v1.1

.gitattributes

@@ -35,3 +35,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 images/salamandra_header.png filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

config.json

@@ -6,6 +6,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -17,12 +18,12 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "vocab_size": 256000
 }

generation_config.json

@@ -7,5 +7,5 @@
   "top_p": 0.95,
   "max_new_tokens": 25,
   "repetition_penalty": 1.2,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.45.2"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476aa35f9b2251b2e15b9d9107bc63b8506d219e999817fe9d870fb410c2145d
+oid sha256:37605bf126644abb6e195034fae986f5248aed453b3579047e3a475aaf2387ab
 size 4982973048

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c1450233d3453c9faafdbfa1d4f96f5c29e669f3f7e69ccdd1a7b53ad934d1
+oid sha256:de573b93500a81744174cbfdbcd54465ab5e1e5d76dccd32d53382ad54a3d337
 size 4995660232

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c5c41380f2f7b4caea1c011a4170270d33e76190135faae2bde104d1946fe2
+oid sha256:f507941af2449c9f24c776ffa379ea78995b94c2d370202a786ac6d5642888d9
 size 3460482936

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbfdbb42a23f684cc00c560209fa0256881f6ff8eade4f3c0d9c8f13d3825989
+oid sha256:c4944914fb33caad0b42c1591478d6fe95dd07811a899ea7ac6b3bfcbd3c2052
 size 2097152128

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:990527d1e7b98c027d386c742250b2f8517bd3adf98c46cc6c1c2f35b234c224
-size 37007559
+oid sha256:2e90b85b3e3b3ebfc6b9bafeb954b37f2435eed595738337e53f2a746d23d5a2
+size 37007416

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa490e57cebce5cb1a0a5b1a5d3fa4de05aee53dc3a44791f1c3401db44d802d
-size 4813274
+oid sha256:ab94ddf46d14f0279254858d53770c5319c5129d47291ee2bada530271cb1292
+size 4813276

tokenizer_config.json

@@ -31,8 +31,9 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 8192,
+  "legacy": false,
+  "local_files_only": true,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,