Upload /Mistral-7B-v0.1-AWQ/AWQ_batch_size_1_sq_len_256_new_tokens_256/experiment_config.json with huggingface_hub

Mistral-7B-v0.1-AWQ/AWQ_batch_size_1_sq_len_256_new_tokens_256/experiment_config.json

@@ -3,7 +3,7 @@
         "name": "pytorch",
         "version": "2.2.1+cu118",
         "_target_": "optimum_benchmark.backends.pytorch.backend.PyTorchBackend",
-        "model": "microsoft/phi-2",
+        "model": "kreas/Mistral-7B-v0.1-AWQ",
         "task": "text-generation",
         "library": "transformers",
         "device": "cuda",
@@ -29,13 +29,8 @@
         "cache_implementation": null,
         "torch_compile": false,
         "torch_compile_config": {},
-        "quantization_scheme": "bnb",
-        "quantization_config": {
-            "llm_int8_threshold": 0.0,
-            "load_in_4bit": true,
-            "bnb_4bit_compute_dtype": "float16",
-            "bnb_4bit_quant_type": "nf4"
-        },
+        "quantization_scheme": "awq",
+        "quantization_config": {},
         "deepspeed_inference": false,
         "deepspeed_inference_config": {},
         "peft_type": null,
@@ -68,7 +63,7 @@
         },
         "call_kwargs": {}
     },
-    "experiment_name": "phi-2-nf4",
+    "experiment_name": "Mistral-7B-v0.1-AWQ-AWQ",
     "task": null,
     "model": null,
     "device": null,