--- library_name: transformers tags: - mistral - quantized - text-generation-inference - roleplay # - rp # - uncensored pipeline_tag: text-generation inference: false # language: # - en # FILL THE INFORMATION: # Reference: Test157t/Copium-Cola-9B # Author: Test157t # Model: Copium-Cola-9B # Llama.cpp version: b2343 --- Uploading... ```python quantization_options = [ "Q4_K_M", "Q4_K_S", "IQ4_NL", "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XS", "IQ3_XXS" ] ```
## GGUF-Imatrix quantizations for [Test157t/Copium-Cola-9B](https://huggingface.co/Test157t/Copium-Cola-9B/). All credits belong to the author. If you liked these, check out the work with [FantasiaFoundry's GGUF-IQ-Imatrix-Quantization-Script](https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script). ## What does "Imatrix" mean? It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006/)
The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance and lead to better quality preservation, especially when the calibration data is diverse.
[[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384/) For --imatrix data, included `imatrix.dat` was used. Using [llama.cpp-b2343](https://github.com/ggerganov/llama.cpp/releases/tag/b2343/): ``` Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants) ``` The new **IQ3_S** quant-option has shown to be better than the old Q3_K_S, so I added that instead of the later. Only supported in `koboldcpp-1.59.1` or higher. If you want any specific quantization to be added, feel free to ask. ## Original model information: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/rEj8wf7Vkq_Lf8H30uE-J.png) This model was merged using the passthrough merge method. ### Models Merged The following models were included in the merge: * [ChaoticNeutrals/Eris_7B](https://huggingface.co/ChaoticNeutrals/Eris_7B) ### Configuration The following YAML configuration was used to produce this model: ```yaml slices: - sources: - model: ChaoticNeutrals/Eris_7B layer_range: [0, 20] - sources: - model: ChaoticNeutrals/Eris_7B layer_range: [12, 32] merge_method: passthrough dtype: float16 ```