v1.4.0

Author: OlivierDehaene

Cargo.lock

@@ -11,7 +11,7 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "1.3.0"
+version = "1.4.0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-embeddings-inference"

Cargo.toml

@@ -104,7 +104,7 @@ model=BAAI/bge-large-en-v1.5
 revision=refs/pr/5
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.3 --model-id $model --revision $revision
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.4 --model-id $model --revision $revision
 ```
 
 And then you can make requests like
@@ -309,13 +309,13 @@ Text Embeddings Inference ships with multiple Docker images that you can use to
 
 | Architecture                        | Image                                                                   |
 |-------------------------------------|-------------------------------------------------------------------------|
-| CPU                                 | ghcr.io/huggingface/text-embeddings-inference:cpu-1.3                   |
+| CPU                                 | ghcr.io/huggingface/text-embeddings-inference:cpu-1.4                   |
 | Volta                               | NOT SUPPORTED                                                           |
-| Turing (T4, RTX 2000 series, ...)   | ghcr.io/huggingface/text-embeddings-inference:turing-1.3 (experimental) |
-| Ampere 80 (A100, A30)               | ghcr.io/huggingface/text-embeddings-inference:1.3                       |
-| Ampere 86 (A10, A40, ...)           | ghcr.io/huggingface/text-embeddings-inference:86-1.3                    |
-| Ada Lovelace (RTX 4000 series, ...) | ghcr.io/huggingface/text-embeddings-inference:89-1.3                    |
-| Hopper (H100)                       | ghcr.io/huggingface/text-embeddings-inference:hopper-1.3 (experimental) |
+| Turing (T4, RTX 2000 series, ...)   | ghcr.io/huggingface/text-embeddings-inference:turing-1.4 (experimental) |
+| Ampere 80 (A100, A30)               | ghcr.io/huggingface/text-embeddings-inference:1.4                       |
+| Ampere 86 (A10, A40, ...)           | ghcr.io/huggingface/text-embeddings-inference:86-1.4                    |
+| Ada Lovelace (RTX 4000 series, ...) | ghcr.io/huggingface/text-embeddings-inference:89-1.4                    |
+| Hopper (H100)                       | ghcr.io/huggingface/text-embeddings-inference:hopper-1.4 (experimental) |
 
 **Warning**: Flash Attention is turned off by default for the Turing image as it suffers from precision issues.
 You can turn Flash Attention v1 ON by using the `USE_FLASH_ATTENTION=True` environment variable.
@@ -344,7 +344,7 @@ model=<your private model>
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 token=<your cli READ token>
 
-docker run --gpus all -e HF_API_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.3 --model-id $model
+docker run --gpus all -e HF_API_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.4 --model-id $model
 ```
 
 ### Using Re-rankers models
@@ -362,7 +362,7 @@ model=BAAI/bge-reranker-large
 revision=refs/pr/4
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.3 --model-id $model --revision $revision
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.4 --model-id $model --revision $revision
 ```
 
 And then you can rank the similarity between a query and a list of texts with:
@@ -382,7 +382,7 @@ You can also use classic Sequence Classification models like `SamLowe/roberta-ba
 model=SamLowe/roberta-base-go_emotions
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.3 --model-id $model
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.4 --model-id $model
 ```
 
 Once you have deployed the model you can use the `predict` endpoint to get the emotions most associated with an input:
@@ -402,7 +402,7 @@ You can choose to activate SPLADE pooling for Bert and Distilbert MaskedLM archi
 model=naver/efficient-splade-VI-BT-large-query
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.3 --model-id $model --pooling splade
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.4 --model-id $model --pooling splade
 ```
 
 Once you have deployed the model you can use the `/embed_sparse` endpoint to get the sparse embedding:
@@ -432,7 +432,7 @@ model=BAAI/bge-large-en-v1.5
 revision=refs/pr/5
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.3-grpc --model-id $model --revision $revision
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.4-grpc --model-id $model --revision $revision
 ```
 
 ```shell

README.md

@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "1.3.0"
+    "version": "1.4.0"
   },
   "paths": {
     "/decode": {

docs/openapi.json

@@ -37,5 +37,5 @@ model=<your private model>
 volume=$PWD/data
 token=<your cli Hugging Face Hub token>
 
-docker run --gpus all -e HF_API_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.3 --model-id $model
+docker run --gpus all -e HF_API_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.4 --model-id $model
 ```