Raghav-Singhal/pretrain-normal-smollm-1p7b-100B-20n-2048sl-960gbsz
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: Raghav-Singhal/pretrain-normal-smollm-1p7b-100B-20n-2048sl-960gbsz
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-08 02:08:12 +08:00
commit fd16c855f6
11 changed files with 294143 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
README.md Normal file
View File

@@ -0,0 +1,21 @@
---
library_name: transformers
pipeline_tag: text-generation
tags:
- llama
- causal-lm
- bfloat16
---
# pretrain-normal-smollm-1p7b-100B-20n-2048sl-960gbsz
Converted Hugging Face base checkpoint from the Model Raising pretraining run.
## Details
- Architecture: `LlamaForCausalLM`
- Base model size: `1.7B`
- Precision on disk: `bfloat16`
- Tokenizer: `HuggingFaceTB/SmolLM2-1.7B-Instruct`
This repo contains the verified Hugging Face export of the final pretraining checkpoint before SFT.