📄 Llama 3 1 405B Instruct Fp8¶
engines.rits.llama_3_1_405b_instruct_fp8
type: RITSInferenceEngine
model_name: meta-llama/llama-3-1-405b-instruct-fp8
max_tokens: 2048
seed: 42
[source]Read more about catalog usage here.
engines.rits.llama_3_1_405b_instruct_fp8
type: RITSInferenceEngine
model_name: meta-llama/llama-3-1-405b-instruct-fp8
max_tokens: 2048
seed: 42
[source]Read more about catalog usage here.