lorinet3/gpt-sw3-126m-exercise-scenario-generator
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: lorinet3/gpt-sw3-126m-exercise-scenario-generator
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-18 00:51:16 +08:00
commit 7cbf69a626
40 changed files with 8896 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
checkpoint-5000/added_tokens.json Normal file
View File

@@ -0,0 +1,18 @@
{
"[A1]": 64012,
"[A2]": 64013,
"[B1]": 64014,
"[B2]": 64015,
"[EXERCISE_VARIATIONS]": 64011,
"[LESSON]": 64009,
"[PRACTICE_TEXT]": 64010,
"antonym_focus": 64007,
"definition_only": 64008,
"fill_in_the_blanks": 64003,
"free_writing": 64000,
"general_vocab": 64004,
"matching_pairs": 64001,
"morphology_focus": 64005,
"reorder_tokens": 64002,
"synonym_focus": 64006
}

36
checkpoint-5000/config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"activation_function": "gelu",
"apply_query_key_layer_scaling": true,
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 2,
"dtype": "bfloat16",
"embd_pdrop": 0.1,
"eos_token_id": 3,
"initializer_range": 0.023,
"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": 4096,
"normalize_attention_scores": true,
"pad_token_id": 0,
"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,
"tokenizer_class": "GPTSw3Tokenizer",
"transformers_version": "4.57.1",
"use_cache": false,
"vocab_size": 64016
}

8
checkpoint-5000/generation_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"_from_model_config": true,
"bos_token_id": 2,
"eos_token_id": 3,
"pad_token_id": 0,
"transformers_version": "4.57.1",
"use_cache": false
}

3
checkpoint-5000/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c8409674d4f5f7842bdbe90eafd6f4ee47fd5a324ad1335a27ee50dd3d1464c
size 274779928

3
checkpoint-5000/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ebd558a9a8e6f927612096fcee1a8f7eb45ef97e36a8768896f17cb53316d9a8
size 549590475

3
checkpoint-5000/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3fefcda1eb027efef7338951cd8da153385aed51c0764a3508e3386a88297f27
size 14645

3
checkpoint-5000/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:12b1feb292d5e79121d1de1f6c7915c97f017d43ae37c65efa1038db2ec6c3d5
size 1465

127
checkpoint-5000/special_tokens_map.json Normal file
View File

@@ -0,0 +1,127 @@
{
"additional_special_tokens": [
{
"content": "--",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "free_writing",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "matching_pairs",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "reorder_tokens",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "fill_in_the_blanks",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "general_vocab",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "morphology_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "synonym_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "antonym_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "definition_only",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[LESSON]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[PRACTICE_TEXT]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[EXERCISE_VARIATIONS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[A1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[A2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[B1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[B2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
],
"bos_token": "<s>",
"eos_token": "<|endoftext|>",
"pad_token": "<pad>",
"unk_token": "<unk>"
}

3
checkpoint-5000/spiece.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4bda2cd84ff0ac659cda40e746c55f47ee3e57cf18471670ad26998c28be52d
size 1071955

203
checkpoint-5000/tokenizer_config.json Normal file
View File

@@ -0,0 +1,203 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"603": {
"content": "--",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64000": {
"content": "free_writing",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64001": {
"content": "matching_pairs",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64002": {
"content": "reorder_tokens",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64003": {
"content": "fill_in_the_blanks",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64004": {
"content": "general_vocab",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64005": {
"content": "morphology_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64006": {
"content": "synonym_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64007": {
"content": "antonym_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64008": {
"content": "definition_only",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64009": {
"content": "[LESSON]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64010": {
"content": "[PRACTICE_TEXT]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64011": {
"content": "[EXERCISE_VARIATIONS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64012": {
"content": "[A1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64013": {
"content": "[A2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64014": {
"content": "[B1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64015": {
"content": "[B2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"--",
"free_writing",
"matching_pairs",
"reorder_tokens",
"fill_in_the_blanks",
"general_vocab",
"morphology_focus",
"synonym_focus",
"antonym_focus",
"definition_only",
"[LESSON]",
"[PRACTICE_TEXT]",
"[EXERCISE_VARIATIONS]",
"[A1]",
"[A2]",
"[B1]",
"[B2]"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"keep_accents": false,
"model_max_length": 4096,
"pad_token": "<pad>",
"remove_space": false,
"sp_model_kwargs": {},
"tokenizer_class": "GPTSw3Tokenizer",
"unk_token": "<unk>"
}

3614
checkpoint-5000/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-5000/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:28a647ef5efc6ef28f13ecc4d3c99da28526fcc6c25fb933bc470139f20fd302
size 5969