update the AMP model with better accuracy numbers and lower effective bitwidth (5.6) (#2)

- update Quark quantized Auto Mixed Precision (AMP) model with better accuracies (5e0e79c04731261ade9075c8554d0f06ec5ea937)

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.53.2"
+  "transformers_version": "4.52.4"
 }

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf7450fd914671687f7ae4966def7c8dc571d4d123e423cdc88655bd770f2af
+size 4986676292

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629c551eeb823cb60d857ab05e58f3e7aa1ab532c75c49c1f88b4539ee6faaa0
+size 4977170176

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a02bdf83bb814852b65751107d01679f974fc0209051cd0323300b61922a369
+size 4976299316

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b765fa2e4ca6b338fecced030062cf67afbe9c1f98c27caecc73dd3ae2b6243
+size 4988969216

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5772a1a9f3f4c3e66255eb1243f1d0b3a424f08e3c6a93aed67c40440d1648c7
+size 4979964724

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b42a7dec69e0f76199d68a8e29ec9cccfb098e7fd85bcc11a58ccf6404a13c
+size 4984793756

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145050d5df0e4a90fd216f0eb3ebf5350f19790dee7856f19747fb7f6eab9cf3
+size 4986151124

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e14de3ab4a1db0792d7b8fdbf7cc53c97daf70f2b543d812c0f9a18ec9304a14
+size 2586436692

tokenizer_config.json

@@ -34,7 +34,7 @@
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "legacy": false,
-  "model_max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
   "padding_side": "left",
   "sp_model_kwargs": {},