初始化项目，由ModelHub XC社区提供模型

Model: bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,70 @@
+*.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_LFM2-1.2B-Extract-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-1.2B-Extract-bf16.gguf filter=lfs diff=lfs merge=lfs -text

LiquidAI_LFM2-1.2B-Extract-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c008e0b877d13fbf2db1d483335e242b6ccc14face080d57169af14b4c6c228e
+size 434131520

LiquidAI_LFM2-1.2B-Extract-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20996c95a8630101d9bfc6ce3480327006be06216bc2ec96676392c5b3ff091f
+size 566792768

LiquidAI_LFM2-1.2B-Extract-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7867596f613618563d50a4d18593bae596412cfbbe1be4bd0a4bb6cbb85c464a
+size 537809472

LiquidAI_LFM2-1.2B-Extract-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f562f8c3b934201723a1acc7eb60fc2a9b8c16c507798211ad25b285366e651b
+size 490984000

LiquidAI_LFM2-1.2B-Extract-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09e13b8e79109564d1ed7e91454cc8bf8e2f9154a8018a004df2faa8367eca0
+size 695751232

LiquidAI_LFM2-1.2B-Extract-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51de9be31efdea88f19991e76883ba7fb240dd3fa0704f2aa288415d59eee14
+size 663376448

LiquidAI_LFM2-1.2B-Extract-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155415705db60818e09139435222b30f072ac122f9d6949a76366ad5d947a57c
+size 483398208

LiquidAI_LFM2-1.2B-Extract-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdce0f4c51202132ab4751f20ea3e4a1d34023d82b8d6a721b1f3df74c39aea2
+size 515904064

LiquidAI_LFM2-1.2B-Extract-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a694b9a8073e7aeede29550dd08ce59179e870c91736db8548d8bee860cef1d
+size 635474496

LiquidAI_LFM2-1.2B-Extract-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9affb8c4fce6eaa9402c0b3bc3bd028b28c92212317b02dc706b23203ef2698c
+size 600347200

LiquidAI_LFM2-1.2B-Extract-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e0cf8c93d904dc0bc06f8e6a58a8ae269709785bbfe4911644b0930e5a36ee
+size 558158400

LiquidAI_LFM2-1.2B-Extract-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531d2d752c778559fbea9e70715beab337e0570b7c729bfa313d294f88ed2388
+size 667980352

LiquidAI_LFM2-1.2B-Extract-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be66107278e2d07290777beda3d48f59a3244f1c4b9b4636c94589d98f4557e
+size 697848384

LiquidAI_LFM2-1.2B-Extract-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d74bc9a7584f60e0ceb6527749327496ff55931c680f98bc2825fd24b6a4af
+size 760500800

LiquidAI_LFM2-1.2B-Extract-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed757aa25c0c4b78b9cc30686eeef2d694b9da5b62a6663c756c65ceb0adb15
+size 763400768

LiquidAI_LFM2-1.2B-Extract-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a1c5600045e9ade49bc4a9e3df083cef7c82b05a6d47ea2e58ab44cc98b16a
+size 730894912

LiquidAI_LFM2-1.2B-Extract-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5ec71f850948fc3f68ab4475a8ed6d334cdf3bf327a3c4eca116392883a104
+size 700469824

LiquidAI_LFM2-1.2B-Extract-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e54d9af3b7ec44e3d34e50774006f68b53792f3cbb61195c181fbedfe230112
+size 875860544

LiquidAI_LFM2-1.2B-Extract-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b1a2727916a07f56de63697cbf912881c6f850c2ead23350870f1daa16f960
+size 843354688

LiquidAI_LFM2-1.2B-Extract-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c552ac9ce7849fed1407ea08188bd691c0dd2035800fa14bd5f0fd35c02cca5b
+size 825250368

LiquidAI_LFM2-1.2B-Extract-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3467b1f66e174a050fa2af856e3eb57696dfa8ed96076fdc76ab71fd47abbb0
+size 962843200

LiquidAI_LFM2-1.2B-Extract-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6498023e408ccbfa349f35dc7f2d728d4b3b8a4351fb304cfb25125f6ffb1ebc
+size 995349056

LiquidAI_LFM2-1.2B-Extract-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3a583bab4bb92e02a7944abe1aadd369e07a7349e33e372952aacced7e11b9
+size 1246253632

LiquidAI_LFM2-1.2B-Extract-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218a8147b6de57b76ff1ef6e530e522e1001b43375edb975defc8e0b58ddb24c
+size 2343325984

README.md

@@ -0,0 +1,164 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model_relation: quantized
+base_model: LiquidAI/LFM2-1.2B-Extract
+---
+
+## Llamacpp imatrix Quantizations of LFM2-1.2B-Extract 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/LFM2-1.2B-Extract
+
+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 |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [LFM2-1.2B-Extract-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-bf16.gguf) | bf16 | 2.34GB | false | Full BF16 weights. |
+| [LFM2-1.2B-Extract-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q8_0.gguf) | Q8_0 | 1.25GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [LFM2-1.2B-Extract-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q6_K_L.gguf) | Q6_K_L | 1.00GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [LFM2-1.2B-Extract-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q6_K.gguf) | Q6_K | 0.96GB | false | Very high quality, near perfect, *recommended*. |
+| [LFM2-1.2B-Extract-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q5_K_L.gguf) | Q5_K_L | 0.88GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [LFM2-1.2B-Extract-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q5_K_M.gguf) | Q5_K_M | 0.84GB | false | High quality, *recommended*. |
+| [LFM2-1.2B-Extract-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q5_K_S.gguf) | Q5_K_S | 0.83GB | false | High quality, *recommended*. |
+| [LFM2-1.2B-Extract-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_K_L.gguf) | Q4_K_L | 0.76GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [LFM2-1.2B-Extract-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_1.gguf) | Q4_1 | 0.76GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [LFM2-1.2B-Extract-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_K_M.gguf) | Q4_K_M | 0.73GB | false | Good quality, default size for most use cases, *recommended*. |
+| [LFM2-1.2B-Extract-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_K_S.gguf) | Q4_K_S | 0.70GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [LFM2-1.2B-Extract-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_0.gguf) | Q4_0 | 0.70GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [LFM2-1.2B-Extract-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ4_NL.gguf) | IQ4_NL | 0.70GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [LFM2-1.2B-Extract-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q3_K_XL.gguf) | Q3_K_XL | 0.67GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [LFM2-1.2B-Extract-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ4_XS.gguf) | IQ4_XS | 0.66GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [LFM2-1.2B-Extract-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q3_K_L.gguf) | Q3_K_L | 0.64GB | false | Lower quality but usable, good for low RAM availability. |
+| [LFM2-1.2B-Extract-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q3_K_M.gguf) | Q3_K_M | 0.60GB | false | Low quality. |
+| [LFM2-1.2B-Extract-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ3_M.gguf) | IQ3_M | 0.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [LFM2-1.2B-Extract-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q3_K_S.gguf) | Q3_K_S | 0.56GB | false | Low quality, not recommended. |
+| [LFM2-1.2B-Extract-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ3_XS.gguf) | IQ3_XS | 0.54GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [LFM2-1.2B-Extract-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q2_K_L.gguf) | Q2_K_L | 0.52GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [LFM2-1.2B-Extract-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ3_XXS.gguf) | IQ3_XXS | 0.49GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [LFM2-1.2B-Extract-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q2_K.gguf) | Q2_K | 0.48GB | false | Very low quality but surprisingly usable. |
+| [LFM2-1.2B-Extract-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ2_M.gguf) | IQ2_M | 0.43GB | 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_LFM2-1.2B-Extract-GGUF --include "LiquidAI_LFM2-1.2B-Extract-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_LFM2-1.2B-Extract-GGUF --include "LiquidAI_LFM2-1.2B-Extract-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (LiquidAI_LFM2-1.2B-Extract-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}