A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 10:45 UTC
[Doc] Update Granite model docs (#9025)
Nick Hill committed
Oct 3, 2024 at 03:42 UTC
18c2e30c5754dc83f86d9b8c75af0499a77e4b3f
1 file changed
+6
-2
docs/source/models/supported_models.rst
+6
-2
@@ -92,8 +92,12 @@ Decoder-only Language Models
92
- :code:`EleutherAI/gpt-neox-20b`, :code:`EleutherAI/pythia-12b`, :code:`OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5`, :code:`databricks/dolly-v2-12b`, :code:`stabilityai/stablelm-tuned-alpha-7b`, etc.
93
-
94
* - :code:`GraniteForCausalLM`
95
- - Granite, Power-LM
96
- - :code:`ibm/granite-7b-base`, :code:`ibm/PowerLM-3b` etc.
95
+ - PowerLM
96
+ - :code:`ibm/PowerLM-3b` etc.
97
+ - ✅︎
98
+ * - :code:`GraniteMoeForCausalLM`
99
+ - PowerMoE
100
+ - :code:`ibm/PowerMoE-3b` etc.
101
- ✅︎
102
* - :code:`InternLMForCausalLM`
103
- InternLM