gemma-2b-it_sarvam_ai_dataset

Model overview

gemma-2b-it_sarvam_ai_dataset is published by Siddartha10 as a Gemma text-generation model. Captured metadata reports 2,506,172,416 parameters with GemmaForCausalLM, and card data records other licensing. According to the model card, it was converted to MLX format from google/gemma-2b-it.

Recorded capabilities

Use cases in the source record

• Conversational text generation through the documented mlx-lm load and generate workflow.
• MLX-based experimentation starting from a documented google/gemma-2b-it conversion, consulting the original card for behavior details.

Limitations and unknowns

• No context-window value was extracted from this record.
• No evaluation results were extracted from this record.
• Hub tags reference a sarvamai dataset marker, but the card documents only an MLX conversion, so training use of that dataset is unconfirmed.
• Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: Siddartha10/gemma-2b-it_sarvam_ai_dataset

Captured: Unknown. Processed: 2026-09-07T19:34:37.027856+00:00.

Siddartha10/gemma-2b-it_sarvam_ai_dataset This model was converted to MLX format from google/gemma-2b-it . Refer to the original model card for more details on the model. Use with mlx pip install mlx-lm from mlx_lm import load, generate model, tokenizer = load( "Siddartha10/gemma-2b-it_sarvam_ai_dataset" ) response = generate(model, tokenizer, prompt= "hello" , verbose= True )