Llamacpp quants

.gitattributes

@@ -33,3 +33,26 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+EulerMath-Mistral-7B.imatrix filter=lfs diff=lfs merge=lfs -text

EulerMath-Mistral-7B-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ec03d6e0ca7e7352a47db0347e0b6e200233dd4483cde6bfc4c3f488828129
+size 1754449984

EulerMath-Mistral-7B-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b71aebac61cff79d20c9c9b7ab0451c6c4087e4ed6af30003841e1f70cdfdd9
+size 1612105792

EulerMath-Mistral-7B-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802ddb02c78d4b3e02f26440967e30ca5d49e7355144b6f6ef3adb77790bdb34
+size 2500717024

EulerMath-Mistral-7B-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d36f829c2fb4d714158ee459925d85184da0d9de7483f9da9d47751baba640
+size 2310924768

EulerMath-Mistral-7B-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa8a889acb96fcaba8208d5bcc18376340d3c5912155282031f0ad0748300c0
+size 2198259776

EulerMath-Mistral-7B-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98224db49de388414e844e211d5085a8687af19d5f790d7ea516cdbe75691374
+size 1991690304

EulerMath-Mistral-7B-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b900768fcf23666b2a28675d87368f5106aa58e3c890cb94f9f2b1e8e7f80c9
+size 3284896768

EulerMath-Mistral-7B-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b811a6c94307b77fcd0bcc998edf5439fd115063259a2cdc308f78525d7c5e9
+size 3182398464

EulerMath-Mistral-7B-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b1f8e582ff6c44aa324e3fb234399d6d5c0f4d6df2de548fdacaa2b6061644
+size 3018820608

EulerMath-Mistral-7B-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03cab4079bc205f5541ea03d9a938e8e83c083a84d32591bd4361127630c7bd
+size 2827348448

EulerMath-Mistral-7B-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e45da2b61a966fa390953b8afbdd295ec1f0a13dc854d5d66e5db97f66176d
+size 4125699616

EulerMath-Mistral-7B-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55752a68979cb06421c3be170154b835258222172c1d32fb1d4daf66c90c511
+size 3907693984

EulerMath-Mistral-7B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6064f1ff10b1518168893c6088373a2035b5ded6c2675b784a9c45a91e200256
+size 2719246944

EulerMath-Mistral-7B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f974f2a51947bff14b3088ff374d4dea873d49ae0224a65fe8180e7e93dc4f
+size 3822029824

EulerMath-Mistral-7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766c7bb48a4210359d7d24c9f423b65386f002a41098a0ff75fc56404fb9ebc2
+size 3518991360

EulerMath-Mistral-7B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ff4b371eb2add75d0d2d9eb47d21118507618801336e0ec220b941a593c081
+size 3164572672

EulerMath-Mistral-7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01103cfeaffc04bcf05ad7f2b06d0e78425d828d5de4eddcd93c0ea00fb6633b
+size 4368444960

EulerMath-Mistral-7B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b32a8f24c8a5ceb76dd7116340e7c6ede2e3b61fc4a10cf3f4642f854ab2a3a
+size 4140379680

EulerMath-Mistral-7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54233bda306ed22b296072a0e178816d44ff002a906dd85740ee9bb403d2680
+size 5131415584

EulerMath-Mistral-7B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416c2942b4e855429a83fcd2b74b54d8e95cda111c8991f9cf75324a5db9e635
+size 4997722144

EulerMath-Mistral-7B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad8818340bba7ff11f84f772d38f5fe35768cd259f3feb776f81e215018222e
+size 5942071872

EulerMath-Mistral-7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:721ae34342e4ba58c380763a3fc5afbb3dad0d54248a5f4d95fcdbd2002cfc2a
+size 7695866368

EulerMath-Mistral-7B.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebfbbac9560505096697fae9cebba293b764286d81a05ebf7c8600e16360fd1
+size 4988126

README.md

@@ -0,0 +1,88 @@
+---
+license: other
+tags:
+- math
+- alpaca
+- synthetic data
+- instruct
+- axolotl
+- finetune
+- gpt4
+datasets:
+- TIGER-Lab/MathInstruct
+- microsoft/orca-math-word-problems-200k
+language:
+- en
+base_model: meta-math/MetaMath-Mistral-7B
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+
+## Llamacpp Quantizations of EulerMath-Mistral-7B
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2636">b2636</a> for quantization.
+
+Original model: https://huggingface.co/Weyaxi/EulerMath-Mistral-7B
+
+All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
+
+## Prompt format
+
+```
+### Instruction: {prompt}
+
+### Response: </s>
+```
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [EulerMath-Mistral-7B-Q8_0.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
+| [EulerMath-Mistral-7B-Q6_K.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
+| [EulerMath-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, *recommended*. |
+| [EulerMath-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, *recommended*. |
+| [EulerMath-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
+| [EulerMath-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with more space savings, *recommended*. |
+| [EulerMath-Mistral-7B-IQ4_NL.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ4_NL.gguf) | IQ4_NL | 4.12GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
+| [EulerMath-Mistral-7B-IQ4_XS.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ4_XS.gguf) | IQ4_XS | 3.90GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [EulerMath-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
+| [EulerMath-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
+| [EulerMath-Mistral-7B-IQ3_M.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ3_M.gguf) | IQ3_M | 3.28GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [EulerMath-Mistral-7B-IQ3_S.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ3_S.gguf) | IQ3_S | 3.18GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
+| [EulerMath-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
+| [EulerMath-Mistral-7B-IQ3_XS.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ3_XS.gguf) | IQ3_XS | 3.01GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [EulerMath-Mistral-7B-IQ3_XXS.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ3_XXS.gguf) | IQ3_XXS | 2.82GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [EulerMath-Mistral-7B-Q2_K.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-Q2_K.gguf) | Q2_K | 2.71GB | Very low quality but surprisingly usable. |
+| [EulerMath-Mistral-7B-IQ2_M.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ2_M.gguf) | IQ2_M | 2.50GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
+| [EulerMath-Mistral-7B-IQ2_S.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ2_S.gguf) | IQ2_S | 2.31GB | Very low quality, uses SOTA techniques to be usable. |
+| [EulerMath-Mistral-7B-IQ2_XS.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ2_XS.gguf) | IQ2_XS | 2.19GB | Very low quality, uses SOTA techniques to be usable. |
+| [EulerMath-Mistral-7B-IQ2_XXS.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ2_XXS.gguf) | IQ2_XXS | 1.99GB | Lower quality, uses SOTA techniques to be usable. |
+| [EulerMath-Mistral-7B-IQ1_M.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ1_M.gguf) | IQ1_M | 1.75GB | Extremely low quality, *not* recommended. |
+| [EulerMath-Mistral-7B-IQ1_S.gguf](https://huggingface.co/bartowski/EulerMath-Mistral-7B-GGUF/blob/main/EulerMath-Mistral-7B-IQ1_S.gguf) | IQ1_S | 1.61GB | Extremely low quality, *not* recommended. |
+
+## Which file should I choose?
+
+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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+
+The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski