnft5",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsbok3a_hw",
         "batch_size": 1,
         "model_name": "McGill-NLP/Llama-3-8B-Web",
         "task": "text_text_generation",