clowman/Llama-3.2-3B-Instruct-GPTQ-Int8
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: clowman/Llama-3.2-3B-Instruct-GPTQ-Int8
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-12 14:31:39 +08:00
commit 0b8046e604
13 changed files with 2876 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
args-lambda-quant.json Normal file
View File

@@ -0,0 +1 @@
{"quantization": "GPTQ-Int8", "model": "meta-llama/Llama-3.2-3B-Instruct", "dataset": "HuggingFaceH4/ultrachat_200k", "dataset_split": "train_sft", "dataset_name": null, "num_samples": 512, "seq_length": 2048, "batch_size": 32, "update_metadata_only": false}