From 9d18e60749026ba9d8b283b516eae7e6c4641669 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 13 Apr 2026 23:33:04 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Reflection-Llama-3.1-8B-GGUF Source: Original Platform --- .gitattributes | 49 +++++++++++++++++++++ README.md | 68 +++++++++++++++++++++++++++++ Reflection-Llama-3.1-8B.IQ3_M.gguf | 3 ++ Reflection-Llama-3.1-8B.IQ3_S.gguf | 3 ++ Reflection-Llama-3.1-8B.IQ3_XS.gguf | 3 ++ Reflection-Llama-3.1-8B.IQ4_XS.gguf | 3 ++ Reflection-Llama-3.1-8B.Q2_K.gguf | 3 ++ Reflection-Llama-3.1-8B.Q3_K_L.gguf | 3 ++ Reflection-Llama-3.1-8B.Q3_K_M.gguf | 3 ++ Reflection-Llama-3.1-8B.Q3_K_S.gguf | 3 ++ Reflection-Llama-3.1-8B.Q4_K_M.gguf | 3 ++ Reflection-Llama-3.1-8B.Q4_K_S.gguf | 3 ++ Reflection-Llama-3.1-8B.Q5_K_M.gguf | 3 ++ Reflection-Llama-3.1-8B.Q5_K_S.gguf | 3 ++ Reflection-Llama-3.1-8B.Q6_K.gguf | 3 ++ Reflection-Llama-3.1-8B.Q8_0.gguf | 3 ++ reflection-llama-3.1-8B.IQ3_M.gguf | 3 ++ reflection-llama-3.1-8B.IQ3_S.gguf | 3 ++ reflection-llama-3.1-8B.IQ3_XS.gguf | 3 ++ reflection-llama-3.1-8B.IQ4_XS.gguf | 3 ++ reflection-llama-3.1-8B.Q2_K.gguf | 3 ++ reflection-llama-3.1-8B.Q3_K_L.gguf | 3 ++ reflection-llama-3.1-8B.Q3_K_M.gguf | 3 ++ reflection-llama-3.1-8B.Q3_K_S.gguf | 3 ++ reflection-llama-3.1-8B.Q4_K_M.gguf | 3 ++ reflection-llama-3.1-8B.Q4_K_S.gguf | 3 ++ reflection-llama-3.1-8B.Q5_K_M.gguf | 3 ++ reflection-llama-3.1-8B.Q5_K_S.gguf | 3 ++ reflection-llama-3.1-8B.Q6_K.gguf | 3 ++ reflection-llama-3.1-8B.Q8_0.gguf | 3 ++ 30 files changed, 201 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 Reflection-Llama-3.1-8B.IQ3_M.gguf create mode 100644 Reflection-Llama-3.1-8B.IQ3_S.gguf create mode 100644 Reflection-Llama-3.1-8B.IQ3_XS.gguf create mode 100644 Reflection-Llama-3.1-8B.IQ4_XS.gguf create mode 100644 Reflection-Llama-3.1-8B.Q2_K.gguf create mode 100644 Reflection-Llama-3.1-8B.Q3_K_L.gguf create mode 100644 Reflection-Llama-3.1-8B.Q3_K_M.gguf create mode 100644 Reflection-Llama-3.1-8B.Q3_K_S.gguf create mode 100644 Reflection-Llama-3.1-8B.Q4_K_M.gguf create mode 100644 Reflection-Llama-3.1-8B.Q4_K_S.gguf create mode 100644 Reflection-Llama-3.1-8B.Q5_K_M.gguf create mode 100644 Reflection-Llama-3.1-8B.Q5_K_S.gguf create mode 100644 Reflection-Llama-3.1-8B.Q6_K.gguf create mode 100644 Reflection-Llama-3.1-8B.Q8_0.gguf create mode 100644 reflection-llama-3.1-8B.IQ3_M.gguf create mode 100644 reflection-llama-3.1-8B.IQ3_S.gguf create mode 100644 reflection-llama-3.1-8B.IQ3_XS.gguf create mode 100644 reflection-llama-3.1-8B.IQ4_XS.gguf create mode 100644 reflection-llama-3.1-8B.Q2_K.gguf create mode 100644 reflection-llama-3.1-8B.Q3_K_L.gguf create mode 100644 reflection-llama-3.1-8B.Q3_K_M.gguf create mode 100644 reflection-llama-3.1-8B.Q3_K_S.gguf create mode 100644 reflection-llama-3.1-8B.Q4_K_M.gguf create mode 100644 reflection-llama-3.1-8B.Q4_K_S.gguf create mode 100644 reflection-llama-3.1-8B.Q5_K_M.gguf create mode 100644 reflection-llama-3.1-8B.Q5_K_S.gguf create mode 100644 reflection-llama-3.1-8B.Q6_K.gguf create mode 100644 reflection-llama-3.1-8B.Q8_0.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..04c0116 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +Reflection-Llama-3.1-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reflection-Llama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f54d9f0 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: terrycraddock/Reflection-Llama-3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- unsloth +--- +## About + + + + + + +static quants of https://huggingface.co/terrycraddock/Reflection-Llama-3.1-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q2_K.gguf) | Q2_K | 6.5 | | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_XS.gguf) | IQ3_XS | 7.1 | | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 7.4 | | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_S.gguf) | IQ3_S | 7.5 | beats Q3_K* | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_M.gguf) | IQ3_M | 7.7 | | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 8.1 | lower quality | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 8.7 | | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 9.1 | | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 9.5 | fast, recommended | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 9.9 | fast, recommended | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 11.3 | | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 11.6 | | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q6_K.gguf) | Q6_K | 13.3 | very good quality | +| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q8_0.gguf) | Q8_0 | 17.2 | fast, best quality | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/Reflection-Llama-3.1-8B.IQ3_M.gguf b/Reflection-Llama-3.1-8B.IQ3_M.gguf new file mode 100644 index 0000000..e9e748d --- /dev/null +++ b/Reflection-Llama-3.1-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c633fbe6d2922dddf55dbd63b537a50d54eb5d41b6d080d1f1aba461c74c445 +size 3784823520 diff --git a/Reflection-Llama-3.1-8B.IQ3_S.gguf b/Reflection-Llama-3.1-8B.IQ3_S.gguf new file mode 100644 index 0000000..d500389 --- /dev/null +++ b/Reflection-Llama-3.1-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e226ad6a5654274f7688e7f7830f7392f3c7d7d63222ba4db07afd82e4e67487 +size 3682325216 diff --git a/Reflection-Llama-3.1-8B.IQ3_XS.gguf b/Reflection-Llama-3.1-8B.IQ3_XS.gguf new file mode 100644 index 0000000..d3322ca --- /dev/null +++ b/Reflection-Llama-3.1-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77f0308973dfdbc476c70238000544e9bef450dd58934d463360592f8d4154f +size 3518747360 diff --git a/Reflection-Llama-3.1-8B.IQ4_XS.gguf b/Reflection-Llama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..8778b42 --- /dev/null +++ b/Reflection-Llama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2e9c0fd5aafe2d9969a0017409201f5a69f9941e5944b03fa3e2ce7e3285e5 +size 4484362976 diff --git a/Reflection-Llama-3.1-8B.Q2_K.gguf b/Reflection-Llama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..d131008 --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea4f6ba8578c39623e705c1bc0f101d21447e3019d4590459ab509c3ee03a39d +size 3179131616 diff --git a/Reflection-Llama-3.1-8B.Q3_K_L.gguf b/Reflection-Llama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0d2102f --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff62e3924bf69412c0e76f62f31badbbb492943e969a4722493939ae30b420f3 +size 4321956576 diff --git a/Reflection-Llama-3.1-8B.Q3_K_M.gguf b/Reflection-Llama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..ae77a86 --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7bc03b5b533be60976590ba8e071c301f900a2946100f6cd7698ffeb5d1d4e +size 4018918112 diff --git a/Reflection-Llama-3.1-8B.Q3_K_S.gguf b/Reflection-Llama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..7dd0adb --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f2af7aa699574b67b59447c6913cc516be4f7e3dbe05cfe4afc5d36f647be4 +size 3664499424 diff --git a/Reflection-Llama-3.1-8B.Q4_K_M.gguf b/Reflection-Llama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..704625d --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b1c7bc1f55227ca5a8552b9902a997ac05f5044c002d6a64ab24b224c7b6e8 +size 4920734432 diff --git a/Reflection-Llama-3.1-8B.Q4_K_S.gguf b/Reflection-Llama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..79caa2c --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e4b69c47cc57a232b908b09883200eafcfdf9f52f148e24bb98f8396ae994e +size 4692669152 diff --git a/Reflection-Llama-3.1-8B.Q5_K_M.gguf b/Reflection-Llama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..988e14d --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42c52e0ffca23ec7167fa2f1b2093ac8980c4940dd35e38812716ddb9c14ab97 +size 5732987616 diff --git a/Reflection-Llama-3.1-8B.Q5_K_S.gguf b/Reflection-Llama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..c835295 --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24791f07f98cf27bbaab7cad5bca13791272a11c01bf576ec9e896bbb732f73d +size 5599294176 diff --git a/Reflection-Llama-3.1-8B.Q6_K.gguf b/Reflection-Llama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..7848c26 --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96127a4ec4ff8edec25781f3a062ec19e9f04aa4017516e81843959d8fd84f4 +size 6596006624 diff --git a/Reflection-Llama-3.1-8B.Q8_0.gguf b/Reflection-Llama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..defb793 --- /dev/null +++ b/Reflection-Llama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f91ce6aa98d9ae8a5f08f9e0597454a41705a8a019d5b01424c733b881de565 +size 8540771040 diff --git a/reflection-llama-3.1-8B.IQ3_M.gguf b/reflection-llama-3.1-8B.IQ3_M.gguf new file mode 100644 index 0000000..11bf274 --- /dev/null +++ b/reflection-llama-3.1-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6c1b8a2bbdd77d7fe925e2fa80fccf17bcd38ece596b9062edca6e0c633ea3 +size 3784829056 diff --git a/reflection-llama-3.1-8B.IQ3_S.gguf b/reflection-llama-3.1-8B.IQ3_S.gguf new file mode 100644 index 0000000..5e5e605 --- /dev/null +++ b/reflection-llama-3.1-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85c09b28999a8dcfb6d31d2f848740339ad61c4ec850da0c487d99d22b30b2a5 +size 3682330752 diff --git a/reflection-llama-3.1-8B.IQ3_XS.gguf b/reflection-llama-3.1-8B.IQ3_XS.gguf new file mode 100644 index 0000000..c76ad8a --- /dev/null +++ b/reflection-llama-3.1-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87f0db1e4e49e77c6c283106c4ad6bf1bad880fbb1eee34938ab2d56181438df +size 3518752896 diff --git a/reflection-llama-3.1-8B.IQ4_XS.gguf b/reflection-llama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..3af1f80 --- /dev/null +++ b/reflection-llama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b67162487b49fbb68dfc09923fb1214b27bb3b4c6e4ba525fd8dbd864f35565 +size 4484368512 diff --git a/reflection-llama-3.1-8B.Q2_K.gguf b/reflection-llama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..671d18b --- /dev/null +++ b/reflection-llama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a75842c3b1f8ee77f07af0e6c168bad3e281a832388edfcd7242533f99a74b2 +size 3179137152 diff --git a/reflection-llama-3.1-8B.Q3_K_L.gguf b/reflection-llama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0b7b7f8 --- /dev/null +++ b/reflection-llama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8fe97c0c1cf2fc7f5a88265033ad690786756f563d48a86379212f83a855112 +size 4321962112 diff --git a/reflection-llama-3.1-8B.Q3_K_M.gguf b/reflection-llama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..63bbe51 --- /dev/null +++ b/reflection-llama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b5139f846d3232759c08a39e924c8a50c2abe33a870c80f9ad10609d783d18 +size 4018923648 diff --git a/reflection-llama-3.1-8B.Q3_K_S.gguf b/reflection-llama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..f231436 --- /dev/null +++ b/reflection-llama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dfbd3612392190c0a6752eccd4e8f0a47021d505e8f39ea4e99312f0ca0e6a1 +size 3664504960 diff --git a/reflection-llama-3.1-8B.Q4_K_M.gguf b/reflection-llama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..e03fa3c --- /dev/null +++ b/reflection-llama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d46bf740de267a802628b172a10d8b7b784a16cb6dd81cd82152a8903c1efb +size 4920739968 diff --git a/reflection-llama-3.1-8B.Q4_K_S.gguf b/reflection-llama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..8490a09 --- /dev/null +++ b/reflection-llama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01ed99e1fb119120bad07f6438eb06a48fe4227d8981a5f115f7b3f643ba090a +size 4692674688 diff --git a/reflection-llama-3.1-8B.Q5_K_M.gguf b/reflection-llama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..3a66923 --- /dev/null +++ b/reflection-llama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60484e2b0ed8aff2538680150644b631938bf0a72400fff25987a7c87294fada +size 5732993152 diff --git a/reflection-llama-3.1-8B.Q5_K_S.gguf b/reflection-llama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..0d302a4 --- /dev/null +++ b/reflection-llama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d6a1207216b60a46be170079050eb5b2db0e6b5e724807cbf53239a74c978ee +size 5599299712 diff --git a/reflection-llama-3.1-8B.Q6_K.gguf b/reflection-llama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..84687f6 --- /dev/null +++ b/reflection-llama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e16f3597a1b28cf471b4d2be98b478835827e4c97bdae307f7d9ee3b3ca3ee7 +size 6596012160 diff --git a/reflection-llama-3.1-8B.Q8_0.gguf b/reflection-llama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..7a614a1 --- /dev/null +++ b/reflection-llama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187580d45c83ae747706cca009e87c10cc6caa3b98887426bfb4ac780864eacb +size 8540776576