Updated quantized model

generation_config.json

@@ -1,11 +1,13 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
+  "do_sample": true,
   "eos_token_id": [
     1,
     106
   ],
   "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
   "transformers_version": "4.50.0.dev0"
 }

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce2cfa590ffd7c1edff32fd62bc5e978703e4db0a497c5c04f68749bca69901
+oid sha256:3ee3056de4d09801fd8c05d4518650e2327759e4f54990bfbbd59fde4d5e6804
 size 3406987504

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2bdf5acd222022a409ad1043ff2e9da87d571aa83174d6225a75428e30eecb6
+oid sha256:fc7d43f12cddd04200bc80a73f2e5c7a64da97592132bf0ce2dfdce8914f8edd
 size 3406987768

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6fd260835db80c5cdb3b7a0a1e18ab9162d730cbe36e325e4a097cec53c34d
+oid sha256:cffdaddf3828b94d69402af42b9347f8dd04e6fbfa642cb298041bfbfffae866
 size 3406987768

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92faeb810d36efb81f4749611ffb0d4401ef2e3ef87c3917b547bea5dec8ffc
+oid sha256:8abfbbdc62e611a6353b73de06a9e5ae6a6e1d19f19117d53252a928ec081b78
 size 2981114272