Upload mosaicml/mpt-7b-chat ctranslate fp16 weights

README.md

@@ -20,14 +20,14 @@ Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on
 
 quantized version of [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat)
 ```bash
-pip install hf-hub-ctranslate2>=2.0.8 
+pip install hf-hub-ctranslate2>=2.0.8 ctranslate2>=3.14.0
 ```
-Converted on 2023-05-30 using
+Converted on 2023-05-31 using
 ```
-ct2-transformers-converter --model mosaicml/mpt-7b-chat --output_dir /home/michael/tmp-ct2fast-mpt-7b-chat --force --copy_files configuration_mpt.py meta_init_context.py tokenizer.json hf_prefixlm_converter.py README.md tokenizer_config.json blocks.py adapt_tokenizer.py attention.py norm.py generation_config.json flash_attn_triton.py special_tokens_map.json param_init_fns.py .gitattributes --quantization float16 --trust_remote_code
+ct2-transformers-converter --model mosaicml/mpt-7b-chat --output_dir /home/michael/tmp-ct2fast-mpt-7b-chat --force --copy_files tokenizer.json README.md tokenizer_config.json generation_config.json special_tokens_map.json .gitattributes --quantization float16 --trust_remote_code
 ```
 
-Checkpoint compatible to [ctranslate2>=3.13.0](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2>=2.0.6](https://github.com/michaelfeil/hf-hub-ctranslate2)
+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"`
 
@@ -46,7 +46,8 @@ model = GeneratorCT2fromHfHub(
 )
 outputs = model.generate(
     text=["How do you call a fast Flan-ingo?", "User: How are you doing? Bot:"],
-    max_length=64
+    max_length=64, 
+    include_prompt_in_result=False
 )
 print(outputs)
 ```