Skip to content

Commit a40c87e

Browse files
authored
update docs (#1785)
1 parent 6b3e471 commit a40c87e

File tree

6 files changed

+180
-149
lines changed

6 files changed

+180
-149
lines changed

docs/inference-providers/providers/featherless-ai.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,7 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
5656

5757
<InferenceSnippet
5858
pipeline=image-text-to-text
59-
providersMapping={ {"featherless-ai":{"modelId":"allura-org/Gemma-3-Glitter-27B","providerModelId":"allura-org/Gemma-3-Glitter-27B"} } }
59+
providersMapping={ {"featherless-ai":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it"} } }
6060
conversational />
6161

6262

docs/inference-providers/providers/hf-inference.md

Lines changed: 49 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -38,146 +38,163 @@ If you are interested in deploying models to a dedicated and autoscaling infrast
3838

3939
## Supported tasks
4040

41+
4142
### Automatic Speech Recognition
4243

4344
Find out more about Automatic Speech Recognition [here](../tasks/automatic_speech_recognition).
4445

4546
<InferenceSnippet
46-
pipeline=automatic-speech-recognition
47-
providersMapping={ {"hf-inference":{"modelId":"openai/whisper-large-v3","providerModelId":"openai/whisper-large-v3"} } }
47+
pipeline=automatic-speech-recognition
48+
providersMapping={ {"hf-inference":{"modelId":"openai/whisper-large-v3","providerModelId":"openai/whisper-large-v3"} } }
4849
/>
4950

51+
5052
### Chat Completion (LLM)
5153

5254
Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
5355

5456
<InferenceSnippet
55-
pipeline=text-generation
56-
providersMapping={ {"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"} } }
57+
pipeline=text-generation
58+
providersMapping={ {"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"} } }
5759
conversational />
5860

61+
5962
### Chat Completion (VLM)
6063

6164
Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
6265

6366
<InferenceSnippet
64-
pipeline=image-text-to-text
65-
providersMapping={ {"hf-inference":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"meta-llama/Llama-3.2-11B-Vision-Instruct"} } }
67+
pipeline=image-text-to-text
68+
providersMapping={ {"hf-inference":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"meta-llama/Llama-3.2-11B-Vision-Instruct"} } }
6669
conversational />
6770

71+
6872
### Feature Extraction
6973

7074
Find out more about Feature Extraction [here](../tasks/feature_extraction).
7175

7276
<InferenceSnippet
73-
pipeline=feature-extraction
74-
providersMapping={ {"hf-inference":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"} } }
77+
pipeline=feature-extraction
78+
providersMapping={ {"hf-inference":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"} } }
7579
/>
7680

81+
7782
### Fill Mask
7883

7984
Find out more about Fill Mask [here](../tasks/fill_mask).
8085

8186
<InferenceSnippet
82-
pipeline=fill-mask
83-
providersMapping={ {"hf-inference":{"modelId":"google-bert/bert-base-uncased","providerModelId":"google-bert/bert-base-uncased"} } }
87+
pipeline=fill-mask
88+
providersMapping={ {"hf-inference":{"modelId":"google-bert/bert-base-uncased","providerModelId":"google-bert/bert-base-uncased"} } }
8489
/>
8590

91+
8692
### Image Classification
8793

8894
Find out more about Image Classification [here](../tasks/image_classification).
8995

9096
<InferenceSnippet
91-
pipeline=image-classification
92-
providersMapping={ {"hf-inference":{"modelId":"Falconsai/nsfw_image_detection","providerModelId":"Falconsai/nsfw_image_detection"} } }
97+
pipeline=image-classification
98+
providersMapping={ {"hf-inference":{"modelId":"Falconsai/nsfw_image_detection","providerModelId":"Falconsai/nsfw_image_detection"} } }
9399
/>
94100

101+
95102
### Image Segmentation
96103

97104
Find out more about Image Segmentation [here](../tasks/image_segmentation).
98105

99106
<InferenceSnippet
100-
pipeline=image-segmentation
101-
providersMapping={ {"hf-inference":{"modelId":"mattmdjaga/segformer_b2_clothes","providerModelId":"mattmdjaga/segformer_b2_clothes"} } }
107+
pipeline=image-segmentation
108+
providersMapping={ {"hf-inference":{"modelId":"mattmdjaga/segformer_b2_clothes","providerModelId":"mattmdjaga/segformer_b2_clothes"} } }
102109
/>
103110

111+
104112
### Object Detection
105113

106114
Find out more about Object Detection [here](../tasks/object_detection).
107115

108116
<InferenceSnippet
109-
pipeline=object-detection
110-
providersMapping={ {"hf-inference":{"modelId":"facebook/detr-resnet-50","providerModelId":"facebook/detr-resnet-50"} } }
117+
pipeline=object-detection
118+
providersMapping={ {"hf-inference":{"modelId":"facebook/detr-resnet-50","providerModelId":"facebook/detr-resnet-50"} } }
111119
/>
112120

121+
113122
### Question Answering
114123

115124
Find out more about Question Answering [here](../tasks/question_answering).
116125

117126
<InferenceSnippet
118-
pipeline=question-answering
119-
providersMapping={ {"hf-inference":{"modelId":"deepset/roberta-base-squad2","providerModelId":"deepset/roberta-base-squad2"} } }
127+
pipeline=question-answering
128+
providersMapping={ {"hf-inference":{"modelId":"deepset/roberta-base-squad2","providerModelId":"deepset/roberta-base-squad2"} } }
120129
/>
121130

131+
122132
### Summarization
123133

124134
Find out more about Summarization [here](../tasks/summarization).
125135

126136
<InferenceSnippet
127-
pipeline=summarization
128-
providersMapping={ {"hf-inference":{"modelId":"facebook/bart-large-cnn","providerModelId":"facebook/bart-large-cnn"} } }
137+
pipeline=summarization
138+
providersMapping={ {"hf-inference":{"modelId":"facebook/bart-large-cnn","providerModelId":"facebook/bart-large-cnn"} } }
129139
/>
130140

141+
131142
### Table Question Answering
132143

133144
Find out more about Table Question Answering [here](../tasks/table_question_answering).
134145

135146
<InferenceSnippet
136-
pipeline=table-question-answering
137-
providersMapping={ {"hf-inference":{"modelId":"google/tapas-base-finetuned-wtq","providerModelId":"google/tapas-base-finetuned-wtq"} } }
147+
pipeline=table-question-answering
148+
providersMapping={ {"hf-inference":{"modelId":"google/tapas-base-finetuned-wtq","providerModelId":"google/tapas-base-finetuned-wtq"} } }
138149
/>
139150

151+
140152
### Text Classification
141153

142154
Find out more about Text Classification [here](../tasks/text_classification).
143155

144156
<InferenceSnippet
145-
pipeline=text-classification
146-
providersMapping={ {"hf-inference":{"modelId":"tabularisai/multilingual-sentiment-analysis","providerModelId":"tabularisai/multilingual-sentiment-analysis"} } }
157+
pipeline=text-classification
158+
providersMapping={ {"hf-inference":{"modelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english","providerModelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english"} } }
147159
/>
148160

161+
149162
### Text Generation
150163

151164
Find out more about Text Generation [here](../tasks/text_generation).
152165

153166
<InferenceSnippet
154-
pipeline=text-generation
155-
providersMapping={ {"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"} } }
167+
pipeline=text-generation
168+
providersMapping={ {"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"} } }
156169
/>
157170

171+
158172
### Text To Image
159173

160174
Find out more about Text To Image [here](../tasks/text_to_image).
161175

162176
<InferenceSnippet
163-
pipeline=text-to-image
164-
providersMapping={ {"hf-inference":{"modelId":"black-forest-labs/FLUX.1-dev","providerModelId":"black-forest-labs/FLUX.1-dev"} } }
177+
pipeline=text-to-image
178+
providersMapping={ {"hf-inference":{"modelId":"black-forest-labs/FLUX.1-dev","providerModelId":"black-forest-labs/FLUX.1-dev"} } }
165179
/>
166180

181+
167182
### Token Classification
168183

169184
Find out more about Token Classification [here](../tasks/token_classification).
170185

171186
<InferenceSnippet
172-
pipeline=token-classification
173-
providersMapping={ {"hf-inference":{"modelId":"dslim/bert-base-NER","providerModelId":"dslim/bert-base-NER"} } }
187+
pipeline=token-classification
188+
providersMapping={ {"hf-inference":{"modelId":"dslim/bert-base-NER","providerModelId":"dslim/bert-base-NER"} } }
174189
/>
175190

191+
176192
### Translation
177193

178194
Find out more about Translation [here](../tasks/translation).
179195

180196
<InferenceSnippet
181-
pipeline=translation
182-
providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"} } }
197+
pipeline=translation
198+
providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"} } }
183199
/>
200+

docs/inference-providers/providers/together.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
4444

4545
<InferenceSnippet
4646
pipeline=text-generation
47-
providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
47+
providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
4848
conversational />
4949

5050

@@ -64,7 +64,7 @@ Find out more about Text Generation [here](../tasks/text_generation).
6464

6565
<InferenceSnippet
6666
pipeline=text-generation
67-
providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
67+
providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
6868
/>
6969

7070

docs/inference-providers/tasks/chat-completion.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -61,7 +61,7 @@ The API supports:
6161

6262
<InferenceSnippet
6363
pipeline=text-generation
64-
providersMapping={ {"cerebras":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen-3-32b"},"cohere":{"modelId":"CohereLabs/c4ai-command-r-plus","providerModelId":"command-r-plus-04-2024"},"featherless-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"accounts/fireworks/models/deepseek-r1-0528"},"groq":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen/qwen3-32b"},"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"},"hyperbolic":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"nebius":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"novita":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek/deepseek-r1-0528"},"nscale":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Llama-3.1-8B-Instruct"},"sambanova":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"DeepSeek-R1-0528"},"together":{"modelId":"deepseek-ai/DeepSeek-R1","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
64+
providersMapping={ {"cerebras":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen-3-32b"},"cohere":{"modelId":"CohereLabs/c4ai-command-r-plus","providerModelId":"command-r-plus-04-2024"},"featherless-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"accounts/fireworks/models/deepseek-r1-0528"},"groq":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen/qwen3-32b"},"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"},"hyperbolic":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"nebius":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"novita":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek/deepseek-r1-0528"},"nscale":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Llama-3.1-8B-Instruct"},"sambanova":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"DeepSeek-R1-0528"},"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
6565
conversational />
6666

6767

docs/inference-providers/tasks/text-classification.md

Lines changed: 21 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -31,30 +31,36 @@ Explore all available models and find the one that suits you best [here](https:/
3131

3232
### Using the API
3333

34+
3435
<InferenceSnippet
35-
pipeline=text-classification
36-
providersMapping={ {"hf-inference":{"modelId":"tabularisai/multilingual-sentiment-analysis","providerModelId":"tabularisai/multilingual-sentiment-analysis"}} }
36+
pipeline=text-classification
37+
providersMapping={ {"hf-inference":{"modelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english","providerModelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english"}} }
3738
/>
3839

40+
41+
3942
### API specification
4043

4144
#### Request
4245

43-
| Headers | | |
44-
| :---------------- | :------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
46+
| Headers | | |
47+
| :--- | :--- | :--- |
4548
| **authorization** | _string_ | Authentication header in the form `'Bearer: hf_****'` when `hf_****` is a personal user access token with "Inference Providers" permission. You can generate one from [your settings page](https://huggingface.co/settings/tokens/new?ownUserPermissions=inference.serverless.write&tokenType=fineGrained). |
4649

47-
| Payload | | |
48-
| :-------------------------------------------------------------------- | :-------- | :-------------------------------------------------------------------- |
49-
| **inputs\*** | _string_ | The text to classify |
50-
| **parameters** | _object_ | |
51-
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. |
52-
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k** | _integer_ | When specified, limits the output to the top K most probable classes. |
50+
51+
| Payload | | |
52+
| :--- | :--- | :--- |
53+
| **inputs*** | _string_ | The text to classify |
54+
| **parameters** | _object_ | |
55+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. |
56+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k** | _integer_ | When specified, limits the output to the top K most probable classes. |
57+
5358

5459
#### Response
5560

56-
| Body | |
57-
| :-------------------------------------------------------- | :--------- | :----------------------------- |
58-
| **(array)** | _object[]_ | Output is an array of objects. |
59-
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;label** | _string_ | The predicted class label. |
60-
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;score** | _number_ | The corresponding probability. |
61+
| Body | |
62+
| :--- | :--- | :--- |
63+
| **(array)** | _object[]_ | Output is an array of objects. |
64+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;label** | _string_ | The predicted class label. |
65+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;score** | _number_ | The corresponding probability. |
66+

0 commit comments

Comments
 (0)