commit 4c42b082804ca0e19939f0b6ec2e5eb9702bedf4 Author: ModelHub XC Date: Sun Sep 27 02:37:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Base-Instruct-Slerp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..28dab48 --- /dev/null +++ b/.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 +*.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 +Llama-3-Base-Instruct-Slerp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Base-Instruct-Slerp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Base-Instruct-Slerp.IQ4_XS.gguf b/Llama-3-Base-Instruct-Slerp.IQ4_XS.gguf new file mode 100644 index 0000000..20fb9a0 --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c152b452d1c08eaf3a656ede5d334634f7a7ef8db81532635e01799af144db92 +size 4484363360 diff --git a/Llama-3-Base-Instruct-Slerp.Q2_K.gguf b/Llama-3-Base-Instruct-Slerp.Q2_K.gguf new file mode 100644 index 0000000..82e9e6d --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7269b369a4a871178f298b32c38280d7cadddf1a1ca3075a83c80460eb1da92a +size 3179132000 diff --git a/Llama-3-Base-Instruct-Slerp.Q3_K_L.gguf b/Llama-3-Base-Instruct-Slerp.Q3_K_L.gguf new file mode 100644 index 0000000..5ffa574 --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99cfda79bd9d8f0b769e3839dd7a2f888ebadef54c69fb7b9b8a9de9bc8e8e2f +size 4321956960 diff --git a/Llama-3-Base-Instruct-Slerp.Q3_K_M.gguf b/Llama-3-Base-Instruct-Slerp.Q3_K_M.gguf new file mode 100644 index 0000000..5769657 --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec00544d0f1838b80051d44ac6bd1aa241502a8d0c16c8a1535d2c4ea9cf9ca9 +size 4018918496 diff --git a/Llama-3-Base-Instruct-Slerp.Q3_K_S.gguf b/Llama-3-Base-Instruct-Slerp.Q3_K_S.gguf new file mode 100644 index 0000000..77fbfbc --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3dffd1b0c28f68a69aab1fc45ad0379d3cdcaf62700e2b0ac41fc23c222f360 +size 3664499808 diff --git a/Llama-3-Base-Instruct-Slerp.Q4_K_M.gguf b/Llama-3-Base-Instruct-Slerp.Q4_K_M.gguf new file mode 100644 index 0000000..76ad33c --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc26bcddb49f9cbd1a647450bfb14fb0f735324984793b40a47d8caa5ec4364 +size 4920734816 diff --git a/Llama-3-Base-Instruct-Slerp.Q4_K_S.gguf b/Llama-3-Base-Instruct-Slerp.Q4_K_S.gguf new file mode 100644 index 0000000..9f92b33 --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca67f910777f5fc2a1a15e6dfbf2c25eca3cc2c15e5056e425302423185c817 +size 4692669536 diff --git a/Llama-3-Base-Instruct-Slerp.Q5_K_M.gguf b/Llama-3-Base-Instruct-Slerp.Q5_K_M.gguf new file mode 100644 index 0000000..730863b --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c9b80393810f7e68afeb424a9ddb4148b9118b543135fd52c59a83ae6ea015 +size 5732988000 diff --git a/Llama-3-Base-Instruct-Slerp.Q5_K_S.gguf b/Llama-3-Base-Instruct-Slerp.Q5_K_S.gguf new file mode 100644 index 0000000..1b343ca --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22fab2c0ef01c89d9e9a073120e97335b9e327d64fb539b26ae4965ef1d4f072 +size 5599294560 diff --git a/Llama-3-Base-Instruct-Slerp.Q6_K.gguf b/Llama-3-Base-Instruct-Slerp.Q6_K.gguf new file mode 100644 index 0000000..ee275c9 --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9676e5dd53564dc320af55f05cf20b0b6b5c4366dcb3d13149c8644e858785ab +size 6596007008 diff --git a/Llama-3-Base-Instruct-Slerp.Q8_0.gguf b/Llama-3-Base-Instruct-Slerp.Q8_0.gguf new file mode 100644 index 0000000..4257125 --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd81674cecca270517c8b2e0c5ea49ecfc1c39add7555a2cf5452154e9ce670e +size 8540771424 diff --git a/Llama-3-Base-Instruct-Slerp.f16.gguf b/Llama-3-Base-Instruct-Slerp.f16.gguf new file mode 100644 index 0000000..166c858 --- /dev/null +++ b/Llama-3-Base-Instruct-Slerp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bedc2f02b09f0c1e1b1d33a7c38a91a80da2cbfad1449e5153321a307ea26401 +size 16068891744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..57567ce --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: arcee-ai/Llama-3-Base-Instruct-Slerp +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- meta-llama/Meta-Llama-3-8B +- meta-llama/Meta-Llama-3-8B-Instruct +--- +## About + + + + + + +static quants of https://huggingface.co/arcee-ai/Llama-3-Base-Instruct-Slerp + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-Base-Instruct-Slerp-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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 | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Base-Instruct-Slerp-GGUF/resolve/main/Llama-3-Base-Instruct-Slerp.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +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. + +