Upload 28 files
Browse files- models--airesearch--wangchanberta-base-att-spm-uncased/.no_exist/b81d38df6b4755dbedec0bfea863c9956cbb963e/added_tokens.json +0 -0
- models--airesearch--wangchanberta-base-att-spm-uncased/.no_exist/b81d38df6b4755dbedec0bfea863c9956cbb963e/generation_config.json +0 -0
- models--airesearch--wangchanberta-base-att-spm-uncased/.no_exist/b81d38df6b4755dbedec0bfea863c9956cbb963e/special_tokens_map.json +0 -0
- models--airesearch--wangchanberta-base-att-spm-uncased/.no_exist/b81d38df6b4755dbedec0bfea863c9956cbb963e/tokenizer.json +0 -0
- models--airesearch--wangchanberta-base-att-spm-uncased/refs/main +1 -0
- models--airesearch--wangchanberta-base-att-spm-uncased/snapshots/b81d38df6b4755dbedec0bfea863c9956cbb963e/config.json +23 -0
- models--airesearch--wangchanberta-base-att-spm-uncased/snapshots/b81d38df6b4755dbedec0bfea863c9956cbb963e/model.safetensors +3 -0
- models--airesearch--wangchanberta-base-att-spm-uncased/snapshots/b81d38df6b4755dbedec0bfea863c9956cbb963e/sentencepiece.bpe.model +3 -0
- models--airesearch--wangchanberta-base-att-spm-uncased/snapshots/b81d38df6b4755dbedec0bfea863c9956cbb963e/tokenizer_config.json +14 -0
- models--gpt2/.no_exist/607a30d783dfa663caf39e06633721c8d4cfcd7e/added_tokens.json +0 -0
- models--gpt2/.no_exist/607a30d783dfa663caf39e06633721c8d4cfcd7e/special_tokens_map.json +0 -0
- models--gpt2/refs/main +1 -0
- models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/config.json +31 -0
- models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/generation_config.json +6 -0
- models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/merges.txt +0 -0
- models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/model.safetensors +3 -0
- models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer.json +0 -0
- models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer_config.json +1 -0
- models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/vocab.json +0 -0
- models--openai-community--gpt2/.no_exist/607a30d783dfa663caf39e06633721c8d4cfcd7e/added_tokens.json +0 -0
- models--openai-community--gpt2/.no_exist/607a30d783dfa663caf39e06633721c8d4cfcd7e/special_tokens_map.json +0 -0
- models--openai-community--gpt2/refs/main +1 -0
- models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/config.json +31 -0
- models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/merges.txt +0 -0
- models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer.json +0 -0
- models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer_config.json +1 -0
- models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/vocab.json +0 -0
- version.txt +1 -0
models--airesearch--wangchanberta-base-att-spm-uncased/.no_exist/b81d38df6b4755dbedec0bfea863c9956cbb963e/added_tokens.json
ADDED
|
File without changes
|
models--airesearch--wangchanberta-base-att-spm-uncased/.no_exist/b81d38df6b4755dbedec0bfea863c9956cbb963e/generation_config.json
ADDED
|
File without changes
|
models--airesearch--wangchanberta-base-att-spm-uncased/.no_exist/b81d38df6b4755dbedec0bfea863c9956cbb963e/special_tokens_map.json
ADDED
|
File without changes
|
models--airesearch--wangchanberta-base-att-spm-uncased/.no_exist/b81d38df6b4755dbedec0bfea863c9956cbb963e/tokenizer.json
ADDED
|
File without changes
|
models--airesearch--wangchanberta-base-att-spm-uncased/refs/main
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
b81d38df6b4755dbedec0bfea863c9956cbb963e
|
models--airesearch--wangchanberta-base-att-spm-uncased/snapshots/b81d38df6b4755dbedec0bfea863c9956cbb963e/config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "camembert",
|
| 17 |
+
"num_attention_head": 12,
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"type_vocab_size": 1,
|
| 22 |
+
"vocab_size": 25005
|
| 23 |
+
}
|
models--airesearch--wangchanberta-base-att-spm-uncased/snapshots/b81d38df6b4755dbedec0bfea863c9956cbb963e/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03b5fce837ca21563d2a30e2e6d0e3c9d9a7c7b17e01d7c0c36e93dce67fcd38
|
| 3 |
+
size 423470574
|
models--airesearch--wangchanberta-base-att-spm-uncased/snapshots/b81d38df6b4755dbedec0bfea863c9956cbb963e/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
|
| 3 |
+
size 904693
|
models--airesearch--wangchanberta-base-att-spm-uncased/snapshots/b81d38df6b4755dbedec0bfea863c9956cbb963e/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"sep_token": "</s>",
|
| 6 |
+
"cls_token": "<s>",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"additional_special_tokens": [
|
| 10 |
+
"<s>NOTUSED",
|
| 11 |
+
"</s>NOTUSED",
|
| 12 |
+
"<_>"
|
| 13 |
+
]
|
| 14 |
+
}
|
models--gpt2/.no_exist/607a30d783dfa663caf39e06633721c8d4cfcd7e/added_tokens.json
ADDED
|
File without changes
|
models--gpt2/.no_exist/607a30d783dfa663caf39e06633721c8d4cfcd7e/special_tokens_map.json
ADDED
|
File without changes
|
models--gpt2/refs/main
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
607a30d783dfa663caf39e06633721c8d4cfcd7e
|
models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 1024,
|
| 14 |
+
"n_embd": 768,
|
| 15 |
+
"n_head": 12,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"resid_pdrop": 0.1,
|
| 19 |
+
"summary_activation": null,
|
| 20 |
+
"summary_first_dropout": 0.1,
|
| 21 |
+
"summary_proj_to_labels": true,
|
| 22 |
+
"summary_type": "cls_index",
|
| 23 |
+
"summary_use_proj": true,
|
| 24 |
+
"task_specific_params": {
|
| 25 |
+
"text-generation": {
|
| 26 |
+
"do_sample": true,
|
| 27 |
+
"max_length": 50
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 50256,
|
| 3 |
+
"eos_token_id": 50256,
|
| 4 |
+
"transformers_version": "4.26.0.dev0",
|
| 5 |
+
"_from_model_config": true
|
| 6 |
+
}
|
models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:248dfc3911869ec493c76e65bf2fcf7f615828b0254c12b473182f0f81d3a707
|
| 3 |
+
size 548105171
|
models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_max_length": 1024}
|
models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models--openai-community--gpt2/.no_exist/607a30d783dfa663caf39e06633721c8d4cfcd7e/added_tokens.json
ADDED
|
File without changes
|
models--openai-community--gpt2/.no_exist/607a30d783dfa663caf39e06633721c8d4cfcd7e/special_tokens_map.json
ADDED
|
File without changes
|
models--openai-community--gpt2/refs/main
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
607a30d783dfa663caf39e06633721c8d4cfcd7e
|
models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 1024,
|
| 14 |
+
"n_embd": 768,
|
| 15 |
+
"n_head": 12,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"resid_pdrop": 0.1,
|
| 19 |
+
"summary_activation": null,
|
| 20 |
+
"summary_first_dropout": 0.1,
|
| 21 |
+
"summary_proj_to_labels": true,
|
| 22 |
+
"summary_type": "cls_index",
|
| 23 |
+
"summary_use_proj": true,
|
| 24 |
+
"task_specific_params": {
|
| 25 |
+
"text-generation": {
|
| 26 |
+
"do_sample": true,
|
| 27 |
+
"max_length": 50
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_max_length": 1024}
|
models--openai-community--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
1
|