初始化项目,由ModelHub XC社区提供模型
Model: fpadovani/eng_100mb_baseline_seed3407 Source: Original Platform
This commit is contained in:
35
checkpoint-20000/config.json
Normal file
35
checkpoint-20000/config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"_name_or_path": "goldfish-models/eng_latn_100mb",
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 2048,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 2048,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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": "bfloat16",
|
||||
"transformers_version": "4.47.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
7
checkpoint-20000/generation_config.json
Normal file
7
checkpoint-20000/generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": 50001,
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.47.0"
|
||||
}
|
||||
3
checkpoint-20000/model.safetensors
Normal file
3
checkpoint-20000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e85c41b4232f991822a871c7cab9ea8f3b3d21d4b27f52ebca7db7a4f99cd0dd
|
||||
size 251915968
|
||||
3
checkpoint-20000/optimizer.pt
Normal file
3
checkpoint-20000/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3d831383f3982465fc7800c05baeb691f6532855772b78cb5dfcaf2b7c0f1bca
|
||||
size 503926155
|
||||
3
checkpoint-20000/rng_state.pth
Normal file
3
checkpoint-20000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4daaedc5aca0815419c3cdca2050c361c2d53e62363a733c235fb39522267c4c
|
||||
size 14645
|
||||
3
checkpoint-20000/scheduler.pt
Normal file
3
checkpoint-20000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6654d4acd90458a188fd9adc6ca8bb91014a57eb893fdbe0b259fd07bf04c820
|
||||
size 1465
|
||||
1249
checkpoint-20000/special_tokens_map.json
Normal file
1249
checkpoint-20000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
210940
checkpoint-20000/tokenizer.json
Normal file
210940
checkpoint-20000/tokenizer.json
Normal file
File diff suppressed because one or more lines are too long
10829
checkpoint-20000/tokenizer_config.json
Normal file
10829
checkpoint-20000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
28193
checkpoint-20000/trainer_state.json
Normal file
28193
checkpoint-20000/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-20000/training_args.bin
Normal file
3
checkpoint-20000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d158a5b32cad30637a7c568c36ecb1696be17e1bd944853e45e7b88828bc9f6
|
||||
size 6097
|
||||
Reference in New Issue
Block a user