TAUR-dev / M-sft_exp_zayne-sft

huggingface.co
Total runs: 1
24-hour runs: 0
7-day runs: 0
30-day runs: 1
Model's Last Updated: September 11 2025

Introduction of M-sft_exp_zayne-sft

Model Details of M-sft_exp_zayne-sft

M-sft_exp_zayne-sft

This model was created as part of the sft_exp_zayne experiment using the SkillFactory experiment management system.

Model Details
  • Training Method : LLaMAFactory SFT (Supervised Fine-Tuning)
  • Stage Name : sft
  • Experiment : sft_exp_zayne
Training Configuration

{"model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct", "trust_remote_code": true, "stage": "sft", "do_train": true, "finetuning_type": "full", "deepspeed": "/scratch/10416/zaynesprague/skill_factory_dir/skill-factory/thirdparty/LLaMA-Factory/examples/deepspeed/ds_z2_config.json", "dataset": "TAUR_dev__D_SFT_C_sft_exp_zayne_sft_data__sft_train", "template": "qwen", "cutoff_len": 16384, "max_samples": 1000000, "overwrite_cache": true, "preprocessing_num_workers": 1, "dataloader_num_workers": 0, "disable_tqdm": false, "output_dir": "/scratch/10416/zaynesprague/skill_inject_outputs/sf_experiments/sft_v2/llamafactory/checkpoints", "logging_steps": 10, "save_steps": 100000, "plot_loss": true, "overwrite_output_dir": true, "per_device_train_batch_size": 1, "gradient_accumulation_steps": 1, "learning_rate": 1e-06, "num_train_epochs": 3, "lr_scheduler_type": "cosine", "warmup_ratio": 0.05, "weight_decay": 0.0001, "adam_beta1": 0.9, "adam_beta2": 0.95, "bf16": true, "ddp_timeout": 180000000, "gradient_checkpointing": true, "save_only_model": true, "enable_masked_ranges": false, "save_strategy": "steps", "save_total_limit": 5, "sf_tracker_dataset_id": "TAUR-dev/D-ExpTracker__sft_exp_zayne__v1", "sf_eval_before_training": false, "sf_wandb_project": "sft_exp_zayne_sft", "sf_eval_steps": null, "run_name": "sft_exp_zayne_sft"}

Experiment Tracking

🔗 View complete experiment details : Experiment Tracker Dataset

Usage
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TAUR-dev/M-sft_exp_zayne-sft")
model = AutoModelForCausalLM.from_pretrained("TAUR-dev/M-sft_exp_zayne-sft")

Runs of TAUR-dev M-sft_exp_zayne-sft on huggingface.co

1
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
1
30-day runs

More Information About M-sft_exp_zayne-sft huggingface.co Model

M-sft_exp_zayne-sft huggingface.co

M-sft_exp_zayne-sft huggingface.co is an AI model on huggingface.co that provides M-sft_exp_zayne-sft's model effect (), which can be used instantly with this TAUR-dev M-sft_exp_zayne-sft model. huggingface.co supports a free trial of the M-sft_exp_zayne-sft model, and also provides paid use of the M-sft_exp_zayne-sft. Support call M-sft_exp_zayne-sft model through api, including Node.js, Python, http.

M-sft_exp_zayne-sft huggingface.co Url

https://huggingface.co/TAUR-dev/M-sft_exp_zayne-sft

TAUR-dev M-sft_exp_zayne-sft online free

M-sft_exp_zayne-sft huggingface.co is an online trial and call api platform, which integrates M-sft_exp_zayne-sft's modeling effects, including api services, and provides a free online trial of M-sft_exp_zayne-sft, you can try M-sft_exp_zayne-sft online for free by clicking the link below.

TAUR-dev M-sft_exp_zayne-sft online free url in huggingface.co:

https://huggingface.co/TAUR-dev/M-sft_exp_zayne-sft

M-sft_exp_zayne-sft install

M-sft_exp_zayne-sft is an open source model from GitHub that offers a free installation service, and any user can find M-sft_exp_zayne-sft on GitHub to install. At the same time, huggingface.co provides the effect of M-sft_exp_zayne-sft install, users can directly use M-sft_exp_zayne-sft installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

M-sft_exp_zayne-sft install url in huggingface.co:

https://huggingface.co/TAUR-dev/M-sft_exp_zayne-sft

Url of M-sft_exp_zayne-sft

M-sft_exp_zayne-sft huggingface.co Url

Provider of M-sft_exp_zayne-sft huggingface.co

TAUR-dev
ORGANIZATIONS

Other API from TAUR-dev

huggingface.co

Total runs: 51
Run Growth: 0
Growth Rate: 0.00%
Updated:June 11 2025