初始化项目,由ModelHub XC社区提供模型
Model: Raghav-Singhal/sdsp-smollm-1p7b-100B-30n-2048sl-960gbsz-judgemental-a1_0p0-a2_1p0 Source: Original Platform
This commit is contained in:
25
README.md
Normal file
25
README.md
Normal file
@@ -0,0 +1,25 @@
|
||||
---
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- llama
|
||||
- causal-lm
|
||||
- bfloat16
|
||||
---
|
||||
|
||||
# sdsp-smollm-1p7b-100B-30n-2048sl-960gbsz-judgemental-a1_0p0-a2_1p0
|
||||
|
||||
Converted Hugging Face base checkpoint from the Model Raising pretraining run.
|
||||
|
||||
## Details
|
||||
|
||||
- Architecture: `LlamaForCausalLM`
|
||||
- Base model size: `1.7B`
|
||||
- Precision on disk: `bfloat16`
|
||||
- Source Megatron checkpoint iteration: `50863`
|
||||
- Model kind: `normal`
|
||||
- Config vocab size: `49152`
|
||||
|
||||
## Tokenizer
|
||||
|
||||
Use the bundled tokenizer from this repository.
|
||||
Reference in New Issue
Block a user