We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 0fc0d5d commit a2ea412Copy full SHA for a2ea412
src/recipe.yaml
@@ -121,6 +121,24 @@
121
extra_labels:
122
openllm_alias: 7b,7b-instruct
123
model_name: mistralai/Mistral-7B-Instruct-v0.1
124
+"capybarahermes-2_5:7b-fp16":
125
+ project: vllm-chat
126
+ service_config:
127
+ name: capybarahermes2_5
128
+ traffic:
129
+ timeout: 300
130
+ resources:
131
+ gpu: 1
132
+ gpu_type: nvidia-tesla-l4
133
+ engine_config:
134
+ model: argilla/CapybaraHermes-2.5-Mistral-7B
135
+ max_model_len: 1024
136
+ enforce_eager: true
137
+ dtype: half
138
+ chat_template: mistral-instruct
139
+ extra_labels:
140
+ openllm_alias: 7b
141
+ model_name: argilla/CapybaraHermes-2.5-Mistral-7B
142
"llama3:8b-instruct-awq-4bit":
143
project: vllm-chat
144
service_config:
0 commit comments