Text Generation
Transformers
Safetensors
Serbian
English
llama
conversational
text-generation-inference
Inference Endpoints
zolicsaki commited on
Commit
ebd5994
1 Parent(s): 06e9259

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -7
README.md CHANGED
@@ -26,6 +26,7 @@ SambaLingo-Serbian-Chat is a human aligned chat model trained in Serbian and Eng
26
  - **Language(s):** Serbian, English
27
  - **Finetuned from model:** [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf)
28
  - **Try this model:** [SambaLingo-chat-space](https://huggingface.co/spaces/sambanovasystems/SambaLingo-chat-space)
 
29
  - **Blog Post**: [sambalingo-open-source-language-experts](https://sambanova.ai/blog/sambalingo-open-source-language-experts)
30
 
31
  ## Getting Started
@@ -82,6 +83,9 @@ The DPO phase was done on the [ultrafeedback](https://huggingface.co/datasets/Hu
82
  ## Tokenizer Details
83
  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.
84
 
 
 
 
85
  ## Uses
86
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
87
 
@@ -124,12 +128,12 @@ We would like to give a special thanks to the following groups:
124
 
125
  ## Cite SambaLingo
126
  ```
127
- @software{sambalingo,
128
- title = {{SambaLingo: Open Source Language Experts}},
129
- author = {SambaNova Systems},
130
- url = {https://huggingface.co/sambanovasystems/SambaLingo-Serbian-Chat}
131
- month = {2},
132
- year = {2024},
133
- version = {1.0},
134
  }
135
  ```
 
26
  - **Language(s):** Serbian, English
27
  - **Finetuned from model:** [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf)
28
  - **Try this model:** [SambaLingo-chat-space](https://huggingface.co/spaces/sambanovasystems/SambaLingo-chat-space)
29
+ - **Paper:** [SambaLingo: Teaching Large Language Models New Languages](https://arxiv.org/abs/2404.05829)
30
  - **Blog Post**: [sambalingo-open-source-language-experts](https://sambanova.ai/blog/sambalingo-open-source-language-experts)
31
 
32
  ## Getting Started
 
83
  ## Tokenizer Details
84
  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.
85
 
86
+ ## Evaluation
87
+ For evaluation results see our paper: [SambaLingo: Teaching Large Language Models New Languages](https://arxiv.org/abs/2404.05829)
88
+
89
  ## Uses
90
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
91
 
 
128
 
129
  ## Cite SambaLingo
130
  ```
131
+ @misc{csaki2024sambalingo,
132
+ title={SambaLingo: Teaching Large Language Models New Languages},
133
+ author={Zoltan Csaki and Bo Li and Jonathan Li and Qiantong Xu and Pian Pawakapan and Leon Zhang and Yun Du and Hengyu Zhao and Changran Hu and Urmish Thakker},
134
+ year={2024},
135
+ eprint={2404.05829},
136
+ archivePrefix={arXiv},
137
+ primaryClass={cs.CL}
138
  }
139
  ```