Upload folder using huggingface_hub

rinna/bilingual-gpt-neox-4b-instruction-sft/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "rinna/bilingual-gpt-neox-4b-instruction-sft",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 2816,
+  "initializer_range": 0.02,
+  "intermediate_size": 11264,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 22,
+  "num_hidden_layers": 36,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 65536
+}

rinna/bilingual-gpt-neox-4b-instruction-sft/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "transformers_version": "4.33.2"
+}

rinna/bilingual-gpt-neox-4b-instruction-sft/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

rinna/bilingual-gpt-neox-4b-instruction-sft/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a0205d37a98bb3b97cf4ca3f507c78873cf8f6cefa3b51d8d6a15006dc889d
+size 1341798

rinna/bilingual-gpt-neox-4b-instruction-sft/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "[UNK]"
+}

rinna/japanese-gpt2-xsmall/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "rinna/japanese-gpt2-xsmall",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": 2304,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

rinna/japanese-gpt2-xsmall/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.2"
+}