legraphista's picture
Upload README.md with huggingface_hub
cad72ef verified
|
raw
history blame
8.55 kB
metadata
base_model: CohereForAI/c4ai-command-r-plus-08-2024
extra_gated_prompt: >-
  By submitting this form, you agree to the [License
  Agreement](https://cohere.com/c4ai-cc-by-nc-license)  and acknowledge that the
  information you provide will be collected, used, and shared in accordance with
  Cohere’s [Privacy Policy]( https://cohere.com/privacy).
inference: false
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ja
  - ko
  - zh
  - ar
library_name: gguf
license: cc-by-nc-4.0
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - quantization
  - imat
  - imatrix
  - static
  - 16bit
  - 8bit
  - 6bit
  - 5bit
  - 4bit
  - 3bit
  - 2bit
  - 1bit

c4ai-command-r-plus-08-2024-IMat-GGUF

Llama.cpp imatrix quantization of CohereForAI/c4ai-command-r-plus-08-2024

Original Model: CohereForAI/c4ai-command-r-plus-08-2024
Original dtype: FP16 (float16)
Quantized by: llama.cpp b3645
IMatrix dataset: here


Files

IMatrix

Status: βœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
c4ai-command-r-plus-08-2024.Q8_0 Q8_0 - ⏳ Processing βšͺ Static -
c4ai-command-r-plus-08-2024.Q6_K/* Q6_K 85.17GB βœ… Available βšͺ Static βœ‚ Yes
c4ai-command-r-plus-08-2024.Q4_K/* Q4_K 62.75GB βœ… Available 🟒 IMatrix βœ‚ Yes
c4ai-command-r-plus-08-2024.Q3_K/* Q3_K 50.98GB βœ… Available 🟒 IMatrix βœ‚ Yes
c4ai-command-r-plus-08-2024.Q2_K.gguf Q2_K 39.50GB βœ… Available 🟒 IMatrix πŸ“¦ No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
c4ai-command-r-plus-08-2024.FP16/* F16 207.64GB βœ… Available βšͺ Static βœ‚ Yes
c4ai-command-r-plus-08-2024.Q8_0 Q8_0 - ⏳ Processing βšͺ Static -
c4ai-command-r-plus-08-2024.Q6_K/* Q6_K 85.17GB βœ… Available βšͺ Static βœ‚ Yes
c4ai-command-r-plus-08-2024.Q5_K/* Q5_K 73.62GB βœ… Available βšͺ Static βœ‚ Yes
c4ai-command-r-plus-08-2024.Q5_K_S/* Q5_K_S 71.80GB βœ… Available βšͺ Static βœ‚ Yes
c4ai-command-r-plus-08-2024.Q4_K/* Q4_K 62.75GB βœ… Available 🟒 IMatrix βœ‚ Yes
c4ai-command-r-plus-08-2024.Q4_K_S Q4_K_S - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ4_NL IQ4_NL - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ4_XS IQ4_XS - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.Q3_K/* Q3_K 50.98GB βœ… Available 🟒 IMatrix βœ‚ Yes
c4ai-command-r-plus-08-2024.Q3_K_L Q3_K_L - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.Q3_K_S Q3_K_S - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ3_M IQ3_M - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ3_S IQ3_S - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ3_XS IQ3_XS - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ3_XXS IQ3_XXS - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.Q2_K.gguf Q2_K 39.50GB βœ… Available 🟒 IMatrix πŸ“¦ No
c4ai-command-r-plus-08-2024.Q2_K_S Q2_K_S - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ2_M IQ2_M - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ2_S IQ2_S - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ2_XS IQ2_XS - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ2_XXS IQ2_XXS - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ1_M IQ1_M - ⏳ Processing 🟒 IMatrix -
c4ai-command-r-plus-08-2024.IQ1_S IQ1_S - ⏳ Processing 🟒 IMatrix -

Downloading using huggingface-cli

If you do not have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Download the specific file you want:

huggingface-cli download legraphista/c4ai-command-r-plus-08-2024-IMat-GGUF --include "c4ai-command-r-plus-08-2024.Q8_0.gguf" --local-dir ./

If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/c4ai-command-r-plus-08-2024-IMat-GGUF --include "c4ai-command-r-plus-08-2024.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Simple chat template

<BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{user_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{assistant_response}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{next_user_prompt}<|END_OF_TURN_TOKEN|>

Chat template with system prompt

<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{system_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{user_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{assistant_response}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{next_user_prompt}<|END_OF_TURN_TOKEN|>

Llama.cpp

llama.cpp/main -m c4ai-command-r-plus-08-2024.Q8_0.gguf --color -i -p "prompt here (according to the chat template)"

FAQ

Why is the IMatrix not applied everywhere?

According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).

How do I merge a split GGUF?

  1. Make sure you have gguf-split available
  2. Locate your GGUF chunks folder (ex: c4ai-command-r-plus-08-2024.Q8_0)
  3. Run gguf-split --merge c4ai-command-r-plus-08-2024.Q8_0/c4ai-command-r-plus-08-2024.Q8_0-00001-of-XXXXX.gguf c4ai-command-r-plus-08-2024.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!