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-41387/config.json
Normal file
35
checkpoint-41387/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": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": null,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"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-41387/generation_config.json
Normal file
9
checkpoint-41387/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-41387/model.safetensors
Normal file
3
checkpoint-41387/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bfb01924edc39e9b251cdeeddf0ca4e46b5694b3887475c58764d3800d990a97
|
||||
size 496201344
|
||||
3
checkpoint-41387/optimizer.pt
Normal file
3
checkpoint-41387/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb1c92d3f953c44397d88aa767c4ee8182bedb9b434ee29395e8673de455b1b6
|
||||
size 992499083
|
||||
3
checkpoint-41387/rng_state.pth
Normal file
3
checkpoint-41387/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13bed6601325b27039db676acc7e73f5b329a90683a6c41a8fb7f375bd40784f
|
||||
size 14645
|
||||
3
checkpoint-41387/scaler.pt
Normal file
3
checkpoint-41387/scaler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7e262a33f24fc97140ad37f10e9cd135813189769b63f6c658bec08702b24255
|
||||
size 1383
|
||||
3
checkpoint-41387/scheduler.pt
Normal file
3
checkpoint-41387/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:75fd4e3a2ab7426471542b9e73a6ad9aab6cf10535aadf8e3868febeda754bd5
|
||||
size 1465
|
||||
5823
checkpoint-41387/trainer_state.json
Normal file
5823
checkpoint-41387/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-41387/training_args.bin
Normal file
3
checkpoint-41387/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