commit 33fdc4387c167a867fc8ee04d5b8f56756bc77be Author: ModelHub XC Date: Thu Jun 4 02:09:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaGramma-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..94e6736 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +LlamaGramma-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaGramma-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaGramma-7b.IQ3_M.gguf b/LlamaGramma-7b.IQ3_M.gguf new file mode 100644 index 0000000..646ef06 --- /dev/null +++ b/LlamaGramma-7b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4b8769661ca6a8bd788ff3b785bdb6af7182ba23b4db37c120acd240a2d198 +size 3114864960 diff --git a/LlamaGramma-7b.IQ3_S.gguf b/LlamaGramma-7b.IQ3_S.gguf new file mode 100644 index 0000000..e132399 --- /dev/null +++ b/LlamaGramma-7b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff67ee1c3f9437e7045930693182220b09974eb308494d61157a472dd8bb166 +size 2948305216 diff --git a/LlamaGramma-7b.IQ3_XS.gguf b/LlamaGramma-7b.IQ3_XS.gguf new file mode 100644 index 0000000..2115db6 --- /dev/null +++ b/LlamaGramma-7b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c678631386f5cc3dcdd96e66cee24724b0f1137706073b66da450bf855b4468a +size 2796523840 diff --git a/LlamaGramma-7b.IQ4_XS.gguf b/LlamaGramma-7b.IQ4_XS.gguf new file mode 100644 index 0000000..11e2f65 --- /dev/null +++ b/LlamaGramma-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bd76cd8af60f11a95c8cd5a69c360edc0a4fde12ffef27fc647a00e3f1d23ba +size 3647516992 diff --git a/LlamaGramma-7b.Q2_K.gguf b/LlamaGramma-7b.Q2_K.gguf new file mode 100644 index 0000000..dddaeb7 --- /dev/null +++ b/LlamaGramma-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8208959cd14ebffb049154ade52fe216107eae9cd32ac977a91f85c2a106e46b +size 2532864320 diff --git a/LlamaGramma-7b.Q3_K_L.gguf b/LlamaGramma-7b.Q3_K_L.gguf new file mode 100644 index 0000000..8302375 --- /dev/null +++ b/LlamaGramma-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39de1ead10b51ecf39894157328ac836c5d6a5d2db78cb99c32c40ac2e92a29 +size 3597111616 diff --git a/LlamaGramma-7b.Q3_K_M.gguf b/LlamaGramma-7b.Q3_K_M.gguf new file mode 100644 index 0000000..bd5c250 --- /dev/null +++ b/LlamaGramma-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6b0a16ba8d7abb0f7007dcdac1457d240b8489d556083ea97ea6d9dfd74543f +size 3298005312 diff --git a/LlamaGramma-7b.Q3_K_S.gguf b/LlamaGramma-7b.Q3_K_S.gguf new file mode 100644 index 0000000..7daa8e9 --- /dev/null +++ b/LlamaGramma-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9975e6a833c5202ff45a381d6d177a0ddb1099ad137ae6357c1de37cd65240 +size 2948305216 diff --git a/LlamaGramma-7b.Q4_K_M.gguf b/LlamaGramma-7b.Q4_K_M.gguf new file mode 100644 index 0000000..dd1f3f2 --- /dev/null +++ b/LlamaGramma-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2042103988c0fa8e391db60ac84bbf91f8171e5bb6d0669c693f27dddfc647c1 +size 4081004864 diff --git a/LlamaGramma-7b.Q4_K_S.gguf b/LlamaGramma-7b.Q4_K_S.gguf new file mode 100644 index 0000000..1459045 --- /dev/null +++ b/LlamaGramma-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4024167eb0febe93c87cf7f5a6b5150688c8d2be7fa503613311cb29b6dde30 +size 3856740672 diff --git a/LlamaGramma-7b.Q5_K_M.gguf b/LlamaGramma-7b.Q5_K_M.gguf new file mode 100644 index 0000000..f33eea9 --- /dev/null +++ b/LlamaGramma-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca9c36555f474553a01f18e8a3b3d3446f2eeac8a1cfd6c0cd3e8a2790d6cc2 +size 4783157568 diff --git a/LlamaGramma-7b.Q5_K_S.gguf b/LlamaGramma-7b.Q5_K_S.gguf new file mode 100644 index 0000000..c1a1173 --- /dev/null +++ b/LlamaGramma-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:088edc6cedfab8fdb0646a8d5463b7da64b65bd7fe8ed6acd8341a1653688f12 +size 4651692352 diff --git a/LlamaGramma-7b.Q6_K.gguf b/LlamaGramma-7b.Q6_K.gguf new file mode 100644 index 0000000..238af23 --- /dev/null +++ b/LlamaGramma-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e85e5d51b2748ccc60ce981b121be4896ff43bc432a7a8389673944887bba83b +size 5529194816 diff --git a/LlamaGramma-7b.Q8_0.gguf b/LlamaGramma-7b.Q8_0.gguf new file mode 100644 index 0000000..480f20e --- /dev/null +++ b/LlamaGramma-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77492443ab0f32e5f8db9d8a4df64682f262d138b88dc25cc3de1d3e6b3942f0 +size 7161090368 diff --git a/LlamaGramma-7b.f16.gguf b/LlamaGramma-7b.f16.gguf new file mode 100644 index 0000000..7911ef3 --- /dev/null +++ b/LlamaGramma-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9a6e022b62b2a9d7c891a7d0be1baa452e5f7d80854c0d4ad6692eb4dd15ca +size 13478105408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9343d5f --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Gryphe/LlamaGramma-7b +datasets: +- Gryphe/CoEdit-Alpaca +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Gryphe/LlamaGramma-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LlamaGramma-7b-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 | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaGramma-7b-GGUF/resolve/main/LlamaGramma-7b.f16.gguf) | f16 | 13.6 | 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. + +