初始化项目，由ModelHub XC社区提供模型

Model: bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,47 @@
+*.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
+*.gguf* 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

Locutusque_liberalis-cogitator-llama-3.1-8b-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a9093fd42c9ff79d3996e5f41d07028f1939cca5bb7473a7ee1b3619f12f0f
+size 2948281792

Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de999814cd8ca2230ec3b137d9b13ac327ec0f7161f63cb2036ed47013e3901e
+size 3784824256

Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33cd1a9c5ed85653dbaee7efd1df83a1898efd025bc5f4ae432a5925a02c9e43
+size 3518748096

Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1a29ea4552ad3b33ca20e2af6afefba585fa99899f7172fb6d6cb2c4524a77
+size 3274913216

Locutusque_liberalis-cogitator-llama-3.1-8b-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fd8bb2b01cd393c5ab5e6f560f48544f5921141a035b263cb5d7512e42d179
+size 4677989824

Locutusque_liberalis-cogitator-llama-3.1-8b-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6628e73ddc832766e3a4d18a6de92d43e4e9518dca99d923a2714d069ac509ec
+size 4447663552

Locutusque_liberalis-cogitator-llama-3.1-8b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ee24f346c31360bdf659e2a9ed800b16f97b530ada91ae3328247ab2bfc80b
+size 3179132352

Locutusque_liberalis-cogitator-llama-3.1-8b-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff1462c0b8d54e27229de3b9ac827491f94dca7118092b83d080f3ff352697f
+size 3692156352

Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c3b859c27ecc9e122967ac24155bdca726df423b505067d416a5a62c54d67e
+size 4321957312

Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72894d08f476699292d6089fc27d58e79ed2b6b5d4c8432237184afdc8c9c171
+size 4018918848

Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49311c418eb2401a43859d9eb443b41947ba2f190f9800f6c669f8ecfa382f6e
+size 3664500160

Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96285743851b46ec742bbe491b32a7d01402741bf0813e42d9b1c44f9b353317
+size 4781626816

Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b9e4c7a9d86840ccef53fe73587542b9b6e17539e7638ec3893f309134bffa
+size 4675892672

Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7361fcd7a130308539e949fa7cb0d7671c739839c14e7f9a267734b5d710ee2
+size 5130253760

Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94db5ed8074f47f2e2c1d3d69f5f204b263c72d78a9b6699529b6a45f134054c
+size 5310633408

Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986f3f6d0858393800af93cad86048d324c31d06a804c9f393368daf2ee070c5
+size 4920735168

Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332de4a2925074e0fb0b9d44a548f0267abbe94d7686695625a160c52b6edb75
+size 4692669888

Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce4b27020fce0b144450963b41b8c9d39134e393e38bd38a11384bdc728af95
+size 6057219520

Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2008f002836da9fc1c33cb64974c006aaf936f56b5247c5f7b63ad5585118739
+size 5732988352

Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef6b8440e3173a5297668fd7dfbf6171224cc199cc8eecd782166d91dcbb3114
+size 5599294912

Locutusque_liberalis-cogitator-llama-3.1-8b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e69969a7283d9f1559c79f9bc17e24bacb4711a16ec9cff89926da8d722c25f
+size 6596007360

Locutusque_liberalis-cogitator-llama-3.1-8b-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19195d5249f2c0bbc9f1242303d9e1466a47a561dfbb5b376e4612fe8b01a33
+size 6850467264

Locutusque_liberalis-cogitator-llama-3.1-8b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e36bd546427440805c3447650ff67fc9002af6b6ce7a3f8359dd00cd25efc69
+size 8540771776

Locutusque_liberalis-cogitator-llama-3.1-8b-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6b0d1668878e979ed0630b5d8caf72baed1b83f2f49a976d622c3c7543b109
+size 16068891776

Locutusque_liberalis-cogitator-llama-3.1-8b-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef5a1346faac68d5b62a0ff65535403ba31e829e6583b0555dde8c8d71d8a11
+size 5015232

README.md

@@ -0,0 +1,164 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model_relation: quantized
+base_model: Locutusque/liberalis-cogitator-llama-3.1-8b
+---
+
+## Llamacpp imatrix Quantizations of liberalis-cogitator-llama-3.1-8b by Locutusque
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b6115">b6115</a> for quantization.
+
+Original model: https://huggingface.co/Locutusque/liberalis-cogitator-llama-3.1-8b
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
+
+Run them in [LM Studio](https://lmstudio.ai/)
+
+Run them directly with [llama.cpp](https://github.com/ggerganov/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 |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [liberalis-cogitator-llama-3.1-8b-bf16.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-bf16.gguf) | bf16 | 16.07GB | false | Full BF16 weights. |
+| [liberalis-cogitator-llama-3.1-8b-Q8_0.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [liberalis-cogitator-llama-3.1-8b-Q6_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q6_K.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q5_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q5_K_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q5_K_S.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q4_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q4_1.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_1.gguf) | Q4_1 | 5.13GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [liberalis-cogitator-llama-3.1-8b-Q4_K_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for most use cases, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q3_K_XL.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_XL.gguf) | Q3_K_XL | 4.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [liberalis-cogitator-llama-3.1-8b-Q4_K_S.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q4_0.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [liberalis-cogitator-llama-3.1-8b-IQ4_NL.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ4_NL.gguf) | IQ4_NL | 4.68GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [liberalis-cogitator-llama-3.1-8b-IQ4_XS.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [liberalis-cogitator-llama-3.1-8b-Q3_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
+| [liberalis-cogitator-llama-3.1-8b-Q3_K_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
+| [liberalis-cogitator-llama-3.1-8b-IQ3_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [liberalis-cogitator-llama-3.1-8b-Q2_K_L.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [liberalis-cogitator-llama-3.1-8b-Q3_K_S.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
+| [liberalis-cogitator-llama-3.1-8b-IQ3_XS.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [liberalis-cogitator-llama-3.1-8b-IQ3_XXS.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [liberalis-cogitator-llama-3.1-8b-Q2_K.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
+| [liberalis-cogitator-llama-3.1-8b-IQ2_M.gguf](https://huggingface.co/bartowski/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF/blob/main/Locutusque_liberalis-cogitator-llama-3.1-8b-IQ2_M.gguf) | IQ2_M | 2.95GB | 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/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF --include "Locutusque_liberalis-cogitator-llama-3.1-8b-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/Locutusque_liberalis-cogitator-llama-3.1-8b-GGUF --include "Locutusque_liberalis-cogitator-llama-3.1-8b-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (Locutusque_liberalis-cogitator-llama-3.1-8b-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/ggerganov/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/ggerganov/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/ggerganov/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/ggerganov/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}