初始化项目,由ModelHub XC社区提供模型
Model: craa/100M_low_1000_6910 Source: Original Platform
This commit is contained in:
31
checkpoint-92750/config.json
Normal file
31
checkpoint-92750/config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": null,
|
||||
"n_layer": 12,
|
||||
"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,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.47.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 52000
|
||||
}
|
||||
6
checkpoint-92750/generation_config.json
Normal file
6
checkpoint-92750/generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.47.0.dev0"
|
||||
}
|
||||
3
checkpoint-92750/model.safetensors
Normal file
3
checkpoint-92750/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1b63c717f01d64be9761547b4c0226cdc091e343dfa33a4cd32991575cf53e98
|
||||
size 503128704
|
||||
3
checkpoint-92750/optimizer.pt
Normal file
3
checkpoint-92750/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09a74afb4dc2ea40e2eb675a43116a14e983ee37b17cb5f843be5b085b1745df
|
||||
size 1006351290
|
||||
3
checkpoint-92750/rng_state.pth
Normal file
3
checkpoint-92750/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d87c7863c938558f3805c0a7b34210c6686f145cd424a20b61baeaa1f77b7722
|
||||
size 14244
|
||||
3
checkpoint-92750/scheduler.pt
Normal file
3
checkpoint-92750/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6f1aadb4bada80ad28c6a4542fcf4eb66d53607e0ac01a5320a3db3773d63cf
|
||||
size 1064
|
||||
1
checkpoint-92750/special_tokens_map.json
Normal file
1
checkpoint-92750/special_tokens_map.json
Normal file
@@ -0,0 +1 @@
|
||||
{}
|
||||
269727
checkpoint-92750/tokenizer.json
Normal file
269727
checkpoint-92750/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
14911
checkpoint-92750/tokenizer_config.json
Normal file
14911
checkpoint-92750/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
13846
checkpoint-92750/trainer_state.json
Normal file
13846
checkpoint-92750/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-92750/training_args.bin
Normal file
3
checkpoint-92750/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
|
||||
size 5304
|
||||
Reference in New Issue
Block a user