commit 49319c57b73de3a12359853b949c53b042bac2ca Author: ModelHub XC Date: Thu Jun 18 09:40:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-base-instruct-gradient-1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88ac8f6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +llama3.1-base-instruct-gradient-1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-base-instruct-gradient-1.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bf28663 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: deltanym/llama3.1-base-instruct-gradient-1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/deltanym/llama3.1-base-instruct-gradient-1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.1-base-instruct-gradient-1-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/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-base-instruct-gradient-1-GGUF/resolve/main/llama3.1-base-instruct-gradient-1.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. + + diff --git a/llama3.1-base-instruct-gradient-1.IQ4_XS.gguf b/llama3.1-base-instruct-gradient-1.IQ4_XS.gguf new file mode 100644 index 0000000..aa5ad66 --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38577a64b9eedb5989b9df952a1442c3da122e1cceddaebf1c9241044b35c59d +size 4484368384 diff --git a/llama3.1-base-instruct-gradient-1.Q2_K.gguf b/llama3.1-base-instruct-gradient-1.Q2_K.gguf new file mode 100644 index 0000000..8601402 --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee8c059a85ff285f4148ae97a1a11612e5b456e629b87d394542b3aced679d3 +size 3179137024 diff --git a/llama3.1-base-instruct-gradient-1.Q3_K_L.gguf b/llama3.1-base-instruct-gradient-1.Q3_K_L.gguf new file mode 100644 index 0000000..e37880f --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b5818ace4ead870ea539808f4565f1a48385c1297349909ebe15228bd8edf0 +size 4321961984 diff --git a/llama3.1-base-instruct-gradient-1.Q3_K_M.gguf b/llama3.1-base-instruct-gradient-1.Q3_K_M.gguf new file mode 100644 index 0000000..d64de2d --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46722cc6d6189dc1a76171d80c63ac5b6047eac729ca819ba8030eb8cf16f035 +size 4018923520 diff --git a/llama3.1-base-instruct-gradient-1.Q3_K_S.gguf b/llama3.1-base-instruct-gradient-1.Q3_K_S.gguf new file mode 100644 index 0000000..ab43a12 --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18db09728da2bbd6110f4f609e97683465adb39755366662b3e030448764eabb +size 3664504832 diff --git a/llama3.1-base-instruct-gradient-1.Q4_0_4_4.gguf b/llama3.1-base-instruct-gradient-1.Q4_0_4_4.gguf new file mode 100644 index 0000000..b3440e2 --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0cd3ff9d06dff630702d928bc776e9a6018b692b29d3f0664d4c1c37ce56ea +size 4661217280 diff --git a/llama3.1-base-instruct-gradient-1.Q4_K_M.gguf b/llama3.1-base-instruct-gradient-1.Q4_K_M.gguf new file mode 100644 index 0000000..b8c9c75 --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20736494324b6e594f8becd4ee58110738595dde82cc63642449100850445305 +size 4920739840 diff --git a/llama3.1-base-instruct-gradient-1.Q4_K_S.gguf b/llama3.1-base-instruct-gradient-1.Q4_K_S.gguf new file mode 100644 index 0000000..09728eb --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585592fbb9350caab52e4b733e6f329fcdf489f75c91ae9a0b6e6e27aaa4559d +size 4692674560 diff --git a/llama3.1-base-instruct-gradient-1.Q5_K_M.gguf b/llama3.1-base-instruct-gradient-1.Q5_K_M.gguf new file mode 100644 index 0000000..1c6009e --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9cf5ba4dcdb456e98585904c0f60b37f31d630514528bfb65d801ba37d0c4b7 +size 5732993024 diff --git a/llama3.1-base-instruct-gradient-1.Q5_K_S.gguf b/llama3.1-base-instruct-gradient-1.Q5_K_S.gguf new file mode 100644 index 0000000..09555f8 --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9553aaf9f78871c2bd26c18a08a549166896ab70faeacd0e3afb5c6a8bef72cd +size 5599299584 diff --git a/llama3.1-base-instruct-gradient-1.Q6_K.gguf b/llama3.1-base-instruct-gradient-1.Q6_K.gguf new file mode 100644 index 0000000..ddaa9d9 --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bcc0748bfbc684b8dc3bc4ad30aaf258d779e608845f6b770021a05f2040418 +size 6596012032 diff --git a/llama3.1-base-instruct-gradient-1.Q8_0.gguf b/llama3.1-base-instruct-gradient-1.Q8_0.gguf new file mode 100644 index 0000000..e7138fa --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f9d57a7f075d5133b00e9e55fe7e21c810a651ba5ec08c22e6c70ad15d11a8 +size 8540776448 diff --git a/llama3.1-base-instruct-gradient-1.f16.gguf b/llama3.1-base-instruct-gradient-1.f16.gguf new file mode 100644 index 0000000..89ada55 --- /dev/null +++ b/llama3.1-base-instruct-gradient-1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3c9e690b2fd0ac665c831b7e11998bc880a85475f06d00369c90b54e18b3e3 +size 16068896768