Upload HGRNForCausalLM

config.json

@@ -6,6 +6,7 @@
   "attn_mode": "fused_recurrent",
   "bos_token_id": 1,
   "conv_size": 4,
+  "elementwise_affine": true,
   "eos_token_id": 2,
   "expand_ratio": 1,
   "fuse_cross_entropy": true,
@@ -16,13 +17,14 @@
   "intermediate_size": null,
   "max_position_embeddings": 2048,
   "model_type": "hgrn",
+  "norm_eps": 1e-06,
   "num_heads": 1,
   "num_hidden_layers": 24,
-  "rms_norm_eps": 1e-06,
+  "pad_token_id": 2,
   "share_conv_kernel": true,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "use_lower_bound": true,
   "use_short_conv": false,

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.45.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9dba90c71b61b9b46561282e7bb8266d79769fea03f98fa107603c077589b1
+oid sha256:c242dd37b51c8b16cfdb8fa7b239bf41e4a172bc93236d3c0997c5fc7b1fc0fb
 size 2728816304

special_tokens_map.json

@@ -13,6 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -31,9 +32,9 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",