v1.1

.gitattributes

@@ -35,3 +35,5 @@ 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.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": 2048,
   "initializer_range": 0.02,
@@ -16,14 +17,13 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
   "num_key_value_heads": 16,
-  "num_layers": 24,
   "pretraining_tp": 1,
   "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.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec596bbf8f95408a120b009f320621cdcd2f861b3e373e770fe5a12754de66b
+oid sha256:895a734b23869bfa3fdca1956cfc3de4bba500c4e8c7d958067c74cf807406f3
 size 4507005744

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,