Preparing for release 1.7.0 (candle update + modernbert).

Cargo.toml

@@ -26,7 +26,7 @@ default-members = [
 resolver = "2"
 
 [workspace.package]
-version = "1.6.1"
+version = "1.7.0"
 edition = "2021"
 authors = ["Olivier Dehaene", "Nicolas Patry", "Alvaro Bartolome"]
 homepage = "https://github.com/huggingface/text-embeddings-inference"

docs/openapi.json

@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "1.6.0"
+    "version": "1.7.0"
   },
   "paths": {
     "/decode": {

docs/source/en/private_models.md

@@ -37,5 +37,5 @@ model=<your private model>
 volume=$PWD/data
 token=<your cli Hugging Face Hub token>
 
-docker run --gpus all -e HF_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.6 --model-id $model
+docker run --gpus all -e HF_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7 --model-id $model
 ```

docs/source/en/quick_tour.md

@@ -33,7 +33,7 @@ Finally, deploy your model. Let's say you want to use `BAAI/bge-large-en-v1.5`.
 model=BAAI/bge-large-en-v1.5
 volume=$PWD/data
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.6 --model-id $model
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7 --model-id $model
 ```
 
 <Tip>
@@ -66,7 +66,7 @@ Let's say you want to use `BAAI/bge-reranker-large`:
 model=BAAI/bge-reranker-large
 volume=$PWD/data
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.6 --model-id $model
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7 --model-id $model
 ```
 
 Once you have deployed a model, you can use the `rerank` endpoint to rank the similarity between a query and a list
@@ -87,7 +87,7 @@ You can also use classic Sequence Classification models like `SamLowe/roberta-ba
 model=SamLowe/roberta-base-go_emotions
 volume=$PWD/data
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.6 --model-id $model
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7 --model-id $model
 ```
 
 Once you have deployed the model you can use the `predict` endpoint to get the emotions most associated with an input:
@@ -139,5 +139,5 @@ git clone https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5
 volume=$PWD
 
 # Mount the models directory inside the container with a volume and set the model ID
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.6 --model-id /data/gte-base-en-v1.5
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7 --model-id /data/gte-base-en-v1.5
 ```

docs/source/en/supported_models.md

@@ -66,13 +66,13 @@ Find the appropriate Docker image for your hardware in the following table:
 
 | Architecture                        | Image                                                                    |
 |-------------------------------------|--------------------------------------------------------------------------|
-| CPU                                 | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6                    |
+| CPU                                 | ghcr.io/huggingface/text-embeddings-inference:cpu-1.7                    |
 | Volta                               | NOT SUPPORTED                                                            |
-| Turing (T4, RTX 2000 series, ...)   | ghcr.io/huggingface/text-embeddings-inference:turing-1.6 (experimental)  |
-| Ampere 80 (A100, A30)               | ghcr.io/huggingface/text-embeddings-inference:1.6                        |
-| Ampere 86 (A10, A40, ...)           | ghcr.io/huggingface/text-embeddings-inference:86-1.6                     |
-| Ada Lovelace (RTX 4000 series, ...) | ghcr.io/huggingface/text-embeddings-inference:89-1.6                     |
-| Hopper (H100)                       | ghcr.io/huggingface/text-embeddings-inference:hopper-1.6 (experimental)  |
+| Turing (T4, RTX 2000 series, ...)   | ghcr.io/huggingface/text-embeddings-inference:turing-1.7 (experimental)  |
+| Ampere 80 (A100, A30)               | ghcr.io/huggingface/text-embeddings-inference:1.7                        |
+| Ampere 86 (A10, A40, ...)           | ghcr.io/huggingface/text-embeddings-inference:86-1.7                     |
+| Ada Lovelace (RTX 4000 series, ...) | ghcr.io/huggingface/text-embeddings-inference:89-1.7                     |
+| Hopper (H100)                       | ghcr.io/huggingface/text-embeddings-inference:hopper-1.7 (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.