Upload bigcode/starcoderbase ctranslate fp16 weights

README.md

@@ -256,13 +256,14 @@ quantized version of [bigcode/starcoderbase](https://huggingface.co/bigcode/star
 ```bash
 pip install hf-hub-ctranslate2>=2.0.8 ctranslate2>=3.14.0
 ```
-Converted on 2023-05-31 using
+Converted on 2023-06-01 using
 ```
 ct2-transformers-converter --model bigcode/starcoderbase --output_dir /home/michael/tmp-ct2fast-starcoderbase --force --copy_files merges.txt tokenizer.json README.md tokenizer_config.json vocab.json generation_config.json special_tokens_map.json .gitattributes --quantization float16 --trust_remote_code
 ```
 
-Checkpoint compatible to [ctranslate2>=3.14.0](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2>=2.0.8](https://github.com/michaelfeil/hf-hub-ctranslate2)
-- `compute_type=int8_float16` for `device="cuda"` 
+Checkpoint compatible to [ctranslate2>=3.14.0](https://github.com/OpenNMT/CTranslate2)
+and [hf-hub-ctranslate2>=2.0.8](https://github.com/michaelfeil/hf-hub-ctranslate2)
+- `compute_type=int8_float16` for `device="cuda"`
 - `compute_type=int8`  for `device="cpu"`
 
 ```python
@@ -273,14 +274,14 @@ model_name = "michaelfeil/ct2fast-starcoderbase"
 # use either TranslatorCT2fromHfHub or GeneratorCT2fromHfHub here, depending on model.
 model = GeneratorCT2fromHfHub(
         # load in int8 on CUDA
-        model_name_or_path=model_name, 
+        model_name_or_path=model_name,
         device="cuda",
         compute_type="int8_float16",
         # tokenizer=AutoTokenizer.from_pretrained("bigcode/starcoderbase")
 )
 outputs = model.generate(
-    text=["How do you call a fast Flan-ingo?", "User: How are you doing? Bot:"],
-    max_length=64, 
+    text=["def fibonnaci(", "User: How are you doing? Bot:"],
+    max_length=64,
     include_prompt_in_result=False
 )
 print(outputs)