Upload model
Browse files- config.json +34 -0
- generation_config.json +35 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"classifier_dropout": 0.0,
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"dtype": "bfloat16",
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"scale_decoder_outputs": false,
|
| 29 |
+
"tie_word_embeddings": true,
|
| 30 |
+
"tokenizer_class": "T5Tokenizer",
|
| 31 |
+
"transformers_version": "5.8.1",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 30000
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": false,
|
| 3 |
+
"assistant_confidence_threshold": 0.4,
|
| 4 |
+
"assistant_lookbehind": 10,
|
| 5 |
+
"decoder_start_token_id": 0,
|
| 6 |
+
"diversity_penalty": 0.0,
|
| 7 |
+
"do_sample": false,
|
| 8 |
+
"early_stopping": false,
|
| 9 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 10 |
+
"encoder_repetition_penalty": 1.0,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"epsilon_cutoff": 0.0,
|
| 13 |
+
"eta_cutoff": 0.0,
|
| 14 |
+
"length_penalty": 1.0,
|
| 15 |
+
"max_length": 20,
|
| 16 |
+
"min_length": 0,
|
| 17 |
+
"no_repeat_ngram_size": 0,
|
| 18 |
+
"num_assistant_tokens": 20,
|
| 19 |
+
"num_assistant_tokens_schedule": "constant",
|
| 20 |
+
"num_beam_groups": 1,
|
| 21 |
+
"num_beams": 1,
|
| 22 |
+
"num_return_sequences": 1,
|
| 23 |
+
"output_scores": false,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"remove_invalid_values": false,
|
| 26 |
+
"repetition_penalty": 1.0,
|
| 27 |
+
"return_dict_in_generate": false,
|
| 28 |
+
"target_lookbehind": 10,
|
| 29 |
+
"temperature": 1.0,
|
| 30 |
+
"top_k": 50,
|
| 31 |
+
"top_p": 1.0,
|
| 32 |
+
"transformers_version": "5.8.1",
|
| 33 |
+
"typical_p": 1.0,
|
| 34 |
+
"use_cache": true
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d12fd2049824b6cdf075c91a795801fd06323a5c51c5d3bdc8455678ad15c7e9
|
| 3 |
+
size 488652336
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"extra_ids": 0,
|
| 5 |
+
"extra_special_tokens": [],
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "<pad>",
|
| 10 |
+
"tokenizer_class": "T5Tokenizer",
|
| 11 |
+
"unk_id": 2,
|
| 12 |
+
"unk_token": "<unk>"
|
| 13 |
+
}
|