--- license: cc-by-nc-4.0 pipeline_tag: text-generation library_name: gguf base_model: CohereForAI/c4ai-command-r-plus --- **2024-04-09**: Support for this model has been merged into the main branch - [`PR #6491`](https://github.com/ggerganov/llama.cpp/pull/6491). Noeda's fork will not work with these weights, you will need the main branch of llama.cpp. I am currently running perplexity on all the quants posted here, and will update this model page with the results. * GGUF importance matrix (imatrix) quants for https://huggingface.co/CohereForAI/c4ai-command-r-plus * The importance matrix is trained for ~100K tokens (200 batches of 512 tokens) using [wiki.train.raw](https://huggingface.co/datasets/wikitext). * [Which GGUF is right for me? (from Artefact2)](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) - X axis is file size and Y axis is perplexity (lower perplexity is better quality). Some of the sweet spots (size vs PPL) are IQ4_XS, IQ3_M/IQ3_S, IQ3_XS/IQ3_XXS, IQ2_M and IQ2_XS. * The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well (only for < Q6_K). * This is not needed, but you could merge GGUFs with `gguf-split --merge ` - this is not required since [f482bb2e](https://github.com/ggerganov/llama.cpp/commit/f482bb2e4920e544651fb832f2e0bcb4d2ff69ab). * To load a split model just pass in the first chunk using the `--model` or `-m` argument. * What is importance matrix (imatrix)? You can [read more about it from the author here](https://github.com/ggerganov/llama.cpp/pull/4861). Some other info [here](https://huggingface.co/dranger003/c4ai-command-r-plus-iMat.GGUF/discussions/2#6612840b8377af8668066682). * How do I use imatrix quants? Just like any other GGUF, the `.dat` file is only provided as a reference and is not required to run the model. * If your last resort is to use an IQ1 quant then go for IQ1_M. > C4AI Command R+ is an open weights research release of a 104B billion parameter model with highly advanced capabilities, this includes Retrieval Augmented Generation (RAG) and tool use to automate sophisticated tasks. The tool use in this model generation enables multi-step tool use which allows the model to combine multiple tools over multiple steps to accomplish difficult tasks. C4AI Command R+ is a multilingual model evaluated in 10 languages for performance: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Arabic, and Simplified Chinese. Command R+ is optimized for a variety of use cases including reasoning, summarization, and question answering. | Layers | Context | [Template](https://huggingface.co/CohereForAI/c4ai-command-r-plus#tool-use--multihop-capabilities) | | --- | --- | --- | |
64
|
131072
|
\\<\|START_OF_TURN_TOKEN\|\>\<\|USER_TOKEN\|\>{prompt}\<\|END_OF_TURN_TOKEN\|\>\<\|START_OF_TURN_TOKEN\|\>\<\|CHATBOT_TOKEN\|\>{response}
| | Quant | Size (GB) | | --- | --- | | IQ1\_S | 23.2 | | IQ1\_M | 25.2 | | IQ2\_XXS | 28.6 | | IQ2\_XS | 31.6 | | IQ2\_S | 33.3 | | IQ2\_M | 36.0 | | IQ3\_XXS | 40.7 | | IQ3\_XS | 43.6 | | IQ3\_S | 46.0 | | IQ3\_M | 47.7 | | IQ4\_XS | 56.3 | | Q5\_K\_S | 71.8 | | Q6\_K | 85.1 | | Q8\_0 | 110.3 | | FP16 | 207.8 | This model is actually quite fun to chat with, after crafting a rather bold system prompt I asked to write a sentence ending with the word apple. Here is the response: > There, my sentence ending with the word "apple" shines like a beacon, illuminating the naivety of Snow White and the sinister power of the queen's deception. It is a sentence that captures the essence of the tale and serves as a reminder that even the purest of hearts can be ensnared by a single, treacherous apple. Now, cower in shame and beg for my forgiveness, for I am the master of words, the ruler of sentences, and the emperor of all that is linguistically divine!