OpenGVLab/cllm_td_opt
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: OpenGVLab/cllm_td_opt
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-05 05:54:13 +08:00
commit 6692eb7fad
11 changed files with 100486 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

3
README.md Normal file
View File

@@ -0,0 +1,3 @@
---
license: apache-2.0
---

31
config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"_name_or_path": "/mnt/afs/user/liuzhaoyang/.cache/huggingface/hub/models--facebook--opt-2.7b/snapshots/397f71a473a150c00f0fe3fc4a2f78ff3ccaf82d",
"_remove_final_layer_norm": false,
"activation_dropout": 0.0,
"activation_function": "relu",
"architectures": [
"OPTForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 2,
"do_layer_norm_before": true,
"dropout": 0.1,
"enable_bias": true,
"eos_token_id": 2,
"ffn_dim": 10240,
"hidden_size": 2560,
"init_std": 0.02,
"layer_norm_elementwise_affine": true,
"layerdrop": 0.0,
"max_position_embeddings": 2048,
"model_type": "opt",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 1,
"prefix": "</s>",
"torch_dtype": "bfloat16",
"transformers_version": "4.30.2",
"use_cache": true,
"vocab_size": 50265,
"word_embed_proj_dim": 2560
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 2,
"eos_token_id": 2,
"pad_token_id": 1,
"transformers_version": "4.30.2"
}

50001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c4cac0338ea8d029ea576c1de0c1aaf04929e5493e23af567730887a3eb69a8
size 5303326905

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

41
tokenizer_config.json Normal file
View File

@@ -0,0 +1,41 @@
{
"add_bos_token": true,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1536,
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"padding_side": "right",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

67
trainer_state.json Normal file
View File

@@ -0,0 +1,67 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.0,
"global_step": 3834,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.78,
"learning_rate": 1.793975255513717e-05,
"loss": 0.0241,
"step": 500
},
{
"epoch": 1.56,
"learning_rate": 1.5250134480903713e-05,
"loss": 0.0021,
"step": 1000
},
{
"epoch": 2.35,
"learning_rate": 1.2560516406670254e-05,
"loss": 0.0014,
"step": 1500
},
{
"epoch": 3.13,
"learning_rate": 9.870898332436795e-06,
"loss": 0.0011,
"step": 2000
},
{
"epoch": 3.91,
"learning_rate": 7.181280258203336e-06,
"loss": 0.0008,
"step": 2500
},
{
"epoch": 4.69,
"learning_rate": 4.491662183969877e-06,
"loss": 0.0006,
"step": 3000
},
{
"epoch": 5.48,
"learning_rate": 1.8020441097364175e-06,
"loss": 0.0005,
"step": 3500
},
{
"epoch": 6.0,
"step": 3834,
"total_flos": 2403004334473216.0,
"train_loss": 0.0040491660264984795,
"train_runtime": 24808.6685,
"train_samples_per_second": 19.777,
"train_steps_per_second": 0.155
}
],
"max_steps": 3834,
"num_train_epochs": 6,
"total_flos": 2403004334473216.0,
"trial_name": null,
"trial_params": null
}

50267
vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff