deepseek-llm-67b-base

Checkpointdeepseek-ai/deepseek-llm-67b-baseModel card indexedModel card

Support summary

deepseek-llm-67b-base is a checkpoint published by DeepSeek, built on the DeepseekForCausalLM and LlamaForCausalLM architectures. vLLM 0.28.0, the newest indexed vLLM release, documents support. TensorRT-LLM lists its architecture, but not this exact checkpoint.

vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.

Configured context
4,096 tokens
License
deepseek
Hugging Face model card
Publisher
DeepSeek
Task
text generation
License
deepseek
Library
transformers
Architecture
LlamaForCausalLM
Configured context
4,096 tokens
Weight access
Public
Repository created
2023-11-29
Source 1: deepseek-ai/deepseek-llm-67b-base · publisher model cardSource 2: deepseek-ai/deepseek-llm-67b-base · Hugging Face metadataSource 3: deepseek-ai/deepseek-llm-67b-base · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for deepseek-llm-67b-base
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedCheckpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed 0.28.0This release
Features, dependencies and evidence for vLLM 0.28.0
SGLang0.5.19Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedArchitecture listed; exact checkpoint unknownNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1