mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-12 04:44:52 +00:00
Fixing docs + causal_lm batch_class
.
This commit is contained in:
parent
e2edf2beb2
commit
8ecee7283c
@ -10,6 +10,7 @@ Text Generation Inference enables serving optimized models on specific hardware
|
||||
- [Llama](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
||||
- [Phi 3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
|
||||
- [Gemma](https://huggingface.co/google/gemma-7b)
|
||||
- [PaliGemma](https://huggingface.co/google/paligemma-3b-pt-224)
|
||||
- [Gemma2](https://huggingface.co/google/gemma2-9b)
|
||||
- [Cohere](https://huggingface.co/CohereForAI/c4ai-command-r-plus)
|
||||
- [Dbrx](https://huggingface.co/databricks/dbrx-instruct)
|
||||
|
@ -642,7 +642,7 @@ class CausalLM(Model):
|
||||
|
||||
@property
|
||||
def batch_type(self) -> Type[CausalLMBatch]:
|
||||
return self.batch
|
||||
return self.batch_class
|
||||
|
||||
def forward(
|
||||
self, input_ids, attention_mask, position_ids, past_key_values: Optional = None
|
||||
|
Loading…
Reference in New Issue
Block a user