初始化项目,由ModelHub XC社区提供模型
Model: helloadhavan/llara1.1-100M-base Source: Original Platform
This commit is contained in:
35
checkpoint-19303/config.json
Normal file
35
checkpoint-19303/config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"add_cross_attention": false,
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"dtype": "float32",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 256,
|
||||
"n_embd": 640,
|
||||
"n_head": 10,
|
||||
"n_inner": null,
|
||||
"n_layer": 12,
|
||||
"n_positions": 256,
|
||||
"pad_token_id": 50256,
|
||||
"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,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.12.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 50257
|
||||
}
|
||||
9
checkpoint-19303/generation_config.json
Normal file
9
checkpoint-19303/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"transformers_version": "5.12.1",
|
||||
"use_cache": true
|
||||
}
|
||||
3
checkpoint-19303/model.safetensors
Normal file
3
checkpoint-19303/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3aeb0ecaafe08533200daff41b55fbff8818bb06cb215712d61388d1c59dee9
|
||||
size 365662304
|
||||
3
checkpoint-19303/optimizer.pt
Normal file
3
checkpoint-19303/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff8986558d53ea2107a5881f18093414071be8a94e1f3652faa78ac592b71a79
|
||||
size 731421067
|
||||
3
checkpoint-19303/rng_state.pth
Normal file
3
checkpoint-19303/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e9c37710e18dea87cb9e9715d01568fd86fd880df772ae5090b293b3b1d575ff
|
||||
size 14645
|
||||
3
checkpoint-19303/scaler.pt
Normal file
3
checkpoint-19303/scaler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:50f1261edb18a387451c4394b4d8b434f60bcb2b96618e07c03624c9eccfe8f9
|
||||
size 1383
|
||||
3
checkpoint-19303/scheduler.pt
Normal file
3
checkpoint-19303/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bced912761116e5ca48d074542e3dd2beca50deb5fe07376c4b361b34c8622f2
|
||||
size 1465
|
||||
2736
checkpoint-19303/trainer_state.json
Normal file
2736
checkpoint-19303/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-19303/training_args.bin
Normal file
3
checkpoint-19303/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8afc1c0b06a60d7ee2d75f19dce13ae9555a437de8188f2c1b6a1f58a65c856
|
||||
size 5201
|
||||
Reference in New Issue
Block a user