初始化项目，由ModelHub XC社区提供模型

Model: bartowski/inclusionAI_Ring-mini-2.0-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,74 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+ 
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+inclusionAI_Ring-mini-2.0-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+inclusionAI_Ring-mini-2.0-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,168 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model_relation: quantized
+base_model: inclusionAI/Ring-mini-2.0
+---
+
+## Llamacpp imatrix Quantizations of Ring-mini-2.0 by inclusionAI
+
+Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b6810">b6810</a> for quantization.
+
+Original model: https://huggingface.co/inclusionAI/Ring-mini-2.0
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
+
+Run them in [LM Studio](https://lmstudio.ai/)
+
+Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project
+
+## Prompt format
+
+```
+<role>SYSTEM</role>{system_prompt}<role>HUMAN</role>{prompt}<role>ASSISTANT</role><role>ASSISTANT</role><think>
+```
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Ring-mini-2.0-bf16.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-bf16.gguf) | bf16 | 32.54GB | false | Full BF16 weights. |
+| [Ring-mini-2.0-Q8_0.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q8_0.gguf) | Q8_0 | 17.31GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Ring-mini-2.0-Q6_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q6_K_L.gguf) | Q6_K_L | 13.54GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Ring-mini-2.0-Q6_K.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q6_K.gguf) | Q6_K | 13.39GB | false | Very high quality, near perfect, *recommended*. |
+| [Ring-mini-2.0-Q5_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q5_K_L.gguf) | Q5_K_L | 11.82GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Ring-mini-2.0-Q5_K_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q5_K_M.gguf) | Q5_K_M | 11.62GB | false | High quality, *recommended*. |
+| [Ring-mini-2.0-Q5_K_S.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q5_K_S.gguf) | Q5_K_S | 11.27GB | false | High quality, *recommended*. |
+| [Ring-mini-2.0-Q4_1.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q4_1.gguf) | Q4_1 | 10.28GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Ring-mini-2.0-Q4_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q4_K_L.gguf) | Q4_K_L | 10.18GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Ring-mini-2.0-Q4_K_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q4_K_M.gguf) | Q4_K_M | 9.94GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Ring-mini-2.0-Q4_K_S.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q4_K_S.gguf) | Q4_K_S | 9.60GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Ring-mini-2.0-Q4_0.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q4_0.gguf) | Q4_0 | 9.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Ring-mini-2.0-IQ4_NL.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-IQ4_NL.gguf) | IQ4_NL | 9.30GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Ring-mini-2.0-IQ4_XS.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-IQ4_XS.gguf) | IQ4_XS | 8.80GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Ring-mini-2.0-Q3_K_XL.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q3_K_XL.gguf) | Q3_K_XL | 8.10GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Ring-mini-2.0-Q3_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q3_K_L.gguf) | Q3_K_L | 7.82GB | false | Lower quality but usable, good for low RAM availability. |
+| [Ring-mini-2.0-Q3_K_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q3_K_M.gguf) | Q3_K_M | 7.54GB | false | Low quality. |
+| [Ring-mini-2.0-IQ3_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-IQ3_M.gguf) | IQ3_M | 7.54GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Ring-mini-2.0-Q3_K_S.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q3_K_S.gguf) | Q3_K_S | 7.20GB | false | Low quality, not recommended. |
+| [Ring-mini-2.0-IQ3_XS.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-IQ3_XS.gguf) | IQ3_XS | 6.82GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Ring-mini-2.0-IQ3_XXS.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-IQ3_XXS.gguf) | IQ3_XXS | 6.55GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Ring-mini-2.0-Q2_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q2_K_L.gguf) | Q2_K_L | 6.16GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Ring-mini-2.0-Q2_K.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-Q2_K.gguf) | Q2_K | 5.84GB | false | Very low quality but surprisingly usable. |
+| [Ring-mini-2.0-IQ2_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-IQ2_M.gguf) | IQ2_M | 5.28GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
+| [Ring-mini-2.0-IQ2_S.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-IQ2_S.gguf) | IQ2_S | 4.70GB | false | Low quality, uses SOTA techniques to be usable. |
+| [Ring-mini-2.0-IQ2_XS.gguf](https://huggingface.co/bartowski/inclusionAI_Ring-mini-2.0-GGUF/blob/main/inclusionAI_Ring-mini-2.0-IQ2_XS.gguf) | IQ2_XS | 4.66GB | false | Low quality, uses SOTA techniques to be usable. |
+
+## Embed/output weights
+
+Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
+
+## Downloading using huggingface-cli
+
+<details>
+  <summary>Click to view download instructions</summary>
+
+First, make sure you have hugginface-cli installed:
+
+```
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, you can target the specific file you want:
+
+```
+huggingface-cli download bartowski/inclusionAI_Ring-mini-2.0-GGUF --include "inclusionAI_Ring-mini-2.0-Q4_K_M.gguf" --local-dir ./
+```
+
+If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
+
+```
+huggingface-cli download bartowski/inclusionAI_Ring-mini-2.0-GGUF --include "inclusionAI_Ring-mini-2.0-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (inclusionAI_Ring-mini-2.0-Q8_0) or download them all in place (./)
+
+</details>
+
+## ARM/AVX information
+
+Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
+
+Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
+
+As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
+
+Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
+
+<details>
+  <summary>Click to view Q4_0_X_X information (deprecated</summary>
+
+I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
+
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+
+| model                          |       size |     params | backend    | threads |          test |                  t/s |  % (vs Q4_0)  |
+| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         pp512 |        204.03 ± 1.03 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp1024 |        282.92 ± 0.19 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp2048 |        259.49 ± 0.44 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg128 |         39.12 ± 0.27 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg256 |         39.31 ± 0.69 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg512 |         40.52 ± 0.03 |          100% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         pp512 |        301.02 ± 1.74 |          147% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp1024 |        287.23 ± 0.20 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp2048 |        262.77 ± 1.81 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg128 |         18.80 ± 0.99 |           48% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg256 |         24.46 ± 3.04 |           83% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg512 |         36.32 ± 3.59 |           90% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         pp512 |        271.71 ± 3.53 |          133% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp1024 |       279.86 ± 45.63 |          100% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp2048 |        320.77 ± 5.00 |          124% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg128 |         43.51 ± 0.05 |          111% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg256 |         43.35 ± 0.09 |          110% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg512 |         42.60 ± 0.31 |          105% |
+
+Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
+
+</details>
+
+</details>
+
+## Which file should I choose?
+
+<details>
+  <summary>Click here for details</summary>
+
+A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
+
+The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
+
+If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
+
+If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
+
+Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+
+If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
+
+If you want to get more into the weeds, you can check out this extremely useful feature chart:
+
+[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix)
+
+But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
+
+These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+
+</details>
+
+## Credits
+
+Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
+
+Thank you ZeroWw for the inspiration to experiment with embed/output.
+
+Thank you to LM Studio for sponsoring my work.
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

inclusionAI_Ring-mini-2.0-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28339e4e79d8af899d8595c4e06f1a58f61ff608044eb5345d462bccded1e54f
+size 5282911840

inclusionAI_Ring-mini-2.0-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304f05ed91efa1bc6a30d54452717c8e8f8bfadc51cf00e1d218fcdc39aa39f1
+size 4699182688

inclusionAI_Ring-mini-2.0-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d03e64ad9a5c25f078b9eea1c4db6163605a87a0ab23b54a6870cff4330224d
+size 4656002656

inclusionAI_Ring-mini-2.0-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90812ec49413a645e4d6937b68b8f6c3cfd195c7f7bf895731bee08fab801695
+size 7539611232

inclusionAI_Ring-mini-2.0-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e043e81d85cd8909e037f13bc7c8b35a774441c3ffbeced9fade9fbad9a5955a
+size 6823155296

inclusionAI_Ring-mini-2.0-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230aed67712dd036a420feda1874fcf028d27a27894bdf8117a63c77d38ec9a4
+size 6546536032

inclusionAI_Ring-mini-2.0-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30cef03db1267ef9a67cd29573f46fbf1df562bad22c6ed1dc4ff19c49a820ba
+size 9296426592

inclusionAI_Ring-mini-2.0-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40856a4b488c5e4fa857199e13afd2a03abfde7ba01dcb4e4626b4e764c76a76
+size 8803300960

inclusionAI_Ring-mini-2.0-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccfef42b40110d37a6e26c1ddc1ed56cc4ab4f6ad5be9ced43f210a56678ff2a
+size 5844416096

inclusionAI_Ring-mini-2.0-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:803ac6898f7758f2c30e45c0fa94dc8d780c75053ed3a7cef8909e5f27ed9816
+size 6158784096

inclusionAI_Ring-mini-2.0-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd60f4dbae75bf23bc7db3d160fe963aae18c217b5c3ffc570c138fb58fb28e1
+size 7821284960

inclusionAI_Ring-mini-2.0-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786e888f2fd5f07ddd63ec0498baa6a2d58ccfa5794cbdcb21b3b4c6fc185939
+size 7540921952

inclusionAI_Ring-mini-2.0-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c7fed332f84fdd49b8e7786145121b1de4fb524d23d887940f3b9d96e598c0
+size 7200642656

inclusionAI_Ring-mini-2.0-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fde85339b8c2a70ed46431898a077922b08cc729794bdf71da28d7f2d9ed832
+size 8102958688

inclusionAI_Ring-mini-2.0-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33de5e33fe13ab53d2171688cadbd49c6e0aaa9e47a5ca4bf0ed6aba74ee6296
+size 9437591136

inclusionAI_Ring-mini-2.0-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed74b6458a67bca1608917e837b6894bddea8bddc980d719380f5d7d0b772aa
+size 10277434976

inclusionAI_Ring-mini-2.0-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d6abe673e951ba220ff5fd69655bf3a19a786b4c36613808fff6fb2b2e755a
+size 10180810336

inclusionAI_Ring-mini-2.0-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b09eaf3136e5461865e73b3c157f38d98477e76772ea834eaa08b27c13989f
+size 9941890656

inclusionAI_Ring-mini-2.0-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad12dd3aad0578451b062c4450680fdf4b41912f9cc52ce98fe60eb79728497
+size 9599727200

inclusionAI_Ring-mini-2.0-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:398705a012c1232830fcbdc513ee012d05b9d488ee392e436af86a5f5fcd6255
+size 11818374752

inclusionAI_Ring-mini-2.0-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0815d4412e1a2da8c347f51e4912016e920d4427a81a0682e0125c7156b2c8
+size 11619694176

inclusionAI_Ring-mini-2.0-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a4fe9c09689e5ce3f2b9f35e020934b87576970683c56164e1b0016d1ffe4c
+size 11273107040

inclusionAI_Ring-mini-2.0-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e45a6cc85bb6c6cb009f845d8abcb847e0590bb541156cbce8e860d87c9b1e
+size 13387650656

inclusionAI_Ring-mini-2.0-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60dc87446333413c480490be27e4a6888028f5174dd77776b52b3c93b3bd36b
+size 13543577184

inclusionAI_Ring-mini-2.0-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ee936f3853cf63b9b668485e709ca4cf03bb497ee15a4db0ab7f9f8f59740b
+size 17307653728

inclusionAI_Ring-mini-2.0-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4d01fb5468d4fe2bb6f3a7394793b3e093f66fd6ac211bb48cd09def05c767
+size 32537892160

inclusionAI_Ring-mini-2.0-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2257929b599d1249d98946bba1d423859d752d0d4cf3972dd07fd58f018a143a
+size 90609824