diff --git a/.gitattributes b/.gitattributes index a7ecd72..19ff4fd 100644 --- a/.gitattributes +++ b/.gitattributes @@ -58,3 +58,10 @@ Phi-3-medium-128k-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text Phi-3-medium-128k-instruct-f32.gguf/Phi-3-medium-128k-instruct-f32-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text Phi-3-medium-128k-instruct-f32.gguf/Phi-3-medium-128k-instruct-f32-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text Phi-3-medium-128k-instruct.imatrix filter=lfs diff=lfs merge=lfs -text +Phi-3-medium-128k-instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-medium-128k-instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-medium-128k-instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-medium-128k-instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-medium-128k-instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-medium-128k-instruct-f32/Phi-3-medium-128k-instruct-f32-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-medium-128k-instruct-f32/Phi-3-medium-128k-instruct-f32-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-3-medium-128k-instruct-IQ2_M.gguf b/Phi-3-medium-128k-instruct-IQ2_M.gguf index 80285e9..fd1112b 100644 --- a/Phi-3-medium-128k-instruct-IQ2_M.gguf +++ b/Phi-3-medium-128k-instruct-IQ2_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4ac128777bcf71ddf40d72bfbfdf5c028b15a19d76a2cbc3a0a101560a3f1ff9 -size 4717006368 +oid sha256:e4bca6c2b6bc2795200836dd61816e1fdba6ca405197ce6a5959a43a14b1f06d +size 4717006912 diff --git a/Phi-3-medium-128k-instruct-IQ2_XXS.gguf b/Phi-3-medium-128k-instruct-IQ2_XXS.gguf index ce8b331..51df665 100644 --- a/Phi-3-medium-128k-instruct-IQ2_XXS.gguf +++ b/Phi-3-medium-128k-instruct-IQ2_XXS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9dc512a2ddaed5576fe7ca1a981963c83c04079db3c9c8eabf87ea6690fa74f2 -size 3715757088 +oid sha256:8acde21414d9bf67d727b6a9c851d3de814084277e03053157df5c6ce34aff44 +size 3715757632 diff --git a/Phi-3-medium-128k-instruct-IQ3_M.gguf b/Phi-3-medium-128k-instruct-IQ3_M.gguf index 2f522a5..ccba6cc 100644 --- a/Phi-3-medium-128k-instruct-IQ3_M.gguf +++ b/Phi-3-medium-128k-instruct-IQ3_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a4a1df7bac1fe1a9991388bc78e5eb057999e9ade7e96d832cbdc377e4a267a8 -size 6473977888 +oid sha256:4012fcc9f5d3f1bc74be6197f64e6ff76a03f667d793f6d470ad732753c65b81 +size 6473978432 diff --git a/Phi-3-medium-128k-instruct-IQ3_XS.gguf b/Phi-3-medium-128k-instruct-IQ3_XS.gguf index c4cc47d..c873707 100644 --- a/Phi-3-medium-128k-instruct-IQ3_XS.gguf +++ b/Phi-3-medium-128k-instruct-IQ3_XS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b4a79e3eaaf7daf0653a8b8cadd3b6e9d71be71cc0abbce723170cf8ded3acd4 -size 5806841888 +oid sha256:c1eac74568ef60c5377eb9652250ca10e7854611903ce88fca339f2c01ce5d38 +size 5806842432 diff --git a/Phi-3-medium-128k-instruct-IQ4_XS.gguf b/Phi-3-medium-128k-instruct-IQ4_XS.gguf index acabb8d..62bd814 100644 --- a/Phi-3-medium-128k-instruct-IQ4_XS.gguf +++ b/Phi-3-medium-128k-instruct-IQ4_XS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a9098e8e89e69b71592a1f86d06d835652a42e844f0eafad99f71ebbebef379d -size 7466011168 +oid sha256:56d050a3b7f7e46a9e704d50d905d96458ee746992da80abae04829d5dd62907 +size 7466011712 diff --git a/Phi-3-medium-128k-instruct-Q2_K.gguf b/Phi-3-medium-128k-instruct-Q2_K.gguf index 4f3964c..89854ee 100644 --- a/Phi-3-medium-128k-instruct-Q2_K.gguf +++ b/Phi-3-medium-128k-instruct-Q2_K.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:902f408660621f211a4cc11387e86754d1e5cbf15341a076a7342b1e9461a30b -size 5143000608 +oid sha256:5b98588e7614999356cbf4870d954462c7919af5618796fa305d392d1ec90d80 +size 5143001152 diff --git a/Phi-3-medium-128k-instruct-Q2_K_L.gguf b/Phi-3-medium-128k-instruct-Q2_K_L.gguf new file mode 100644 index 0000000..2c1036c --- /dev/null +++ b/Phi-3-medium-128k-instruct-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b846825b4f9a538de034d883b90fd91b8be102e26cc3ec81c51e286146d54457 +size 5303321152 diff --git a/Phi-3-medium-128k-instruct-Q3_K_L.gguf b/Phi-3-medium-128k-instruct-Q3_K_L.gguf index 282984f..7022d80 100644 --- a/Phi-3-medium-128k-instruct-Q3_K_L.gguf +++ b/Phi-3-medium-128k-instruct-Q3_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d2c7f00f5b2ba6bbd185a9b404f02a2705a8c4709513734372f0d32efc20ab98 -size 7490297888 +oid sha256:cbdedbff19cf9a06a7b3adf6e28f51bbbc75d0099ec55306112949643cd242d6 +size 7490298432 diff --git a/Phi-3-medium-128k-instruct-Q3_K_M.gguf b/Phi-3-medium-128k-instruct-Q3_K_M.gguf index 33dd1b2..10cf670 100644 --- a/Phi-3-medium-128k-instruct-Q3_K_M.gguf +++ b/Phi-3-medium-128k-instruct-Q3_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:38b3f72bdd536b163168583ce8deef6ac4966444c67c699b1ee2e51e82d3fc42 -size 6923411488 +oid sha256:2fff291dc1f2831d4b4beaf1a41c05cb4cc879ee2abdcc85468f2b6d6e9e4d1d +size 6923412032 diff --git a/Phi-3-medium-128k-instruct-Q3_K_S.gguf b/Phi-3-medium-128k-instruct-Q3_K_S.gguf index 3a4e59d..7669d39 100644 --- a/Phi-3-medium-128k-instruct-Q3_K_S.gguf +++ b/Phi-3-medium-128k-instruct-Q3_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7c323ef2d5a5e9bc2a7bbb90a460301c90e271d9404545b8b1ab134ab228a87d -size 6064889888 +oid sha256:a5834dd17ba9f837cb17fccaa8ee5e7671db140527778a4f3bb26dad050bc3bd +size 6064890432 diff --git a/Phi-3-medium-128k-instruct-Q3_K_XL.gguf b/Phi-3-medium-128k-instruct-Q3_K_XL.gguf new file mode 100644 index 0000000..fdcd5c9 --- /dev/null +++ b/Phi-3-medium-128k-instruct-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2563b861c2b419af34a96f0dc26aa5a182cd77624ee7dcebf4b16b1c77d7fb +size 7633945152 diff --git a/Phi-3-medium-128k-instruct-Q4_K_L.gguf b/Phi-3-medium-128k-instruct-Q4_K_L.gguf new file mode 100644 index 0000000..227048b --- /dev/null +++ b/Phi-3-medium-128k-instruct-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88633f358967eb7057ef9d95ea44b1362450282d64cb98ba3c8c8a9c5014d67a +size 8688665152 diff --git a/Phi-3-medium-128k-instruct-Q4_K_M.gguf b/Phi-3-medium-128k-instruct-Q4_K_M.gguf index bcd96c7..510de49 100644 --- a/Phi-3-medium-128k-instruct-Q4_K_M.gguf +++ b/Phi-3-medium-128k-instruct-Q4_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d8ed734336b8b83977874afc85f11674bf3b49a92e8e02ac4197e6812f10c242 -size 8566821408 +oid sha256:6adc92faaf06bca4f706f279a569402b727be5a02ec8600d52fac3dce23ae43d +size 8566821952 diff --git a/Phi-3-medium-128k-instruct-Q4_K_S.gguf b/Phi-3-medium-128k-instruct-Q4_K_S.gguf index dafd981..04adfbd 100644 --- a/Phi-3-medium-128k-instruct-Q4_K_S.gguf +++ b/Phi-3-medium-128k-instruct-Q4_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d39678f87e2c17fccc545955f5d61cc26f3a592c56d503cfea0d7d0e7ac6cf81 -size 7954469408 +oid sha256:8dd7fee0b0184a9766bd2e96327773dc22366a342aa908df5ace93dddd0f7c3d +size 7954469952 diff --git a/Phi-3-medium-128k-instruct-Q5_K_L.gguf b/Phi-3-medium-128k-instruct-Q5_K_L.gguf new file mode 100644 index 0000000..5c6079d --- /dev/null +++ b/Phi-3-medium-128k-instruct-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a64dc50d4aa2a33fddacd7fb58888aa60fe5b99baff292e4e364b4ab534c683 +size 10175513152 diff --git a/Phi-3-medium-128k-instruct-Q5_K_M.gguf b/Phi-3-medium-128k-instruct-Q5_K_M.gguf index 78bc907..065a637 100644 --- a/Phi-3-medium-128k-instruct-Q5_K_M.gguf +++ b/Phi-3-medium-128k-instruct-Q5_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5881f155da96899eb0639ae35b8b8f072267b96ca0955926cd5ef8bf6cee9fbd -size 10074190368 +oid sha256:d06da23c184ad7a0e7c2a030a621907816e6efc4c15acf9612e10f8ba7f81d4f +size 10074190912 diff --git a/Phi-3-medium-128k-instruct-Q5_K_S.gguf b/Phi-3-medium-128k-instruct-Q5_K_S.gguf index 5bb693d..a850985 100644 --- a/Phi-3-medium-128k-instruct-Q5_K_S.gguf +++ b/Phi-3-medium-128k-instruct-Q5_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a0da98dc6e5f1929e4a4343b4983e345e0202ce5ffdac578ee5947c79fdd01f9 -size 9621582368 +oid sha256:d2289f1c08637e3d2583f4b57c6d1b462f1360a2c8e4bedaba6b06104b7f9383 +size 9621582912 diff --git a/Phi-3-medium-128k-instruct-Q6_K.gguf b/Phi-3-medium-128k-instruct-Q6_K.gguf index d1a1e53..b335e4c 100644 --- a/Phi-3-medium-128k-instruct-Q6_K.gguf +++ b/Phi-3-medium-128k-instruct-Q6_K.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fb6337cbbe910dd9a8eb5078b30e09174853a2b5bbf8cebe0fff97d2e8ab9106 -size 11453817888 +oid sha256:806f6fa6b9776843f655a845ce269e208fb4ccb432aa29bc3481281c051543f2 +size 11453818432 diff --git a/Phi-3-medium-128k-instruct-Q6_K_L.gguf b/Phi-3-medium-128k-instruct-Q6_K_L.gguf new file mode 100644 index 0000000..91d1400 --- /dev/null +++ b/Phi-3-medium-128k-instruct-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0cb8b3cd4209825c9917855b8d590f47aaed543f9163fd436799a88c3704a0e +size 11533337152 diff --git a/Phi-3-medium-128k-instruct-Q8_0.gguf b/Phi-3-medium-128k-instruct-Q8_0.gguf index 6c53898..9f968d5 100644 --- a/Phi-3-medium-128k-instruct-Q8_0.gguf +++ b/Phi-3-medium-128k-instruct-Q8_0.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3d344e88ec30ae94b506159a43106ce55126687a2427ff7821f1ebf5dd42a648 -size 14834712608 +oid sha256:5b38b0907c2c72c679b847801ffa214f33f08818b835a057af6932690c189157 +size 14834713152 diff --git a/Phi-3-medium-128k-instruct-f32/Phi-3-medium-128k-instruct-f32-00001-of-00002.gguf b/Phi-3-medium-128k-instruct-f32/Phi-3-medium-128k-instruct-f32-00001-of-00002.gguf new file mode 100644 index 0000000..9a5fe10 --- /dev/null +++ b/Phi-3-medium-128k-instruct-f32/Phi-3-medium-128k-instruct-f32-00001-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cccfd7a472e2ee107db900c9fdf3b5ce01b55d3c505d06f749ac5d4dc35bc4ca +size 39455887040 diff --git a/Phi-3-medium-128k-instruct-f32/Phi-3-medium-128k-instruct-f32-00002-of-00002.gguf b/Phi-3-medium-128k-instruct-f32/Phi-3-medium-128k-instruct-f32-00002-of-00002.gguf new file mode 100644 index 0000000..45ee18f --- /dev/null +++ b/Phi-3-medium-128k-instruct-f32/Phi-3-medium-128k-instruct-f32-00002-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:292e6ddb549b091bca18727230bad79b5968412064895282af7efd6e20096544 +size 16385807136 diff --git a/Phi-3-medium-128k-instruct.imatrix b/Phi-3-medium-128k-instruct.imatrix index 7725e0c..ced411c 100644 --- a/Phi-3-medium-128k-instruct.imatrix +++ b/Phi-3-medium-128k-instruct.imatrix @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:499a8bb5daebfc977e82ecc53018aa645e92dff3d869c2ef74eddf68f04c858f -size 5330287 +oid sha256:34604d58d7a6b2d3ab9f45abf13961d9180228cd0ec943b1ff655f9422f0a988 +size 5330288 diff --git a/README.md b/README.md index e5cc996..c648341 100644 --- a/README.md +++ b/README.md @@ -1,31 +1,32 @@ --- -license: mit -license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE - +base_model: microsoft/Phi-3-medium-128k-instruct language: - multilingual +license: mit +license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE pipeline_tag: text-generation tags: -- phi3 - nlp - code +quantized_by: bartowski inference: parameters: temperature: 0.7 widget: - - messages: - - role: user - content: Can you provide ways to eat combinations of bananas and dragonfruits? -quantized_by: bartowski +- messages: + - role: user + content: Can you provide ways to eat combinations of bananas and dragonfruits? --- ## Llamacpp imatrix Quantizations of Phi-3-medium-128k-instruct -Using llama.cpp pull request 7225 for quantization. +Using llama.cpp release b3561 for quantization. Original model: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct -All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/b6ac44691e994344625687afe3263b3a) +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) ## Prompt format @@ -33,32 +34,49 @@ All quants made using imatrix option with dataset from [here](https://gist.githu <|user|> {prompt}<|end|><|assistant|><|end|> ``` +## What's new: + +Updating to latest llama.cpp for rope fixes (thanks Niluayuk) + ## Download a file (not the whole branch) from below: -| Filename | Quant type | File Size | Description | -| -------- | ---------- | --------- | ----------- | -| [Phi-3-medium-128k-instruct-Q8_0.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q8_0.gguf) | Q8_0 | 14.83GB | Extremely high quality, generally unneeded but max available quant. | -| [Phi-3-medium-128k-instruct-Q6_K.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q6_K.gguf) | Q6_K | 11.45GB | Very high quality, near perfect, *recommended*. | -| [Phi-3-medium-128k-instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q5_K_M.gguf) | Q5_K_M | 10.07GB | High quality, *recommended*. | -| [Phi-3-medium-128k-instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q5_K_S.gguf) | Q5_K_S | 9.62GB | High quality, *recommended*. | -| [Phi-3-medium-128k-instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q4_K_M.gguf) | Q4_K_M | 8.56GB | Good quality, uses about 4.83 bits per weight, *recommended*. | -| [Phi-3-medium-128k-instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q4_K_S.gguf) | Q4_K_S | 7.95GB | Slightly lower quality with more space savings, *recommended*. | -| [Phi-3-medium-128k-instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ4_NL.gguf) | IQ4_NL | 7.89GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. | -| [Phi-3-medium-128k-instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ4_XS.gguf) | IQ4_XS | 7.46GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | -| [Phi-3-medium-128k-instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q3_K_L.gguf) | Q3_K_L | 7.49GB | Lower quality but usable, good for low RAM availability. | -| [Phi-3-medium-128k-instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q3_K_M.gguf) | Q3_K_M | 6.92GB | Even lower quality. | -| [Phi-3-medium-128k-instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ3_M.gguf) | IQ3_M | 6.47GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. | -| [Phi-3-medium-128k-instruct-IQ3_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ3_S.gguf) | IQ3_S | 6.06GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. | -| [Phi-3-medium-128k-instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q3_K_S.gguf) | Q3_K_S | 6.06GB | Low quality, not recommended. | -| [Phi-3-medium-128k-instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ3_XS.gguf) | IQ3_XS | 5.80GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. | -| [Phi-3-medium-128k-instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ3_XXS.gguf) | IQ3_XXS | 5.45GB | Lower quality, new method with decent performance, comparable to Q3 quants. | -| [Phi-3-medium-128k-instruct-Q2_K.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q2_K.gguf) | Q2_K | 5.14GB | Very low quality but surprisingly usable. | -| [Phi-3-medium-128k-instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ2_M.gguf) | IQ2_M | 4.71GB | Very low quality, uses SOTA techniques to also be surprisingly usable. | -| [Phi-3-medium-128k-instruct-IQ2_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ2_S.gguf) | IQ2_S | 4.33GB | Very low quality, uses SOTA techniques to be usable. | -| [Phi-3-medium-128k-instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ2_XS.gguf) | IQ2_XS | 4.12GB | Very low quality, uses SOTA techniques to be usable. | -| [Phi-3-medium-128k-instruct-IQ2_XXS.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ2_XXS.gguf) | IQ2_XXS | 3.71GB | Lower quality, uses SOTA techniques to be usable. | -| [Phi-3-medium-128k-instruct-IQ1_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ1_M.gguf) | IQ1_M | 3.24GB | Extremely low quality, *not* recommended. | -| [Phi-3-medium-128k-instruct-IQ1_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ1_S.gguf) | IQ1_S | 2.95GB | Extremely low quality, *not* recommended. | +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Phi-3-medium-128k-instruct-f32.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-f32) | f32 | 55.84GB | true | Full F32 weights. | +| [Phi-3-medium-128k-instruct-Q8_0.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q8_0.gguf) | Q8_0 | 14.83GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Phi-3-medium-128k-instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q6_K_L.gguf) | Q6_K_L | 11.53GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Phi-3-medium-128k-instruct-Q6_K.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q6_K.gguf) | Q6_K | 11.45GB | false | Very high quality, near perfect, *recommended*. | +| [Phi-3-medium-128k-instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q5_K_L.gguf) | Q5_K_L | 10.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Phi-3-medium-128k-instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q5_K_M.gguf) | Q5_K_M | 10.07GB | false | High quality, *recommended*. | +| [Phi-3-medium-128k-instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q5_K_S.gguf) | Q5_K_S | 9.62GB | false | High quality, *recommended*. | +| [Phi-3-medium-128k-instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q4_K_L.gguf) | Q4_K_L | 8.69GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Phi-3-medium-128k-instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q4_K_M.gguf) | Q4_K_M | 8.57GB | false | Good quality, default size for must use cases, *recommended*. | +| [Phi-3-medium-128k-instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q4_K_S.gguf) | Q4_K_S | 7.95GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Phi-3-medium-128k-instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q3_K_XL.gguf) | Q3_K_XL | 7.63GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Phi-3-medium-128k-instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q3_K_L.gguf) | Q3_K_L | 7.49GB | false | Lower quality but usable, good for low RAM availability. | +| [Phi-3-medium-128k-instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ4_XS.gguf) | IQ4_XS | 7.47GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Phi-3-medium-128k-instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q3_K_M.gguf) | Q3_K_M | 6.92GB | false | Low quality. | +| [Phi-3-medium-128k-instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ3_M.gguf) | IQ3_M | 6.47GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Phi-3-medium-128k-instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q3_K_S.gguf) | Q3_K_S | 6.06GB | false | Low quality, not recommended. | +| [Phi-3-medium-128k-instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ3_XS.gguf) | IQ3_XS | 5.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Phi-3-medium-128k-instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q2_K_L.gguf) | Q2_K_L | 5.30GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Phi-3-medium-128k-instruct-Q2_K.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-Q2_K.gguf) | Q2_K | 5.14GB | false | Very low quality but surprisingly usable. | +| [Phi-3-medium-128k-instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ2_M.gguf) | IQ2_M | 4.72GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Phi-3-medium-128k-instruct-IQ2_XXS.gguf](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF/blob/main/Phi-3-medium-128k-instruct-IQ2_XXS.gguf) | IQ2_XXS | 3.72GB | false | Very 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. + +Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using. + +Thanks! + +## 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 ## Downloading using huggingface-cli @@ -77,7 +95,7 @@ huggingface-cli download bartowski/Phi-3-medium-128k-instruct-GGUF --include "Ph 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/Phi-3-medium-128k-instruct-GGUF --include "Phi-3-medium-128k-instruct-Q8_0.gguf/*" --local-dir Phi-3-medium-128k-instruct-Q8_0 +huggingface-cli download bartowski/Phi-3-medium-128k-instruct-GGUF --include "Phi-3-medium-128k-instruct-Q8_0/*" --local-dir ./ ``` You can either specify a new local-dir (Phi-3-medium-128k-instruct-Q8_0) or download them all in place (./) @@ -107,3 +125,4 @@ These I-quants can also be used on CPU and Apple Metal, but will be slower than 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 +