add tests

src/huggingface_hub/inference/_providers/hyperbolic.py

@@ -18,6 +18,11 @@ def _prepare_payload_as_dict(self, inputs: Any, parameters: Dict, mapped_model:
             parameters["steps"] = parameters.pop("num_inference_steps")
         if "guidance_scale" in parameters:
             parameters["cfg_scale"] = parameters.pop("guidance_scale")
+        # For Hyperbolic, the width and height are required parameters
+        if "width" not in parameters:
+            parameters["width"] = 512
+        if "height" not in parameters:
+            parameters["height"] = 512
         return {"prompt": inputs, "model_name": mapped_model, **parameters}
 
     def get_response(self, response: Union[bytes, Dict]) -> Any:

tests/cassettes/TestInferenceClient.test_chat_completion_no_stream[hyperbolic,conversational].yaml

@@ -0,0 +1,148 @@
+interactions:
+- request:
+    body: null
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      X-Amzn-Trace-Id:
+      - f240d30a-9b93-48f2-a781-80c8e318e585
+    method: GET
+    uri: https://huggingface.co/api/models/meta-llama/Llama-3.2-3B-Instruct?expand=inferenceProviderMapping
+  response:
+    body:
+      string: '{"_id":"66eaef786865fea1324edb5d","id":"meta-llama/Llama-3.2-3B-Instruct","inferenceProviderMapping":{"fireworks-ai":{"status":"staging","providerId":"accounts/fireworks/models/llama-v3p2-3b-instruct","task":"conversational"},"sambanova":{"status":"live","providerId":"Meta-Llama-3.2-3B-Instruct","task":"conversational"},"together":{"status":"live","providerId":"meta-llama/Llama-3.2-3B-Instruct-Turbo","task":"conversational"},"hf-inference":{"status":"live","providerId":"meta-llama/Llama-3.2-3B-Instruct","task":"conversational"},"nebius":{"status":"staging","providerId":"meta-llama/Llama-3.2-3B-Instruct","task":"conversational"},"novita":{"status":"staging","providerId":"meta-llama/llama-3.2-3b-instruct","task":"conversational"},"hyperbolic":{"status":"staging","providerId":"meta-llama/Llama-3.2-3B-Instruct","task":"conversational"}}}'
+    headers:
+      Access-Control-Allow-Origin:
+      - https://huggingface.co
+      Access-Control-Expose-Headers:
+      - X-Repo-Commit,X-Request-Id,X-Error-Code,X-Error-Message,X-Total-Count,ETag,Link,Accept-Ranges,Content-Range,X-Xet-Access-Token,X-Xet-Token-Expiration,X-Xet-Refresh-Route,X-Xet-Cas-Url,X-Xet-Hash
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '845'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Fri, 14 Feb 2025 13:27:49 GMT
+      ETag:
+      - W/"34d-CxprGZuC6rOGzn4LlkoLmsGVV/U"
+      Referrer-Policy:
+      - strict-origin-when-cross-origin
+      Vary:
+      - Origin
+      Via:
+      - 1.1 4a09ca83280b6b5f15a5c3da38e16cc4.cloudfront.net (CloudFront)
+      X-Amz-Cf-Id:
+      - hmvaCatS26JOMGFzzSri3EHEwlqcajSLEyWs_slvzIxugD1miLP5EQ==
+      X-Amz-Cf-Pop:
+      - CDG52-P4
+      X-Cache:
+      - Miss from cloudfront
+      X-Powered-By:
+      - huggingface-moon
+      X-Request-Id:
+      - Root=1-67af44d5-37910ace6d19456d739350ce;f240d30a-9b93-48f2-a781-80c8e318e585
+      cross-origin-opener-policy:
+      - same-origin
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant."},
+      {"role": "user", "content": "What is deep learning?"}], "model": "meta-llama/Llama-3.2-3B-Instruct",
+      "stream": false}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '194'
+      Content-Type:
+      - application/json
+      X-Amzn-Trace-Id:
+      - 0f652278-fd50-4424-a806-1ee795b0a0bb
+    method: POST
+    uri: https://router.huggingface.co/hyperbolic/v1/chat/completions
+  response:
+    body:
+      string: '{"id":"chat-b87e29af773c4d28acd93ab9873bf8fb","object":"chat.completion","created":1739539670,"model":"meta-llama/Llama-3.2-3B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"Deep
+        learning is a subset of machine learning that involves the use of artificial
+        neural networks (ANNs) to analyze and interpret data. It is called \"deep\"
+        learning because these neural networks have multiple layers, similar to the
+        structure of the human brain.\n\nIn traditional machine learning, models are
+        typically trained on a small number of features and use a shallow architecture.
+        In contrast, deep learning models can learn complex patterns and relationships
+        in data by using a large number of layers, each of which performs a specific
+        task, such as:\n\n1. Feature extraction: extracting relevant features from
+        raw data\n2. Transformation: transforming the extracted features into a more
+        suitable format\n3. Classification: classifying the data into different categories\n4.
+        Regression: predicting a continuous value\n\nThe key characteristics of deep
+        learning models are:\n\n1. **Multi-layered architecture**: deep learning models
+        have multiple layers, which allow them to learn complex patterns and relationships
+        in data.\n2. **Large datasets**: deep learning models require large datasets
+        to learn and generalize well.\n3. **Automatic feature learning**: deep learning
+        models can learn features automatically from raw data, eliminating the need
+        for manual feature engineering.\n4. **Non-linear relationships**: deep learning
+        models can learn non-linear relationships between inputs and outputs, which
+        are common in real-world data.\n\nDeep learning models are widely used in
+        many applications, including:\n\n1. **Computer vision**: image recognition,
+        object detection, segmentation, and generation\n2. **Natural language processing**:
+        text classification, sentiment analysis, language translation, and text generation\n3.
+        **Speech recognition**: speech-to-text and text-to-speech synthesis\n4. **Robotics**:
+        motion planning, control, and manipulation\n5. **Healthcare**: disease diagnosis,
+        patient outcomes prediction, and medical image analysis\n\nSome popular deep
+        learning algorithms include:\n\n1. **Convolutional neural networks (CNNs)**:
+        used for image and video analysis\n2. **Recurrent neural networks (RNNs)**:
+        used for sequential data analysis, such as speech and text\n3. **Long short-term
+        memory (LSTM) networks**: a type of RNN used for sequential data analysis\n4.
+        **Generative adversarial networks (GANs)**: used for generating new data samples
+        that resemble existing data\n\nOverall, deep learning has revolutionized the
+        field of machine learning and has many applications in various industries."},"finish_reason":"stop","logprobs":null}],"usage":{"prompt_tokens":46,"total_tokens":523,"completion_tokens":477}}'
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Access-Control-Expose-Headers:
+      - X-Repo-Commit,X-Request-Id,X-Error-Code,X-Error-Message,X-Total-Count,ETag,Link,Accept-Ranges,Content-Range,X-Xet-Access-Token,X-Xet-Token-Expiration,X-Xet-Refresh-Route,X-Xet-Cas-Url,X-Xet-Hash
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 14 Feb 2025 13:27:52 GMT
+      Referrer-Policy:
+      - strict-origin-when-cross-origin
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      Via:
+      - 1.1 4de8cc07f214b77e50bb78828ddb1362.cloudfront.net (CloudFront)
+      X-Amz-Cf-Id:
+      - SfQDgtXFjNo_eDyAx_jvunwoTnlnLAtgSrizQbTT8iVK3Mcrkz8YMw==
+      X-Amz-Cf-Pop:
+      - CDG55-P3
+      X-Cache:
+      - Miss from cloudfront
+      X-Powered-By:
+      - huggingface-moon
+      X-Request-Id:
+      - Root=1-67af44d5-5ac681b23efa303d07c55cc1;0f652278-fd50-4424-a806-1ee795b0a0bb
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - 911d65d73efc2009-IAD
+      cross-origin-opener-policy:
+      - same-origin
+      server:
+      - cloudflare
+    status:
+      code: 200
+      message: OK
+version: 1