Multilingual generation coverage
According to the model card, the model was trained on 23 languages and evaluated on 10 languages, including English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, and Simplified Chinese.
Open Source Model Profile · CohereLabs
c4ai-command-r-08-2024
c4ai-command-r-08-2024 is a CohereLabs 32B-scale text-generation model. Its card documents 128K context, multilingual RAG citations, and tool-use support.
- Publisher
- CohereLabs
- Task
- text-generation
- Model type
- cohere
- License
- cc-by-nc-4.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
c4ai-command-r-08-2024 is published by CohereLabs as a text-generation model. The captured configuration identifies CohereForCausalLM with Safetensors metadata reporting 32,296,476,672 parameters. According to the model card, it is a 32 billion parameter research release with 128K context, multilingual generation, grounded RAG behavior, and single- and multi-step tool use.
Recorded capabilities
Grounded generation with citations
The card says the model produces responses from supplied document snippets with grounding spans, using accurate or fast citation modes.
Single-step and multi-step tool use
According to the model card, the model supports single-step function calling and multi-step agent cycles of Action, Observation, and Reflection.
128K context and chat template
The card lists 128K context length and documents a Command R chat template with tokenizer rendering for grounded and tool-use prompts.
Use cases in the source record
- Grounded summarization and retrieval-augmented question answering with citation spans from supplied documents.
- Single-step function-calling and multi-step agent workflows that interact with external APIs, databases, or search tools.
- Multilingual reasoning, summarization, and question-answering experiments across the card's 23 documented training languages.
Limitations and unknowns
- No independently extracted benchmark scores were included; benchmark comparisons in the card are publisher claims.
- Provider state is historical snapshot data and should be refreshed before being presented as current availability.
- Capability, language, and tool-use details come from the publisher model card and have not been independently verified by Ethen.
Source and provenance
Source: CohereLabs/c4ai-command-r-08-2024
Captured: Unknown. Processed: 2026-09-07T19:34:29.748176+00:00.
Model Card for C4AI Command R 08-2024 Model Summary Cohere Labs Command R 08-2024 is a research release of a 32 billion parameter highly performant generative model. Command R 08-2024 is a large language model with open weights optimized for a variety of use cases including reasoning, summarization, and question answering. Command R 08-2024 has the capability for multilingual generation, trained on 23 languages and evaluated in 10 languages and highly performant RAG capabilities. Developed by: Cohere and Cohere Labs Point of Contact: Cohere Labs License: CC-BY-NC , requires also adhering to Cohere Lab's Acceptable Use Policy Model:…
F001F002F003F004F005F006F007F008F009F010F011F012F014F015F016F017F018F020F024F025F034F035F037