biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Minor documentation fixes (#11580)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-12-28 21:53:59 +08:00
committed by GitHub
parent 42bb201fd6
commit d427e5cfda
13 changed files with 27 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/models/supported_models.md
View File

@@ -435,7 +435,7 @@ despite being described otherwise on its model card.
```
If your model is not in the above list, we will try to automatically convert the model using
:func:`vllm.model_executor.models.adapters.as_embedding_model`. By default, the embeddings
{func}`vllm.model_executor.models.adapters.as_embedding_model`. By default, the embeddings
of the whole prompt are extracted from the normalized hidden state corresponding to the last token.
#### Reward Modeling (`--task reward`)
@@ -468,7 +468,7 @@ of the whole prompt are extracted from the normalized hidden state corresponding
```
If your model is not in the above list, we will try to automatically convert the model using
:func:`vllm.model_executor.models.adapters.as_reward_model`. By default, we return the hidden states of each token directly.
{func}`vllm.model_executor.models.adapters.as_reward_model`. By default, we return the hidden states of each token directly.
```{important}
For process-supervised reward models such as {code}`peiyi9979/math-shepherd-mistral-7b-prm`, the pooling config should be set explicitly,
@@ -500,7 +500,7 @@ e.g.: {code}`--override-pooler-config '{"pooling_type": "STEP", "step_tag_id": 1
```
If your model is not in the above list, we will try to automatically convert the model using
:func:`vllm.model_executor.models.adapters.as_classification_model`. By default, the class probabilities are extracted from the softmaxed hidden state corresponding to the last token.
{func}`vllm.model_executor.models.adapters.as_classification_model`. By default, the class probabilities are extracted from the softmaxed hidden state corresponding to the last token.
#### Sentence Pair Scoring (`--task score`)