初始化项目,由ModelHub XC社区提供模型
Model: TIGER-Lab/One-Shot-CFT-Math-Qwen-14B Source: Original Platform
This commit is contained in:
commit
3fc9190e24
21 files changed
+153413
No files matched your search
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
@@ -0,0 +1,66 @@
|
||||
---
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-14B
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- One-Shot-CFT
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
license: cc-by-4.0
|
||||
---
|
||||
|
||||
# One-Shot-CFT: Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
|
||||
|
||||
<p align="center">
|
||||
<a href="https://github.com/TIGER-AI-Lab/One-Shot-CFT" target="_blank">💻 Code</a> |
|
||||
<a href="https://arxiv.org/pdf/2506.03295" target="_blank">📄 Paper</a> |
|
||||
<a href="https://huggingface.co/datasets/TIGER-Lab/One-Shot-CFT-Data" target="_blank">📊 Dataset</a> |
|
||||
<a href="https://huggingface.co/collections/TIGER-Lab/one-shot-cft-683fbb4d2bcf698dbea8fb21" target="_blank">🤗 Model</a> |
|
||||
<a href="https://tiger-ai-lab.github.io/One-Shot-CFT/" target="_blank">🌐 Project Page</a>
|
||||
</p>
|
||||
|
||||
|
||||
|
||||
## 🧠 Overview
|
||||
|
||||
One-Shot Critique Fine-Tuning (CFT) is a simple, robust, and compute-efficient training paradigm for unleashing the reasoning capabilities of pretrained LLMs in both mathematical and logical domains. By leveraging critiques on just one problem, One-Shot CFT enables models like Qwen and LLaMA to match or even outperform reinforcement learning, while using 20× less compute.
|
||||
|
||||
Instead of learning from reference answers (as in supervised fine-tuning) or reward signals (as in reinforcement learning), One-Shot CFT enables models to learn from critiques of diverse solutions to a single problem, enhancing their exposure to varied reasoning patterns and mitigating overfitting. This exposes the LLMs to multiple perspectives and error types, thereby more effectively unleashing their reasoning potential.
|
||||
|
||||
|
||||
## ✨ Key Highlights
|
||||
|
||||
- **Unleashes Reasoning with One Example:** One-Shot CFT uses critiques of diverse model-generated solutions to a single problem to significantly boost performance across math and logic tasks. For example, with just 5 GPU hours of training on Qwen2.5-Math-7B, One-Shot CFT achieves an average improvement of +15% on six math benchmarks and +16% on three logic reasoning benchmarks.
|
||||
- **Outperforms RLVR and Full SFT with 20× Less Compute:** One-Shot CFT outperforms both one-shot Reinforcement Learning with Verifiable Rewards (RLVR) and full-dataset supervised fine-tuning, while requiring only 5 GPU hours on a 7B model—offering a much more efficient and stable training alternative.
|
||||
- **Robust Across Seeds and Model Scales:** One-Shot CFT remains effective across different seed problem choices and model sizes—from 1.5B to 14B parameters—demonstrating strong generalization and scalability.
|
||||
|
||||
**This specific model is the One-Shot CFT variant trained based on [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) with [DSR-CFT-p0](https://huggingface.co/datasets/TIGER-Lab/One-Shot-CFT-Data) dataset.**
|
||||
|
||||
|
||||
## Main Results
|
||||
|
||||
<p align="center">
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/636a35eff8d9af4aea181608/DCxRSdeDrv-Db4VLuEl0T.png" alt="CFT Performance Comparison" width="1100"/>
|
||||
</p>
|
||||
|
||||
<p align="center"><em>
|
||||
One-shot CFT consistently improves mathematical and logical reasoning.
|
||||
<strong>Left:</strong> Average accuracy on six mathematical reasoning benchmarks for Qwen and LLaMA models, comparing base, SFT, RLVR, and CFT with only one training example.
|
||||
<strong>Right:</strong> In-domain accuracy on three logic reasoning benchmarks (BBEH subtasks) for Qwen2.5-Math-7B.
|
||||
Across both domains, CFT with a single problem significantly outperforms standard SFT and matches or exceeds reinforcement learning with much lower compute.
|
||||
</em></p>
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
If you find our work helpful, please cite it as:
|
||||
|
||||
```bibtex
|
||||
@article{wang2025unleashing,
|
||||
title={Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem},
|
||||
author={Wang, Yubo and Nie, Ping and Zou, Kai and Wu, Lijun and Chen, Wenhu},
|
||||
journal={arXiv preprint arXiv:2506.03295},
|
||||
year={2025}
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
@@ -0,0 +1,366 @@
|
||||
{
|
||||
"model": "/data/yubo/models/Qwen2.5-14B",
|
||||
"model_type": "qwen2_5",
|
||||
"model_revision": null,
|
||||
"task_type": "causal_lm",
|
||||
"torch_dtype": "bfloat16",
|
||||
"attn_impl": "flash_attn",
|
||||
"num_labels": null,
|
||||
"problem_type": null,
|
||||
"rope_scaling": null,
|
||||
"device_map": null,
|
||||
"max_memory": {},
|
||||
"local_repo_path": null,
|
||||
"template": "qwen2_5",
|
||||
"system": null,
|
||||
"max_length": null,
|
||||
"truncation_strategy": "delete",
|
||||
"max_pixels": null,
|
||||
"agent_template": null,
|
||||
"norm_bbox": null,
|
||||
"response_prefix": null,
|
||||
"padding_side": "right",
|
||||
"loss_scale": "default",
|
||||
"sequence_parallel_size": 1,
|
||||
"use_chat_template": true,
|
||||
"template_backend": "swift",
|
||||
"dataset": [
|
||||
"/data/yubo/CriticCoT/dsr_scripts_0514/dsr_one-shot_train_data_0514_p0.jsonl"
|
||||
],
|
||||
"val_dataset": [],
|
||||
"split_dataset_ratio": 0.0,
|
||||
"data_seed": 42,
|
||||
"dataset_num_proc": 4,
|
||||
"dataset_shuffle": true,
|
||||
"val_dataset_shuffle": false,
|
||||
"streaming": false,
|
||||
"interleave_prob": null,
|
||||
"stopping_strategy": "first_exhausted",
|
||||
"shuffle_buffer_size": 1000,
|
||||
"enable_cache": false,
|
||||
"download_mode": "reuse_dataset_if_exists",
|
||||
"columns": {},
|
||||
"strict": false,
|
||||
"remove_unused_columns": false,
|
||||
"model_name": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"model_author": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"custom_dataset_info": [],
|
||||
"quant_method": null,
|
||||
"quant_bits": null,
|
||||
"hqq_axis": null,
|
||||
"bnb_4bit_compute_dtype": "bfloat16",
|
||||
"bnb_4bit_quant_type": "nf4",
|
||||
"bnb_4bit_use_double_quant": true,
|
||||
"bnb_4bit_quant_storage": null,
|
||||
"max_new_tokens": 64,
|
||||
"temperature": 0.0,
|
||||
"top_k": null,
|
||||
"top_p": null,
|
||||
"repetition_penalty": null,
|
||||
"num_beams": 1,
|
||||
"stream": false,
|
||||
"stop_words": [],
|
||||
"logprobs": false,
|
||||
"top_logprobs": null,
|
||||
"ckpt_dir": null,
|
||||
"load_dataset_config": null,
|
||||
"lora_modules": [],
|
||||
"tuner_backend": "peft",
|
||||
"train_type": "full",
|
||||
"adapters": [],
|
||||
"external_plugins": [],
|
||||
"seed": 42,
|
||||
"model_kwargs": {},
|
||||
"load_args": false,
|
||||
"load_data_args": false,
|
||||
"use_hf": true,
|
||||
"hub_token": null,
|
||||
"custom_register_path": [],
|
||||
"ignore_args_error": false,
|
||||
"use_swift_lora": false,
|
||||
"output_dir": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653",
|
||||
"overwrite_output_dir": false,
|
||||
"do_train": false,
|
||||
"do_eval": false,
|
||||
"do_predict": false,
|
||||
"eval_strategy": "steps",
|
||||
"prediction_loss_only": false,
|
||||
"per_device_train_batch_size": 1,
|
||||
"per_device_eval_batch_size": 1,
|
||||
"per_gpu_train_batch_size": null,
|
||||
"per_gpu_eval_batch_size": null,
|
||||
"gradient_accumulation_steps": 128,
|
||||
"eval_accumulation_steps": null,
|
||||
"eval_delay": 0,
|
||||
"torch_empty_cache_steps": null,
|
||||
"learning_rate": 5e-06,
|
||||
"weight_decay": 0.05,
|
||||
"adam_beta1": 0.9,
|
||||
"adam_beta2": 0.95,
|
||||
"adam_epsilon": 1e-08,
|
||||
"max_grad_norm": 1.0,
|
||||
"num_train_epochs": 200.0,
|
||||
"max_steps": -1,
|
||||
"lr_scheduler_type": "cosine",
|
||||
"lr_scheduler_kwargs": null,
|
||||
"warmup_ratio": 0.05,
|
||||
"warmup_steps": 0,
|
||||
"log_level": "passive",
|
||||
"log_level_replica": "warning",
|
||||
"log_on_each_node": true,
|
||||
"logging_dir": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653/runs",
|
||||
"logging_strategy": "steps",
|
||||
"logging_first_step": true,
|
||||
"logging_steps": 1,
|
||||
"logging_nan_inf_filter": true,
|
||||
"save_strategy": "steps",
|
||||
"save_steps": 10.0,
|
||||
"save_total_limit": null,
|
||||
"save_safetensors": true,
|
||||
"save_on_each_node": false,
|
||||
"save_only_model": true,
|
||||
"restore_callback_states_from_checkpoint": false,
|
||||
"no_cuda": false,
|
||||
"use_cpu": false,
|
||||
"use_mps_device": false,
|
||||
"jit_mode_eval": false,
|
||||
"use_ipex": false,
|
||||
"bf16": true,
|
||||
"fp16": false,
|
||||
"fp16_opt_level": "O1",
|
||||
"half_precision_backend": "auto",
|
||||
"bf16_full_eval": false,
|
||||
"fp16_full_eval": false,
|
||||
"tf32": null,
|
||||
"local_rank": 0,
|
||||
"ddp_backend": "nccl",
|
||||
"tpu_num_cores": null,
|
||||
"tpu_metrics_debug": false,
|
||||
"debug": null,
|
||||
"dataloader_drop_last": false,
|
||||
"eval_steps": 10.0,
|
||||
"dataloader_num_workers": 4,
|
||||
"dataloader_prefetch_factor": null,
|
||||
"past_index": -1,
|
||||
"run_name": "/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653",
|
||||
"disable_tqdm": null,
|
||||
"label_names": null,
|
||||
"load_best_model_at_end": false,
|
||||
"metric_for_best_model": "loss",
|
||||
"greater_is_better": false,
|
||||
"ignore_data_skip": false,
|
||||
"fsdp": "",
|
||||
"fsdp_min_num_params": 0,
|
||||
"fsdp_config": null,
|
||||
"tp_size": 0,
|
||||
"fsdp_transformer_layer_cls_to_wrap": null,
|
||||
"accelerator_config": {
|
||||
"dispatch_batches": false
|
||||
},
|
||||
"deepspeed": {
|
||||
"fp16": {
|
||||
"enabled": "auto",
|
||||
"loss_scale": 0,
|
||||
"loss_scale_window": 1000,
|
||||
"initial_scale_power": 16,
|
||||
"hysteresis": 2,
|
||||
"min_loss_scale": 1
|
||||
},
|
||||
"bf16": {
|
||||
"enabled": "auto"
|
||||
},
|
||||
"zero_optimization": {
|
||||
"stage": 3,
|
||||
"offload_optimizer": {
|
||||
"device": "none",
|
||||
"pin_memory": true
|
||||
},
|
||||
"offload_param": {
|
||||
"device": "none",
|
||||
"pin_memory": true
|
||||
},
|
||||
"overlap_comm": false,
|
||||
"contiguous_gradients": true,
|
||||
"sub_group_size": 1000000000.0,
|
||||
"reduce_bucket_size": "auto",
|
||||
"zero_quantized_weights": false,
|
||||
"zero_quantized_gradients": false,
|
||||
"stage3_prefetch_bucket_size": "auto",
|
||||
"stage3_param_persistence_threshold": "auto",
|
||||
"stage3_max_live_parameters": 1000000000.0,
|
||||
"stage3_max_reuse_distance": 1000000000.0,
|
||||
"stage3_gather_16bit_weights_on_model_save": true
|
||||
},
|
||||
"gradient_accumulation_steps": "auto",
|
||||
"gradient_clipping": "auto",
|
||||
"steps_per_print": 2000,
|
||||
"train_batch_size": "auto",
|
||||
"train_micro_batch_size_per_gpu": "auto",
|
||||
"wall_clock_breakdown": false
|
||||
},
|
||||
"label_smoothing_factor": 0.0,
|
||||
"optim": "adamw_torch",
|
||||
"optim_args": null,
|
||||
"adafactor": false,
|
||||
"group_by_length": false,
|
||||
"length_column_name": "length",
|
||||
"report_to": [
|
||||
"none"
|
||||
],
|
||||
"ddp_find_unused_parameters": null,
|
||||
"ddp_bucket_cap_mb": null,
|
||||
"ddp_broadcast_buffers": null,
|
||||
"dataloader_pin_memory": true,
|
||||
"dataloader_persistent_workers": false,
|
||||
"skip_memory_metrics": true,
|
||||
"use_legacy_prediction_loop": false,
|
||||
"push_to_hub": false,
|
||||
"resume_from_checkpoint": null,
|
||||
"hub_model_id": null,
|
||||
"hub_strategy": "every_save",
|
||||
"hub_private_repo": null,
|
||||
"hub_always_push": false,
|
||||
"gradient_checkpointing": true,
|
||||
"gradient_checkpointing_kwargs": null,
|
||||
"include_inputs_for_metrics": false,
|
||||
"include_for_metrics": [],
|
||||
"eval_do_concat_batches": true,
|
||||
"fp16_backend": "auto",
|
||||
"push_to_hub_model_id": null,
|
||||
"push_to_hub_organization": null,
|
||||
"push_to_hub_token": null,
|
||||
"mp_parameters": "",
|
||||
"auto_find_batch_size": false,
|
||||
"full_determinism": false,
|
||||
"torchdynamo": null,
|
||||
"ray_scope": "last",
|
||||
"ddp_timeout": 1800,
|
||||
"torch_compile": false,
|
||||
"torch_compile_backend": null,
|
||||
"torch_compile_mode": null,
|
||||
"include_tokens_per_second": false,
|
||||
"include_num_input_tokens_seen": false,
|
||||
"neftune_noise_alpha": null,
|
||||
"optim_target_modules": null,
|
||||
"batch_eval_metrics": false,
|
||||
"eval_on_start": false,
|
||||
"use_liger_kernel": false,
|
||||
"eval_use_gather_object": false,
|
||||
"average_tokens_across_devices": false,
|
||||
"sortish_sampler": false,
|
||||
"predict_with_generate": false,
|
||||
"generation_max_length": null,
|
||||
"generation_num_beams": null,
|
||||
"generation_config": null,
|
||||
"check_model": true,
|
||||
"acc_strategy": "token",
|
||||
"train_dataloader_shuffle": true,
|
||||
"metric_warmup_step": 0,
|
||||
"fsdp_num": 1,
|
||||
"acc_steps": 1,
|
||||
"eval_use_evalscope": false,
|
||||
"eval_datasets": [],
|
||||
"eval_limit": null,
|
||||
"eval_datasets_args": null,
|
||||
"eval_generation_config": null,
|
||||
"freeze_parameters": [],
|
||||
"freeze_parameters_ratio": 0.0,
|
||||
"trainable_parameters": [],
|
||||
"freeze_llm": false,
|
||||
"freeze_vit": false,
|
||||
"freeze_aligner": false,
|
||||
"target_modules": [
|
||||
"all-linear"
|
||||
],
|
||||
"target_regex": null,
|
||||
"modules_to_save": [],
|
||||
"lora_rank": 8,
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_bias": "none",
|
||||
"lora_dtype": null,
|
||||
"lorap_lr_ratio": null,
|
||||
"use_rslora": false,
|
||||
"use_dora": false,
|
||||
"lora_ga_batch_size": 2,
|
||||
"lora_ga_iters": 2,
|
||||
"lora_ga_max_length": 1024,
|
||||
"lora_ga_direction": "ArB2r",
|
||||
"lora_ga_scale": "stable",
|
||||
"lora_ga_stable_gamma": 16,
|
||||
"init_weights": true,
|
||||
"fourier_n_frequency": 2000,
|
||||
"fourier_scaling": 300.0,
|
||||
"boft_block_size": 4,
|
||||
"boft_block_num": 0,
|
||||
"boft_n_butterfly_factor": 1,
|
||||
"boft_dropout": 0.0,
|
||||
"vera_rank": 256,
|
||||
"vera_projection_prng_key": 0,
|
||||
"vera_dropout": 0.0,
|
||||
"vera_d_initial": 0.1,
|
||||
"adapter_act": "gelu",
|
||||
"adapter_length": 128,
|
||||
"use_galore": false,
|
||||
"galore_target_modules": null,
|
||||
"galore_rank": 128,
|
||||
"galore_update_proj_gap": 50,
|
||||
"galore_scale": 1.0,
|
||||
"galore_proj_type": "std",
|
||||
"galore_optim_per_parameter": false,
|
||||
"galore_with_embedding": false,
|
||||
"galore_quantization": false,
|
||||
"galore_proj_quant": false,
|
||||
"galore_proj_bits": 4,
|
||||
"galore_proj_group_size": 256,
|
||||
"galore_cos_threshold": 0.4,
|
||||
"galore_gamma_proj": 2,
|
||||
"galore_queue_size": 5,
|
||||
"adalora_target_r": 8,
|
||||
"adalora_init_r": 12,
|
||||
"adalora_tinit": 0,
|
||||
"adalora_tfinal": 0,
|
||||
"adalora_deltaT": 1,
|
||||
"adalora_beta1": 0.85,
|
||||
"adalora_beta2": 0.85,
|
||||
"adalora_orth_reg_weight": 0.5,
|
||||
"llamapro_num_new_blocks": 4,
|
||||
"llamapro_num_groups": null,
|
||||
"lisa_activated_layers": 0,
|
||||
"lisa_step_interval": 20,
|
||||
"reft_layer_key": null,
|
||||
"reft_layers": null,
|
||||
"reft_rank": 4,
|
||||
"reft_intervention_type": "LoreftIntervention",
|
||||
"reft_args": null,
|
||||
"swanlab_token": null,
|
||||
"swanlab_project": null,
|
||||
"swanlab_workspace": null,
|
||||
"swanlab_exp_name": null,
|
||||
"swanlab_mode": "cloud",
|
||||
"add_version": true,
|
||||
"resume_only_model": false,
|
||||
"create_checkpoint_symlink": false,
|
||||
"packing": false,
|
||||
"lazy_tokenize": false,
|
||||
"loss_type": null,
|
||||
"optimizer": null,
|
||||
"metric": null,
|
||||
"zero_hpz_partition_size": null,
|
||||
"rank": 0,
|
||||
"global_world_size": 4,
|
||||
"local_world_size": 4,
|
||||
"model_suffix": "Qwen2.5-14B",
|
||||
"model_info": "ModelInfo(model_type='qwen2_5', model_dir='/data/yubo/models/Qwen2.5-14B', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
|
||||
"model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-ILine truncated
|
||||
"model_dir": "/data/yubo/models/Qwen2.5-14B",
|
||||
"hub": "<class 'swift.hub.hub.HFHub'>",
|
||||
"evaluation_strategy": "steps",
|
||||
"training_args": "Seq2SeqTrainingArguments(output_dir='/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=128, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.05, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=200.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=10, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=10, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/data/yubo/CriticCoT/ms-swift/output_models_dsr_14b_0518_p0/v0-20250519-005653', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, tp_size=0, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=[], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None,Line truncated
|
||||
}
|
||||
+29
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 48,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 131072,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.3",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"max_new_tokens": 8192,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
+151388
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2a9fc09e7ce70fe504ccd141c71897665ed05e14e054e89c283e4fd9e87011ca
|
||||
size 4986211280
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0b72d7319d3cd05ee3f00b8893351706e7269f418c757fbb26874630b05be857
|
||||
size 4954847344
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:239abc1ee1fc6ce4f14f1d91b377f1837a1842329315508e6e275985a6206b20
|
||||
size 4954847392
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b8d79837250b6e3f62857643404004d1d5235187a38cf5018d2dbf6c0dc35201
|
||||
size 4954847392
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c614d377a93ad4ecff488334bf6f463a31d26bbab982b88cb3e6df398a26dba
|
||||
size 4954847392
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d89a206612ecba703945f3aba80d54fd5d34ec3959c39f79357e212053651108
|
||||
size 4734533160
|
||||
@@ -0,0 +1,586 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 29540067328
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
LFS
BIN
Binary file not shown.
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
@@ -0,0 +1,634 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 59.7710843373494,
|
||||
"eval_steps": 10,
|
||||
"global_step": 60,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.7710843373493976,
|
||||
"grad_norm": 3.914616675051536,
|
||||
"learning_rate": 5.000000000000001e-07,
|
||||
"loss": 0.6485056281089783,
|
||||
"memory(GiB)": 76.1,
|
||||
"step": 1,
|
||||
"token_acc": 0.8288129939443704,
|
||||
"train_speed(iter/s)": 0.00248
|
||||
},
|
||||
{
|
||||
"epoch": 1.7710843373493976,
|
||||
"grad_norm": 7.135952401058273,
|
||||
"learning_rate": 1.0000000000000002e-06,
|
||||
"loss": 1.306803822517395,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 2,
|
||||
"token_acc": 0.8355539032171605,
|
||||
"train_speed(iter/s)": 0.002291
|
||||
},
|
||||
{
|
||||
"epoch": 2.7710843373493974,
|
||||
"grad_norm": 7.25317611851469,
|
||||
"learning_rate": 1.5e-06,
|
||||
"loss": 1.2851154804229736,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 3,
|
||||
"token_acc": 0.834915035973237,
|
||||
"train_speed(iter/s)": 0.002247
|
||||
},
|
||||
{
|
||||
"epoch": 3.7710843373493974,
|
||||
"grad_norm": 6.865015999508222,
|
||||
"learning_rate": 2.0000000000000003e-06,
|
||||
"loss": 1.290574073791504,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 4,
|
||||
"token_acc": 0.8338767344065504,
|
||||
"train_speed(iter/s)": 0.002214
|
||||
},
|
||||
{
|
||||
"epoch": 4.771084337349397,
|
||||
"grad_norm": 6.57767604145361,
|
||||
"learning_rate": 2.5e-06,
|
||||
"loss": 1.261496901512146,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 5,
|
||||
"token_acc": 0.8348027461456405,
|
||||
"train_speed(iter/s)": 0.0022
|
||||
},
|
||||
{
|
||||
"epoch": 5.771084337349397,
|
||||
"grad_norm": 5.131561904948073,
|
||||
"learning_rate": 3e-06,
|
||||
"loss": 1.20093834400177,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 6,
|
||||
"token_acc": 0.8447540089861448,
|
||||
"train_speed(iter/s)": 0.002191
|
||||
},
|
||||
{
|
||||
"epoch": 6.771084337349397,
|
||||
"grad_norm": 4.169361922366313,
|
||||
"learning_rate": 3.5e-06,
|
||||
"loss": 1.118795394897461,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 7,
|
||||
"token_acc": 0.845426595733518,
|
||||
"train_speed(iter/s)": 0.002187
|
||||
},
|
||||
{
|
||||
"epoch": 7.771084337349397,
|
||||
"grad_norm": 4.513043229540615,
|
||||
"learning_rate": 4.000000000000001e-06,
|
||||
"loss": 1.0338046550750732,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 8,
|
||||
"token_acc": 0.8524168712340995,
|
||||
"train_speed(iter/s)": 0.00218
|
||||
},
|
||||
{
|
||||
"epoch": 8.771084337349398,
|
||||
"grad_norm": 5.185455486257246,
|
||||
"learning_rate": 4.5e-06,
|
||||
"loss": 0.9289287328720093,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 9,
|
||||
"token_acc": 0.8699944903581267,
|
||||
"train_speed(iter/s)": 0.002177
|
||||
},
|
||||
{
|
||||
"epoch": 9.771084337349398,
|
||||
"grad_norm": 3.6878315103563324,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 0.9007519483566284,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 10,
|
||||
"token_acc": 0.8636064441638881,
|
||||
"train_speed(iter/s)": 0.002176
|
||||
},
|
||||
{
|
||||
"epoch": 10.771084337349398,
|
||||
"grad_norm": 3.153907065444448,
|
||||
"learning_rate": 4.999658262481173e-06,
|
||||
"loss": 0.8321974277496338,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 11,
|
||||
"token_acc": 0.8710321094284695,
|
||||
"train_speed(iter/s)": 0.002152
|
||||
},
|
||||
{
|
||||
"epoch": 11.771084337349398,
|
||||
"grad_norm": 2.203676742176422,
|
||||
"learning_rate": 4.998633143352315e-06,
|
||||
"loss": 0.7872496247291565,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 12,
|
||||
"token_acc": 0.8761502671032225,
|
||||
"train_speed(iter/s)": 0.002149
|
||||
},
|
||||
{
|
||||
"epoch": 12.771084337349398,
|
||||
"grad_norm": 2.4327146254784084,
|
||||
"learning_rate": 4.9969249228707625e-06,
|
||||
"loss": 0.7419657707214355,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 13,
|
||||
"token_acc": 0.8786807478287534,
|
||||
"train_speed(iter/s)": 0.002148
|
||||
},
|
||||
{
|
||||
"epoch": 13.771084337349398,
|
||||
"grad_norm": 1.8937402046126173,
|
||||
"learning_rate": 4.994534068046936e-06,
|
||||
"loss": 0.709729790687561,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 14,
|
||||
"token_acc": 0.8879921788137868,
|
||||
"train_speed(iter/s)": 0.002151
|
||||
},
|
||||
{
|
||||
"epoch": 14.771084337349398,
|
||||
"grad_norm": 1.4897225411877277,
|
||||
"learning_rate": 4.991461232516675e-06,
|
||||
"loss": 0.676007866859436,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 15,
|
||||
"token_acc": 0.8962045012503473,
|
||||
"train_speed(iter/s)": 0.00215
|
||||
},
|
||||
{
|
||||
"epoch": 15.771084337349398,
|
||||
"grad_norm": 1.297539359495755,
|
||||
"learning_rate": 4.987707256362529e-06,
|
||||
"loss": 0.6474949717521667,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 16,
|
||||
"token_acc": 0.8947659474239368,
|
||||
"train_speed(iter/s)": 0.002148
|
||||
},
|
||||
{
|
||||
"epoch": 16.771084337349397,
|
||||
"grad_norm": 0.7199351026372981,
|
||||
"learning_rate": 4.983273165884096e-06,
|
||||
"loss": 0.6222354173660278,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 17,
|
||||
"token_acc": 0.9017643862580863,
|
||||
"train_speed(iter/s)": 0.00215
|
||||
},
|
||||
{
|
||||
"epoch": 17.771084337349397,
|
||||
"grad_norm": 1.4007282443863567,
|
||||
"learning_rate": 4.978160173317439e-06,
|
||||
"loss": 0.6050044298171997,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 18,
|
||||
"token_acc": 0.899228721854176,
|
||||
"train_speed(iter/s)": 0.00215
|
||||
},
|
||||
{
|
||||
"epoch": 18.771084337349397,
|
||||
"grad_norm": 1.4351431315774181,
|
||||
"learning_rate": 4.972369676503672e-06,
|
||||
"loss": 0.5903453230857849,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 19,
|
||||
"token_acc": 0.9062169786627631,
|
||||
"train_speed(iter/s)": 0.002149
|
||||
},
|
||||
{
|
||||
"epoch": 19.771084337349397,
|
||||
"grad_norm": 1.1929137455373535,
|
||||
"learning_rate": 4.965903258506806e-06,
|
||||
"loss": 0.5688210725784302,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 20,
|
||||
"token_acc": 0.9079767112253118,
|
||||
"train_speed(iter/s)": 0.002148
|
||||
},
|
||||
{
|
||||
"epoch": 20.771084337349397,
|
||||
"grad_norm": 1.1732494606890316,
|
||||
"learning_rate": 4.9587626871809564e-06,
|
||||
"loss": 0.543393611907959,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 21,
|
||||
"token_acc": 0.9126149389091825,
|
||||
"train_speed(iter/s)": 0.002136
|
||||
},
|
||||
{
|
||||
"epoch": 21.771084337349397,
|
||||
"grad_norm": 1.0573555070054292,
|
||||
"learning_rate": 4.950949914687024e-06,
|
||||
"loss": 0.5107942223548889,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 22,
|
||||
"token_acc": 0.913213028660819,
|
||||
"train_speed(iter/s)": 0.002136
|
||||
},
|
||||
{
|
||||
"epoch": 22.771084337349397,
|
||||
"grad_norm": 0.9119223186948517,
|
||||
"learning_rate": 4.942467076958999e-06,
|
||||
"loss": 0.48675835132598877,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 23,
|
||||
"token_acc": 0.916867432182973,
|
||||
"train_speed(iter/s)": 0.002137
|
||||
},
|
||||
{
|
||||
"epoch": 23.771084337349397,
|
||||
"grad_norm": 1.0782070696527255,
|
||||
"learning_rate": 4.933316493120015e-06,
|
||||
"loss": 0.5053229331970215,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 24,
|
||||
"token_acc": 0.9218187118672303,
|
||||
"train_speed(iter/s)": 0.002139
|
||||
},
|
||||
{
|
||||
"epoch": 24.771084337349397,
|
||||
"grad_norm": 0.9655818937470999,
|
||||
"learning_rate": 4.923500664848327e-06,
|
||||
"loss": 0.5017877817153931,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 25,
|
||||
"token_acc": 0.9221839217084671,
|
||||
"train_speed(iter/s)": 0.002138
|
||||
},
|
||||
{
|
||||
"epoch": 25.771084337349397,
|
||||
"grad_norm": 0.9404583758277602,
|
||||
"learning_rate": 4.913022275693372e-06,
|
||||
"loss": 0.4680900275707245,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 26,
|
||||
"token_acc": 0.9232181127591402,
|
||||
"train_speed(iter/s)": 0.002139
|
||||
},
|
||||
{
|
||||
"epoch": 26.771084337349397,
|
||||
"grad_norm": 0.9566563796831183,
|
||||
"learning_rate": 4.901884190342121e-06,
|
||||
"loss": 0.4565889239311218,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 27,
|
||||
"token_acc": 0.9250697693507346,
|
||||
"train_speed(iter/s)": 0.002138
|
||||
},
|
||||
{
|
||||
"epoch": 27.771084337349397,
|
||||
"grad_norm": 0.7703532186007063,
|
||||
"learning_rate": 4.890089453835894e-06,
|
||||
"loss": 0.43708479404449463,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 28,
|
||||
"token_acc": 0.9259928949775574,
|
||||
"train_speed(iter/s)": 0.002139
|
||||
},
|
||||
{
|
||||
"epoch": 28.771084337349397,
|
||||
"grad_norm": 0.9233409831228016,
|
||||
"learning_rate": 4.8776412907378845e-06,
|
||||
"loss": 0.4270290732383728,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 29,
|
||||
"token_acc": 0.9246415671992716,
|
||||
"train_speed(iter/s)": 0.00214
|
||||
},
|
||||
{
|
||||
"epoch": 29.771084337349397,
|
||||
"grad_norm": 0.9965352268428146,
|
||||
"learning_rate": 4.864543104251587e-06,
|
||||
"loss": 0.41402751207351685,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 30,
|
||||
"token_acc": 0.9240786009778112,
|
||||
"train_speed(iter/s)": 0.002139
|
||||
},
|
||||
{
|
||||
"epoch": 30.771084337349397,
|
||||
"grad_norm": 0.9358295902337755,
|
||||
"learning_rate": 4.850798475290403e-06,
|
||||
"loss": 0.39457955956459045,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 31,
|
||||
"token_acc": 0.9368182401505754,
|
||||
"train_speed(iter/s)": 0.002131
|
||||
},
|
||||
{
|
||||
"epoch": 31.771084337349397,
|
||||
"grad_norm": 0.9813539670443086,
|
||||
"learning_rate": 4.836411161498653e-06,
|
||||
"loss": 0.38136690855026245,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 32,
|
||||
"token_acc": 0.9375963637091769,
|
||||
"train_speed(iter/s)": 0.002133
|
||||
},
|
||||
{
|
||||
"epoch": 32.7710843373494,
|
||||
"grad_norm": 0.4679577449591144,
|
||||
"learning_rate": 4.821385096224268e-06,
|
||||
"loss": 0.36845850944519043,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 33,
|
||||
"token_acc": 0.9348571791559913,
|
||||
"train_speed(iter/s)": 0.002134
|
||||
},
|
||||
{
|
||||
"epoch": 33.7710843373494,
|
||||
"grad_norm": 0.9212511288160155,
|
||||
"learning_rate": 4.8057243874434625e-06,
|
||||
"loss": 0.35925933718681335,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 34,
|
||||
"token_acc": 0.9376081366560561,
|
||||
"train_speed(iter/s)": 0.002133
|
||||
},
|
||||
{
|
||||
"epoch": 34.7710843373494,
|
||||
"grad_norm": 1.0561026403132139,
|
||||
"learning_rate": 4.789433316637644e-06,
|
||||
"loss": 0.3401709794998169,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 35,
|
||||
"token_acc": 0.9403078788403664,
|
||||
"train_speed(iter/s)": 0.002134
|
||||
},
|
||||
{
|
||||
"epoch": 35.7710843373494,
|
||||
"grad_norm": 0.936417548403036,
|
||||
"learning_rate": 4.772516337622907e-06,
|
||||
"loss": 0.3241081237792969,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 36,
|
||||
"token_acc": 0.9484973388290848,
|
||||
"train_speed(iter/s)": 0.002135
|
||||
},
|
||||
{
|
||||
"epoch": 36.7710843373494,
|
||||
"grad_norm": 1.116983283196546,
|
||||
"learning_rate": 4.754978075332398e-06,
|
||||
"loss": 0.30902814865112305,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 37,
|
||||
"token_acc": 0.9476456995060315,
|
||||
"train_speed(iter/s)": 0.002135
|
||||
},
|
||||
{
|
||||
"epoch": 37.7710843373494,
|
||||
"grad_norm": 0.9993160029154087,
|
||||
"learning_rate": 4.736823324551909e-06,
|
||||
"loss": 0.308858722448349,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 38,
|
||||
"token_acc": 0.9504927069901695,
|
||||
"train_speed(iter/s)": 0.002135
|
||||
},
|
||||
{
|
||||
"epoch": 38.7710843373494,
|
||||
"grad_norm": 0.9122824683879396,
|
||||
"learning_rate": 4.71805704860903e-06,
|
||||
"loss": 0.27843528985977173,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 39,
|
||||
"token_acc": 0.9496681563352376,
|
||||
"train_speed(iter/s)": 0.002136
|
||||
},
|
||||
{
|
||||
"epoch": 39.7710843373494,
|
||||
"grad_norm": 1.009388916794573,
|
||||
"learning_rate": 4.698684378016223e-06,
|
||||
"loss": 0.25660544633865356,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 40,
|
||||
"token_acc": 0.9552901130798869,
|
||||
"train_speed(iter/s)": 0.002137
|
||||
},
|
||||
{
|
||||
"epoch": 40.7710843373494,
|
||||
"grad_norm": 1.1895642620511482,
|
||||
"learning_rate": 4.678710609068193e-06,
|
||||
"loss": 0.2424250692129135,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 41,
|
||||
"token_acc": 0.9549429605785101,
|
||||
"train_speed(iter/s)": 0.002131
|
||||
},
|
||||
{
|
||||
"epoch": 41.7710843373494,
|
||||
"grad_norm": 1.1193041843299223,
|
||||
"learning_rate": 4.658141202393935e-06,
|
||||
"loss": 0.23843874037265778,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 42,
|
||||
"token_acc": 0.9608553608553608,
|
||||
"train_speed(iter/s)": 0.002131
|
||||
},
|
||||
{
|
||||
"epoch": 42.7710843373494,
|
||||
"grad_norm": 1.110610217839956,
|
||||
"learning_rate": 4.636981781463848e-06,
|
||||
"loss": 0.210187166929245,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 43,
|
||||
"token_acc": 0.9653150186596419,
|
||||
"train_speed(iter/s)": 0.002132
|
||||
},
|
||||
{
|
||||
"epoch": 43.7710843373494,
|
||||
"grad_norm": 0.8486274696165886,
|
||||
"learning_rate": 4.615238131052339e-06,
|
||||
"loss": 0.21901345252990723,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 44,
|
||||
"token_acc": 0.9653416261042005,
|
||||
"train_speed(iter/s)": 0.002132
|
||||
},
|
||||
{
|
||||
"epoch": 44.7710843373494,
|
||||
"grad_norm": 1.0423804412798912,
|
||||
"learning_rate": 4.592916195656322e-06,
|
||||
"loss": 0.17482870817184448,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 45,
|
||||
"token_acc": 0.9674520144027672,
|
||||
"train_speed(iter/s)": 0.002133
|
||||
},
|
||||
{
|
||||
"epoch": 45.7710843373494,
|
||||
"grad_norm": 1.2841486053816782,
|
||||
"learning_rate": 4.570022077870051e-06,
|
||||
"loss": 0.18200109899044037,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 46,
|
||||
"token_acc": 0.9708482572798199,
|
||||
"train_speed(iter/s)": 0.002133
|
||||
},
|
||||
{
|
||||
"epoch": 46.7710843373494,
|
||||
"grad_norm": 1.172978940255451,
|
||||
"learning_rate": 4.546562036716732e-06,
|
||||
"loss": 0.15860611200332642,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 47,
|
||||
"token_acc": 0.9780445141443995,
|
||||
"train_speed(iter/s)": 0.002133
|
||||
},
|
||||
{
|
||||
"epoch": 47.7710843373494,
|
||||
"grad_norm": 1.2360197347924713,
|
||||
"learning_rate": 4.522542485937369e-06,
|
||||
"loss": 0.14376184344291687,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 48,
|
||||
"token_acc": 0.9766241102700259,
|
||||
"train_speed(iter/s)": 0.002135
|
||||
},
|
||||
{
|
||||
"epoch": 48.7710843373494,
|
||||
"grad_norm": 0.6385686989268172,
|
||||
"learning_rate": 4.497969992237312e-06,
|
||||
"loss": 0.13206440210342407,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 49,
|
||||
"token_acc": 0.9818039023693685,
|
||||
"train_speed(iter/s)": 0.002135
|
||||
},
|
||||
{
|
||||
"epoch": 49.7710843373494,
|
||||
"grad_norm": 1.2901120485113573,
|
||||
"learning_rate": 4.472851273490985e-06,
|
||||
"loss": 0.11426319181919098,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 50,
|
||||
"token_acc": 0.9836425932423786,
|
||||
"train_speed(iter/s)": 0.002135
|
||||
},
|
||||
{
|
||||
"epoch": 50.7710843373494,
|
||||
"grad_norm": 1.2068228907293697,
|
||||
"learning_rate": 4.4471931969052816e-06,
|
||||
"loss": 0.09582371264696121,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 51,
|
||||
"token_acc": 0.9849937986991469,
|
||||
"train_speed(iter/s)": 0.00213
|
||||
},
|
||||
{
|
||||
"epoch": 51.7710843373494,
|
||||
"grad_norm": 1.1813520357475888,
|
||||
"learning_rate": 4.421002777142148e-06,
|
||||
"loss": 0.09163334965705872,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 52,
|
||||
"token_acc": 0.985701349843115,
|
||||
"train_speed(iter/s)": 0.00213
|
||||
},
|
||||
{
|
||||
"epoch": 52.7710843373494,
|
||||
"grad_norm": 1.1122597460598151,
|
||||
"learning_rate": 4.394287174400838e-06,
|
||||
"loss": 0.08439977467060089,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 53,
|
||||
"token_acc": 0.9878925052136355,
|
||||
"train_speed(iter/s)": 0.00213
|
||||
},
|
||||
{
|
||||
"epoch": 53.7710843373494,
|
||||
"grad_norm": 1.1253515530343927,
|
||||
"learning_rate": 4.3670536924603855e-06,
|
||||
"loss": 0.07314425706863403,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 54,
|
||||
"token_acc": 0.9900777579782926,
|
||||
"train_speed(iter/s)": 0.00213
|
||||
},
|
||||
{
|
||||
"epoch": 54.7710843373494,
|
||||
"grad_norm": 1.1033670330706447,
|
||||
"learning_rate": 4.33930977668283e-06,
|
||||
"loss": 0.06532438099384308,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 55,
|
||||
"token_acc": 0.9898691656771185,
|
||||
"train_speed(iter/s)": 0.00213
|
||||
},
|
||||
{
|
||||
"epoch": 55.7710843373494,
|
||||
"grad_norm": 1.1439476751450148,
|
||||
"learning_rate": 4.311063011977723e-06,
|
||||
"loss": 0.06318923085927963,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 56,
|
||||
"token_acc": 0.9903093019267052,
|
||||
"train_speed(iter/s)": 0.002131
|
||||
},
|
||||
{
|
||||
"epoch": 56.7710843373494,
|
||||
"grad_norm": 1.1421545710607997,
|
||||
"learning_rate": 4.282321120728493e-06,
|
||||
"loss": 0.05167176201939583,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 57,
|
||||
"token_acc": 0.991860976682798,
|
||||
"train_speed(iter/s)": 0.002131
|
||||
},
|
||||
{
|
||||
"epoch": 57.7710843373494,
|
||||
"grad_norm": 1.1132394753881205,
|
||||
"learning_rate": 4.253091960681222e-06,
|
||||
"loss": 0.05162680149078369,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 58,
|
||||
"token_acc": 0.992666204277479,
|
||||
"train_speed(iter/s)": 0.002132
|
||||
},
|
||||
{
|
||||
"epoch": 58.7710843373494,
|
||||
"grad_norm": 1.1383077361483038,
|
||||
"learning_rate": 4.2233835227964145e-06,
|
||||
"loss": 0.044882968068122864,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 59,
|
||||
"token_acc": 0.9941307654265692,
|
||||
"train_speed(iter/s)": 0.002132
|
||||
},
|
||||
{
|
||||
"epoch": 59.7710843373494,
|
||||
"grad_norm": 0.9459729284657843,
|
||||
"learning_rate": 4.1932039290643534e-06,
|
||||
"loss": 0.042324937880039215,
|
||||
"memory(GiB)": 77.59,
|
||||
"step": 60,
|
||||
"token_acc": 0.9941203679909544,
|
||||
"train_speed(iter/s)": 0.002132
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 200,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 200,
|
||||
"save_steps": 10,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 268227602284544.0,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cbf7ae9cf5b581ae3023deb857a83edd937efe7f8fcced10c2df2ac05ce83e86
|
||||
size 8312
|
||||
@@ -0,0 +1 @@
|
||||
{"!":0,"\"":1,"#":2,"$":3,"%":4,"&":5,"'":6,"(":7,")":8,"*":9,"+":10,",":11,"-":12,".":13,"/":14,"0":15,"1":16,"2":17,"3":18,"4":19,"5":20,"6":21,"7":22,"8":23,"9":24,":":25,";":26,"<":27,"=":28,">":29,"?":30,"@":31,"A":32,"B":33,"C":34,"D":35,"E":36,"F":37,"G":38,"H":39,"I":40,"J":41,"K":42,"L":43,"M":44,"N":45,"O":46,"P":47,"Q":48,"R":49,"S":50,"T":51,"U":52,"V":53,"W":54,"X":55,"Y":56,"Z":57,"[":58,"\\":59,"]":60,"^":61,"_":62,"`":63,"a":64,"b":65,"c":66,"d":67,"e":68,"f":69,"g":70,"h":71,"i":72,"j":73,"k":74,"l":75,"m":76,"n":77,"o":78,"p":79,"q":80,"r":81,"s":82,"t":83,"u":84,"v":85,"w":86,"x":87,"y":88,"z":89,"{":90,"|":91,"}":92,"~":93,"¡":94,"¢":95,"£":96,"¤":97,"¥":98,"¦":99,"§":100,"¨":101,"©":102,"ª":103,"«":104,"¬":105,"®":106,"¯":107,"°":108,"±":109,"²":110,"³":111,"´":112,"µ":113,"¶":114,"·":115,"¸":116,"¹":117,"º":118,"»":119,"¼":120,"½":121,"¾":122,"¿":123,"À":124,"Á":125,"Â":126,"Ã":127,"Ä":128,"Å":129,"Æ":130,"Ç":131,"È":132,"É":133,"Ê":134,"Ë":135,"Ì":136,"Í":137,"Î":138,"Ï":139,"Ð":140,"Ñ":141,"Ò":142,"Ó":143,"Ô":144,"Õ":145,"Ö":146,"×":147,"Ø":148,"Ù":149,"Ú":150,"Û":151,"Ü":152,"Ý":153,"Þ":154,"ß":155,"à":156,"á":157,"â":158,"ã":159,"ä":160,"å":161,"æ":162,"ç":163,"è":164,"é":165,"ê":166,"ë":167,"ì":168,"í":169,"î":170,"ï":171,"ð":172,"ñ":173,"ò":174,"ó":175,"ô":176,"õ":177,"ö":178,"÷":179,"ø":180,"ù":181,"ú":182,"û":183,"ü":184,"ý":185,"þ":186,"ÿ":187,"Ā":188,"ā":189,"Ă":190,"ă":191,"Ą":192,"ą":193,"Ć":194,"ć":195,"Ĉ":196,"ĉ":197,"Ċ":198,"ċ":199,"Č":200,"č":201,"Ď":202,"ď":203,"Đ":204,"đ":205,"Ē":206,"ē":207,"Ĕ":208,"ĕ":209,"Ė":210,"ė":211,"Ę":212,"ę":213,"Ě":214,"ě":215,"Ĝ":216,"ĝ":217,"Ğ":218,"ğ":219,"Ġ":220,"ġ":221,"Ģ":222,"ģ":223,"Ĥ":224,"ĥ":225,"Ħ":226,"ħ":227,"Ĩ":228,"ĩ":229,"Ī":230,"ī":231,"Ĭ":232,"ĭ":233,"Į":234,"į":235,"İ":236,"ı":237,"IJ":238,"ij":239,"Ĵ":240,"ĵ":241,"Ķ":242,"ķ":243,"ĸ":244,"Ĺ":245,"ĺ":246,"Ļ":247,"ļ":248,"Ľ":249,"ľ":250,"Ŀ":251,"ŀ":252,"Ł":253,"ł":254,"Ń":255,"ĠĠ":256,"ĠĠĠĠ":257,"in":258,"Ġt":259,"ĠĠĠĠĠĠĠĠ":260,"er":261,"ĠĠĠ":262,"on":263,"Ġa":264,"re":265,"at":266,"st":267,"en":268,"or":269,"Ġth":270,"ĊĊ":271,"Ġc":272,"le":273,"Ġs":274,"it":275,"an":276,"ar":277,"al":278,"Ġthe":279,";Ċ":280,"Ġp":281,"Ġf":282,"ou":283,"Ġ=":284,"is":285,"ĠĠĠĠĠĠĠ":286,"ing":287,"es":288,"Ġw":289,"ion":290,"ed":291,"ic":292,"Ġb":293,"Ġd":294,"et":295,"Ġm":296,"Ġo":297,"ĉĉ":298,"ro":299,"as":300,"el":301,"ct":302,"nd":303,"Ġin":304,"Ġh":305,"ent":306,"id":307,"Ġn":308,"am":309,"ĠĠĠĠĠĠĠĠĠĠĠ":310,"Ġto":311,"Ġre":312,"--":313,"Ġ{":314,"Ġof":315,"om":316,");Ċ":317,"im":318,"čĊ":319,"Ġ(":320,"il":321,"//":322,"Ġand":323,"ur":324,"se":325,"Ġl":326,"ex":327,"ĠS":328,"ad":329,"Ġ\"":330,"ch":331,"ut":332,"if":333,"**":334,"Ġ}":335,"em":336,"ol":337,"ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ":338,"th":339,")Ċ":340,"Ġ{Ċ":341,"Ġg":342,"ig":343,"iv":344,",Ċ":345,"ce":346,"od":347,"Ġv":348,"ate":349,"ĠT":350,"ag":351,"ay":352,"Ġ*":353,"ot":354,"us":355,"ĠC":356,"Ġst":357,"ĠI":358,"un":359,"ul":360,"ue":361,"ĠA":362,"ow":363,"Ġ'":364,"ew":365,"Ġ<":366,"ation":367,"()":368,"Ġfor":369,"ab":370,"ort":371,"um":372,"ame":373,"Ġis":374,"pe":375,"tr":376,"ck":377,"âĢ":378,"Ġy":379,"ist":380,"----":381,".ĊĊ":382,"he":383,"Ġe":384,"lo":385,"ĠM":386,"Ġbe":387,"ers":388,"Ġon":389,"Ġcon":390,"ap":391,"ub":392,"ĠP":393,"ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ":394,"ass":395,"int":396,">Ċ":397,"ly":398,"urn":399,"Ġ$":400,";ĊĊ":401,"av":402,"port":403,"ir":404,"->":405,"nt":406,"ction":407,"end":408,"Ġde":409,"ith":410,"out":411,"turn":412,"our":413,"ĠĠĠĠĠ":414,"lic":415,"res":416,"pt":417,"==":418,"Ġthis":419,"Ġwh":420,"Ġif":421,"ĠD":422,"ver":423,"age":424,"ĠB":425,"ht":426,"ext":427,"=\"":428,"Ġthat":429,"****":430,"ĠR":431,"Ġit":432,"ess":433,"ĠF":434,"Ġr":435,"os":436,"and":437,"Ġas":438,"ect":439,"ke":440,"rom":441,"Ġ//":442,"con":443,"ĠL":444,"(\"":445,"qu":446,"lass":447,"Ġwith":448,"iz":449,"de":450,"ĠN":451,"Ġal":452,"op":453,"up":454,"get":455,"Ġ}Ċ":456,"ile":457,"Ġan":458,"ata":459,"ore":460,"ri":461,"Ġpro":462,";čĊ":463,"ĉĉĉĉ":464,"ter":465,"ain":466,"ĠW":467,"ĠE":468,"Ġcom":469,"Ġreturn":470,"art":471,"ĠH":472,"ack":473,"import":474,"ublic":475,"Ġor":476,"est":477,"ment":478,"ĠG":479,"able":480,"Ġ-":481,"ine":482,"ill":483,"ind":484,"ere":485,"::":486,"ity":487,"Ġ+":488,"Ġtr":489,"elf":490,"ight":491,"('":492,"orm":493,"ult":494,"str":495,"..":496,"\",":497,"Ġyou":498,"ype":499,"pl":500,"Ġnew":501,"Ġj":502,"ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ":503,"Ġfrom":504,"Ġex":505,"ĠO":506,"ld":507,"Ġ[":508,"oc":509,":Ċ":510,"Ġse":511,"Ġle":512,"--------":513,".s":514,"{Ċ":515,"',":516,"ant":517,"Ġat":518,"ase":519,".c":520,"Ġch":521,"</":522,"ave":523,"ang":524,"Ġare":525,"Ġint":526,"âĢĻ":527,"_t":528,"Line truncated
|
||||
Reference in new issue
Block a user