Instructions to use Milian/TempSFTPrivate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Milian/TempSFTPrivate with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/root/autodl-tmp/model/qzqwork/TempSFTPrivate") model = PeftModel.from_pretrained(base_model, "Milian/TempSFTPrivate") - Notebooks
- Google Colab
- Kaggle
Download config.json from Milian/TempSFTPrivate: direct link, hf CLI and curl.
- Browser
- Download file 770 Bytes
-
https://huggingface.co/Milian/TempSFTPrivate/resolve/main/config.json
- Command line
-
hf download hf://Milian/TempSFTPrivate/config.json
-
curl -L -o config.json https://huggingface.co/Milian/TempSFTPrivate/resolve/main/config.json
770 Bytes
| { | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 151665, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "unsloth_fixed": true, | |
| "unsloth_version": "2025.3.19", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |