commit 8cfebec7c82d29ea0d1ff15f673a8dad92915b5d Author: ModelHub XC Date: Mon Sep 21 17:24:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mammoth_llama2_7b_full-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d553d8b --- /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 +mammoth_llama2_7b_full.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.f16.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mammoth_llama2_7b_full.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0609c88 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: jura23ssic/mammoth_llama2_7b_full +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/jura23ssic/mammoth_llama2_7b_full + + +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/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/mammoth_llama2_7b_full-GGUF/resolve/main/mammoth_llama2_7b_full.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. + + diff --git a/mammoth_llama2_7b_full.IQ3_M.gguf b/mammoth_llama2_7b_full.IQ3_M.gguf new file mode 100644 index 0000000..ad99a8d --- /dev/null +++ b/mammoth_llama2_7b_full.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df640582a98878ca3e9caf21bb3476968aee4c8782db796d6e7975d74444f48 +size 3114870080 diff --git a/mammoth_llama2_7b_full.IQ3_S.gguf b/mammoth_llama2_7b_full.IQ3_S.gguf new file mode 100644 index 0000000..8510f57 --- /dev/null +++ b/mammoth_llama2_7b_full.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c67777f7d2e06bcab42be4b144b5fc99d745f185ea71497416d8c4cb417ffb8e +size 2948310336 diff --git a/mammoth_llama2_7b_full.IQ3_XS.gguf b/mammoth_llama2_7b_full.IQ3_XS.gguf new file mode 100644 index 0000000..9ddf15d --- /dev/null +++ b/mammoth_llama2_7b_full.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a38cc19b3114f9337d9eee25e648fbbba3a2c4d7355cd8f9d18910f944a5b7 +size 2796528960 diff --git a/mammoth_llama2_7b_full.IQ4_XS.gguf b/mammoth_llama2_7b_full.IQ4_XS.gguf new file mode 100644 index 0000000..cea5499 --- /dev/null +++ b/mammoth_llama2_7b_full.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5541c5a1b0cb4caf89ba64682c0bab9907759f983440d7212c10d62127812f05 +size 3647522528 diff --git a/mammoth_llama2_7b_full.Q2_K.gguf b/mammoth_llama2_7b_full.Q2_K.gguf new file mode 100644 index 0000000..f645f39 --- /dev/null +++ b/mammoth_llama2_7b_full.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd283522ce9b6b4ae1fd9f63a301c4117e7d6831bc53eb94a7717f681557c70c +size 2532869024 diff --git a/mammoth_llama2_7b_full.Q3_K_L.gguf b/mammoth_llama2_7b_full.Q3_K_L.gguf new file mode 100644 index 0000000..c975ace --- /dev/null +++ b/mammoth_llama2_7b_full.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f482ef2672a902dea1b8f12278cb1fdb02989bed38c3e087489d4a99f8344817 +size 3597116736 diff --git a/mammoth_llama2_7b_full.Q3_K_M.gguf b/mammoth_llama2_7b_full.Q3_K_M.gguf new file mode 100644 index 0000000..7d162a8 --- /dev/null +++ b/mammoth_llama2_7b_full.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d5c2e4560098f1e3014a26cd8ed1a08ba35444325a26944fbae721e232fe51 +size 3298010432 diff --git a/mammoth_llama2_7b_full.Q3_K_S.gguf b/mammoth_llama2_7b_full.Q3_K_S.gguf new file mode 100644 index 0000000..d13d75d --- /dev/null +++ b/mammoth_llama2_7b_full.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73537d265e5db0b39469388ce75662efd2dd94920ea090714d9eaaa381fcecb +size 2948310336 diff --git a/mammoth_llama2_7b_full.Q4_K_M.gguf b/mammoth_llama2_7b_full.Q4_K_M.gguf new file mode 100644 index 0000000..fac185e --- /dev/null +++ b/mammoth_llama2_7b_full.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dffcfe271bcb7d23589c011a542fd9a2bd0a22b64b28c1bc52dc8e9a8887171 +size 4081010528 diff --git a/mammoth_llama2_7b_full.Q4_K_S.gguf b/mammoth_llama2_7b_full.Q4_K_S.gguf new file mode 100644 index 0000000..99d26c0 --- /dev/null +++ b/mammoth_llama2_7b_full.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef7825a7bedf3a752460db0caa83d80165747af37853934446a73d42e1de81ce +size 3856746336 diff --git a/mammoth_llama2_7b_full.Q5_K_M.gguf b/mammoth_llama2_7b_full.Q5_K_M.gguf new file mode 100644 index 0000000..8b6506c --- /dev/null +++ b/mammoth_llama2_7b_full.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20af614bda8b81c78e9bdb6ad83dc4fbbe976cce01d4ab51cc3b968bc61c8dc8 +size 4783163744 diff --git a/mammoth_llama2_7b_full.Q5_K_S.gguf b/mammoth_llama2_7b_full.Q5_K_S.gguf new file mode 100644 index 0000000..903bb3b --- /dev/null +++ b/mammoth_llama2_7b_full.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecb12a04f7acadb83b8946aa8d083a303c8166319275977f6376c00601f4a199 +size 4651698528 diff --git a/mammoth_llama2_7b_full.Q6_K.gguf b/mammoth_llama2_7b_full.Q6_K.gguf new file mode 100644 index 0000000..66740ca --- /dev/null +++ b/mammoth_llama2_7b_full.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b593ac3c71709477c53d1c884a803b4f4a6f41cfbe98f93ed7ff4abf210277ac +size 5529201536 diff --git a/mammoth_llama2_7b_full.Q8_0.gguf b/mammoth_llama2_7b_full.Q8_0.gguf new file mode 100644 index 0000000..62a8b13 --- /dev/null +++ b/mammoth_llama2_7b_full.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9bd32d339850317142822ab11211f8b53db3aef10c47d8e52f9b5e6140334d7 +size 7161099072 diff --git a/mammoth_llama2_7b_full.f16.gguf b/mammoth_llama2_7b_full.f16.gguf new file mode 100644 index 0000000..fb53623 --- /dev/null +++ b/mammoth_llama2_7b_full.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09752a0c37758c8bb5aa752e20f9d14b40d3b61815d62c6cce8842d8f1aeeb99 +size 13478121792