Merge pull request #241 from stanford-crfm/jonathanxue0/gemini-1.5-fl…

…ash-8b-1

@jonathanxue0 - add gemini-1.5-flash-8b-1

assets/google.yaml

@@ -1879,3 +1879,25 @@
   prohibited_uses: Not specified
   monitoring: Unknown
   feedback: Unknown
+- type: model
+  name: Gemini 1.5 Flash-8B
+  organization: Google DeepMind
+  description: Gemini 1.5 Flash-8B is a lightweight, speed-optimized variant of the Gemini 1.5 Flash model, designed for efficiency and lower latency especially for tasks such as chat, transcription, and long context language translation. The model is production-ready and offers the lowest cost per intelligence of any Gemini model with improved rate limits.
+  created_date: 2024-10-03
+  url: https://developers.googleblog.com/en/gemini-15-flash-8b-is-now-generally-available-for-use/
+  model_card: unknown
+  modality: text; text
+  analysis: The model nearly matches the performance of the Gemini 1.5 Flash model across many benchmarks through developer feedback and testing.
+  size: 8B parameters
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: Model improvement informed by developer feedback and extensive testing.
+  access: open
+  license: unknown
+  intended_uses: Designed for simple, high-volume tasks including multimodal use cases and long-context summarization.
+  prohibited_uses: unknown
+  monitoring: unknown
+  feedback: Encourages developer feedback to inform model improvements and future updates.
+