Mistral 7B-class record
Captured configuration records MistralForCausalLM with model type mistral and about 7.24B BF16-class parameters.
Open Source Model Profile · FinancialSupport
saiga-7b
saiga-7b is a 7.24B-parameter Mistral text-generation model from FinancialSupport. Its card records Apache-2.0 licensing and publisher-reported Open LLM Leaderboard scores.
- Publisher
- FinancialSupport
- Task
- text-generation
- Model type
- mistral
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
saiga-7b is published by FinancialSupport as a Mistral text-generation model. The captured configuration identifies MistralForCausalLM and Safetensors metadata reports 7,241,732,096 parameters. Card data records apache-2.0, and the model card relates the name to the Italian open-source fauno, camoscio, and cerbero models.
Recorded capabilities
Apache-2.0 conversational record
Card data records apache-2.0, and hub tags record conversational text-generation with Italian and endpoints-compatible markers.
Publisher-reported leaderboard scores
According to the model card, Open LLM Leaderboard figures are reported with an average of 64.51 across six listed tasks.
Use cases in the source record
- Conversational text-generation work using a documented Apache-2.0 Mistral 7B-class model with Transformers support.
- Score-comparison reading that treats the card's reported leaderboard figures as publisher claims to check against the linked source.
Limitations and unknowns
- No context-window value was extracted from this record.
- Reported benchmark figures are publisher claims from the model card and were not independently verified.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: FinancialSupport/saiga-7b
Captured: Unknown. Processed: 2026-09-07T19:34:30.818956+00:00.
il saiga è uno strano incrocio di antilopi che vive nelle steppe siberiane. Il nome deriva dal fatto che è un parente di fauno/camoscio e un lontano cugino di cerbero (altri modelli open source ita). E' un progetto portato avanti nei weekend con pochi soldi/tempo a disposizione Open LLM Leaderboard Evaluation Results Detailed results can be found here Metric Value Avg. 64.51 AI2 Reasoning Challenge (25-Shot) 63.14 HellaSwag (10-Shot) 83.14 MMLU (5-Shot) 61.66 TruthfulQA (0-shot) 54.99 Winogrande (5-shot) 79.01 GSM8k (5-shot) 45.11
F001F002F003F004F005F006F007F009F010F012F013F014