初始化项目，由ModelHub XC社区提供模型

Model: bartowski/LiquidAI_LFM2-350M-Math-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,72 @@
+*.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
+
+LiquidAI_LFM2-350M-Math-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Math-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text

LiquidAI_LFM2-350M-Math-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de177c33f2e225152777e107e6e91634937ba166378dbf80d07af95a38d33f7
+size 142877152

LiquidAI_LFM2-350M-Math-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71482d99eb7eef5c65baf47f4f258299ed68a2fb32159a9d48c336ca950c103e
+size 183656928

LiquidAI_LFM2-350M-Math-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f62eabb83d12e2e35341b4e1220125218b8c5f7e237a43feca17953615bca4
+size 175399392

LiquidAI_LFM2-350M-Math-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4fd70a5ab37ea1c53280e876233b4e62d97f5b1c38f7f99b1f456bb53f8629
+size 158474720

LiquidAI_LFM2-350M-Math-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81c45b60a14b8e9d48d8259a7ff6bce27f20e5eb8a9e105aa1b420d2fa8d7ec
+size 219308512

LiquidAI_LFM2-350M-Math-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec53b7bfcac1c0ea5a336efc963f5be002696000d716acc3b401659aa8f91afc
+size 210330080

LiquidAI_LFM2-350M-Math-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0eb7cfa7428738fd6560a38aeff67f3152d3ea0aee1ebec72445a777249fbd5
+size 160596448

LiquidAI_LFM2-350M-Math-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2031ea1412b801b9fcdff3e2b39d473a9b47de58a2bcaec8eaf7453767a0ea95
+size 176849376

LiquidAI_LFM2-350M-Math-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159967a808dc3e338dabe47d0d47fa0a81c9988dc007fde80ca3dc3971dc22a3
+size 203047392

LiquidAI_LFM2-350M-Math-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8634893fd1a9f62381c461e80304b6822e5d55d06610fd88a89193fdded838ae
+size 193151456

LiquidAI_LFM2-350M-Math-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d0ae538dd3d039c2f9635f0f31e5dd1daeee182891f339b6059581fa238175b
+size 181150176

LiquidAI_LFM2-350M-Math-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f14654e99d22f49987b87e4ff53d93ffedad376949f9afeb277777bfdce910
+size 219300320

LiquidAI_LFM2-350M-Math-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34f509fd3f7659c10ada36c41e090e4f32aeefcaf2f4845289aeebdf529ae2c
+size 219898336

LiquidAI_LFM2-350M-Math-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33143abcb1107b12c2f6cdb32dad76f2fa1ba867e1037984d54c115f4cdca00
+size 237265376

LiquidAI_LFM2-350M-Math-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3d38b4c4d475d0d39d6216a1375311008bb058aab04ce3d08011c8441bbd4c
+size 245563872

LiquidAI_LFM2-350M-Math-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942e5ef43086a7a8ea5d316e819ba6a97f3829c1851cd10b87340e1b38693422
+size 229310944

LiquidAI_LFM2-350M-Math-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067a693e79f6d8c37c4642250ae0dc124ed27befc0a9e4d74701a99118f64851
+size 220750304

LiquidAI_LFM2-350M-Math-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e5e0871954a2c5834b182cb6cc1cd8e2f8dbf9647627e895fabe85a73c692b
+size 276627936

LiquidAI_LFM2-350M-Math-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a9cbe9b7a4a74a461bd7f1634bfdd60ba23e30ee1da1978915913541be59d2
+size 260375008

LiquidAI_LFM2-350M-Math-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4696f60b83d872e69ebcdfdea5e2dfa794402e8023caa8ceb8424bd363e1f1d
+size 255222240

LiquidAI_LFM2-350M-Math-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86242f0951ad1525b313b270e41baf54b75779864033ffb1182efc28231a06d9
+size 293380576

LiquidAI_LFM2-350M-Math-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42e2948ca1c3a71913bbe659934136899d171af4c4f3a75337c302a09b53508
+size 309633504

LiquidAI_LFM2-350M-Math-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8d9ceeb1ec92f2f46ce5957210da2d8d78b9e6ee32d9dc70225ed043d7499e
+size 379216352

LiquidAI_LFM2-350M-Math-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23de91eb1750014289dd6f3f59de94c7c5f15d36c525fbb57430b0032edad61
+size 711483584

README.md

@@ -0,0 +1,164 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model_relation: quantized
+base_model: LiquidAI/LFM2-350M-Math
+---
+
+## Llamacpp imatrix Quantizations of LFM2-350M-Math by LiquidAI
+
+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/b6683">b6683</a> for quantization.
+
+Original model: https://huggingface.co/LiquidAI/LFM2-350M-Math
+
+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
+
+No prompt format found, check original model page
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [LFM2-350M-Math-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-bf16.gguf) | bf16 | 0.71GB | false | Full BF16 weights. |
+| [LFM2-350M-Math-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q8_0.gguf) | Q8_0 | 0.38GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [LFM2-350M-Math-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q6_K_L.gguf) | Q6_K_L | 0.31GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [LFM2-350M-Math-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q6_K.gguf) | Q6_K | 0.29GB | false | Very high quality, near perfect, *recommended*. |
+| [LFM2-350M-Math-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q5_K_L.gguf) | Q5_K_L | 0.28GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [LFM2-350M-Math-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q5_K_M.gguf) | Q5_K_M | 0.26GB | false | High quality, *recommended*. |
+| [LFM2-350M-Math-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q5_K_S.gguf) | Q5_K_S | 0.26GB | false | High quality, *recommended*. |
+| [LFM2-350M-Math-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q4_K_L.gguf) | Q4_K_L | 0.25GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [LFM2-350M-Math-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q4_1.gguf) | Q4_1 | 0.24GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [LFM2-350M-Math-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q4_K_M.gguf) | Q4_K_M | 0.23GB | false | Good quality, default size for most use cases, *recommended*. |
+| [LFM2-350M-Math-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q4_K_S.gguf) | Q4_K_S | 0.22GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [LFM2-350M-Math-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q4_0.gguf) | Q4_0 | 0.22GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [LFM2-350M-Math-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-IQ4_NL.gguf) | IQ4_NL | 0.22GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [LFM2-350M-Math-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q3_K_XL.gguf) | Q3_K_XL | 0.22GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [LFM2-350M-Math-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-IQ4_XS.gguf) | IQ4_XS | 0.21GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [LFM2-350M-Math-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q3_K_L.gguf) | Q3_K_L | 0.20GB | false | Lower quality but usable, good for low RAM availability. |
+| [LFM2-350M-Math-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q3_K_M.gguf) | Q3_K_M | 0.19GB | false | Low quality. |
+| [LFM2-350M-Math-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-IQ3_M.gguf) | IQ3_M | 0.18GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [LFM2-350M-Math-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q3_K_S.gguf) | Q3_K_S | 0.18GB | false | Low quality, not recommended. |
+| [LFM2-350M-Math-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-IQ3_XS.gguf) | IQ3_XS | 0.18GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [LFM2-350M-Math-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q2_K_L.gguf) | Q2_K_L | 0.18GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [LFM2-350M-Math-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-IQ3_XXS.gguf) | IQ3_XXS | 0.16GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [LFM2-350M-Math-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-Q2_K.gguf) | Q2_K | 0.16GB | false | Very low quality but surprisingly usable. |
+| [LFM2-350M-Math-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Math-GGUF/blob/main/LiquidAI_LFM2-350M-Math-IQ2_M.gguf) | IQ2_M | 0.14GB | false | Relatively low quality, uses SOTA techniques to be surprisingly 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/LiquidAI_LFM2-350M-Math-GGUF --include "LiquidAI_LFM2-350M-Math-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/LiquidAI_LFM2-350M-Math-GGUF --include "LiquidAI_LFM2-350M-Math-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (LiquidAI_LFM2-350M-Math-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}