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-92910/config.json
Normal file
31
checkpoint-92910/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-92910/generation_config.json
Normal file
6
checkpoint-92910/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-92910/model.safetensors
Normal file
3
checkpoint-92910/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7959833a1e7a800ab29c46d0f34050a7045b6677c4036b2ad93d02352a64f144
|
||||
size 503128704
|
||||
3
checkpoint-92910/optimizer.pt
Normal file
3
checkpoint-92910/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:055e52d56893db5ec2ae87fe2b153b2dbb9a9fa0e8bea64e14c7989b43446dc7
|
||||
size 1006351290
|
||||
3
checkpoint-92910/rng_state.pth
Normal file
3
checkpoint-92910/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b129b2214bf4b7c264a8d1bbcdeccb1141400ae41ba3726aa2812925cf12a6ce
|
||||
size 14244
|
||||
3
checkpoint-92910/scheduler.pt
Normal file
3
checkpoint-92910/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a5997429af2945b58a621e9797d0c6f2ee46b59c99623e15eb415de112a122b0
|
||||
size 1064
|
||||
1
checkpoint-92910/special_tokens_map.json
Normal file
1
checkpoint-92910/special_tokens_map.json
Normal file
@@ -0,0 +1 @@
|
||||
{}
|
||||
269727
checkpoint-92910/tokenizer.json
Normal file
269727
checkpoint-92910/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
14911
checkpoint-92910/tokenizer_config.json
Normal file
14911
checkpoint-92910/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
13867
checkpoint-92910/trainer_state.json
Normal file
13867
checkpoint-92910/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-92910/training_args.bin
Normal file
3
checkpoint-92910/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c26bb2622799f3a11d143b9d5ed5e2bec603f72cca5c0439c681d8a1aca243e
|
||||
size 5304
|
||||
Reference in New Issue
Block a user