Hugging Face's logo

sambanovasystems
/
SambaLingo-Russian-Base

Text Generation
Transformers
PyTorch
Russian
English
llama
text-generation-inference
Inference Endpoints
Model card Files Community
2
zolicsaki commited on
Commit
01246e8
·
verified ·
1 Parent(s): 6ee6cf8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -52,7 +52,7 @@ All pre-training is done on the [Cultura-X](https://huggingface.co/datasets/uonl
52
  We extended the vocabulary of the base llama model from 32,000 tokens to 57,000 tokens by adding up to 25,000 non-overlapping tokens from the new language.
53
 
54
  ## Evaluation Results
55
- | | sambanovasystems/SambaLingo-Russian-Base | IlyaGusev/saiga_mistral_7b_merged | ai-forever/rugpt3large_based_on_gpt2 | bigscience/bloom-7b1 | facebook/xglm-7.5B | ai-forever/mGPT-13B |
56
  |------------------------------------------|-----------------------------------|--------------------------------------|----------------------|--------------------|---------------------|--------|
57
  | Holdout Perplexity (Lower is better) | **1.444** | 1.556 | 1.611 | 1.797 | 1.504 | 1.806 |
58
  | FLORES en->ru (8 shot, CHRF) | **0.472** | 0.425 | 0.319 | 0.204 | 0.263 | 0.211 |
 
52
  We extended the vocabulary of the base llama model from 32,000 tokens to 57,000 tokens by adding up to 25,000 non-overlapping tokens from the new language.
53
 
54
  ## Evaluation Results
55
+ | | SambaLingo-Russian-Base | saiga_mistral_7b_merged | rugpt3large_based_on_gpt2 | bloom-7b1 | xglm-7.5B | mGPT-13B |
56
  |------------------------------------------|-----------------------------------|--------------------------------------|----------------------|--------------------|---------------------|--------|
57
  | Holdout Perplexity (Lower is better) | **1.444** | 1.556 | 1.611 | 1.797 | 1.504 | 1.806 |
58
  | FLORES en->ru (8 shot, CHRF) | **0.472** | 0.425 | 0.319 | 0.204 | 0.263 | 0.211 |