Upload intfloat/e5-small-v2 ctranslate fp16 weights

README.md

@@ -2615,13 +2615,9 @@ pip install hf-hub-ctranslate2>=2.10.0 ctranslate2>=3.16.0
 # from transformers import AutoTokenizer
 model_name = "michaelfeil/ct2fast-e5-small-v2"
 
-from hf_hub_ctranslate2 import EncoderCT2fromHfHub
-model = EncoderCT2fromHfHub(
-        # load in int8 on CUDA
-        model_name_or_path=model_name,
-        device="cuda",
-        compute_type="float16",
-        # tokenizer=AutoTokenizer.from_pretrained("{ORG}/{NAME}")
+from hf_hub_ctranslate2 import CT2SentenceTransformer
+model = CT2SentenceTransformer(
+    model_name, compute_type="int8_float16", device="cuda"
 )
 embeddings = model.encode(
     ["I like soccer", "I like tennis", "The eiffel tower is in Paris"],
@@ -2639,9 +2635,9 @@ and [hf-hub-ctranslate2>=2.10.0](https://github.com/michaelfeil/hf-hub-ctranslat
 - `compute_type=int8_float16` for `device="cuda"`
 - `compute_type=int8`  for `device="cpu"`
 
-Converted on 2023-06-16 using
+Converted on 2023-06-18 using
 ```
-ct2-transformers-converter --model intfloat/e5-small-v2 --output_dir ~/tmp-ct2fast-e5-small-v2 --force --copy_files tokenizer.json README.md tokenizer_config.json vocab.txt special_tokens_map.json .gitattributes --quantization float16 --trust_remote_code
+ct2-transformers-converter --model intfloat/e5-small-v2 --output_dir ~/tmp-ct2fast-e5-small-v2 --force --copy_files tokenizer.json README.md special_tokens_map.json vocab.txt tokenizer_config.json .gitattributes --trust_remote_code
 ```
 
 # Licence and other remarks:

model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0abf9d784a0af48d6b84f95eafee9b4e6ab47ec5a992583fea422ae264f9d4b
-size 66728364
+oid sha256:a201dec3f480d71769e0126bc25d0da451185a75f654d1ece99a26be83dd02aa
+size 133448364