commit e10d0aa16d34efca3992e07c2b3f2b0584b61a62 Author: ModelHub XC Date: Sun Sep 27 23:47:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/EssplgptLlama2-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..07dfdfc --- /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 +EssplgptLlama2-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +EssplgptLlama2-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EssplgptLlama2-7b.IQ3_M.gguf b/EssplgptLlama2-7b.IQ3_M.gguf new file mode 100644 index 0000000..051e12f --- /dev/null +++ b/EssplgptLlama2-7b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1529d1eb3da994ac9e4aebb481b87e4d64a8a12bc31c9b6ba2cf2b7da2254dd +size 3114864896 diff --git a/EssplgptLlama2-7b.IQ3_S.gguf b/EssplgptLlama2-7b.IQ3_S.gguf new file mode 100644 index 0000000..77aedb1 --- /dev/null +++ b/EssplgptLlama2-7b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:996606b7cdf5ede0492d41b581f84ae151bed2e22a428fa4c2a727e2bc6addb6 +size 2948305152 diff --git a/EssplgptLlama2-7b.IQ3_XS.gguf b/EssplgptLlama2-7b.IQ3_XS.gguf new file mode 100644 index 0000000..58f1f68 --- /dev/null +++ b/EssplgptLlama2-7b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e2c03eb7efab5d1bc0f9c81565da0ae607840d86d0c795e29b62b96ee20365 +size 2796523776 diff --git a/EssplgptLlama2-7b.IQ4_XS.gguf b/EssplgptLlama2-7b.IQ4_XS.gguf new file mode 100644 index 0000000..e22b811 --- /dev/null +++ b/EssplgptLlama2-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96776900eeb389db1dbd1a4e3046459fd425e9fe0bacf507403e3cd5310efb72 +size 3647516928 diff --git a/EssplgptLlama2-7b.Q2_K.gguf b/EssplgptLlama2-7b.Q2_K.gguf new file mode 100644 index 0000000..11f2b2d --- /dev/null +++ b/EssplgptLlama2-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48949fff94ec98669911be29e0bf62fcfaadeb40dac28ad3131a1d6d4fb2566f +size 2532864256 diff --git a/EssplgptLlama2-7b.Q3_K_L.gguf b/EssplgptLlama2-7b.Q3_K_L.gguf new file mode 100644 index 0000000..caca6fa --- /dev/null +++ b/EssplgptLlama2-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b768b6717c46eb70822cd6e84d6d544b1ee0a8108a4e406f4ad03a893589001 +size 3597111552 diff --git a/EssplgptLlama2-7b.Q3_K_M.gguf b/EssplgptLlama2-7b.Q3_K_M.gguf new file mode 100644 index 0000000..9b80577 --- /dev/null +++ b/EssplgptLlama2-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4189db64e9dd27ce1d9e7c9c83db7501b074be8356324e8b68cffc5762e83c68 +size 3298005248 diff --git a/EssplgptLlama2-7b.Q3_K_S.gguf b/EssplgptLlama2-7b.Q3_K_S.gguf new file mode 100644 index 0000000..7caea1c --- /dev/null +++ b/EssplgptLlama2-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08de4ac42582924d325be3d537f91a8983a2fd343e1e974b1cf1bb68b075bae +size 2948305152 diff --git a/EssplgptLlama2-7b.Q4_K_M.gguf b/EssplgptLlama2-7b.Q4_K_M.gguf new file mode 100644 index 0000000..c38ac9d --- /dev/null +++ b/EssplgptLlama2-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595a971d63f43d8d1698cffe0c40c1e24b393a35ce1d61b9c13003c3b5f1c2c4 +size 4081004800 diff --git a/EssplgptLlama2-7b.Q4_K_S.gguf b/EssplgptLlama2-7b.Q4_K_S.gguf new file mode 100644 index 0000000..cf47490 --- /dev/null +++ b/EssplgptLlama2-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3302103d4db5b868967799b79d473b2261c4578853cdae9d88edb260f4a3ff30 +size 3856740608 diff --git a/EssplgptLlama2-7b.Q5_K_M.gguf b/EssplgptLlama2-7b.Q5_K_M.gguf new file mode 100644 index 0000000..4351142 --- /dev/null +++ b/EssplgptLlama2-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:687f82cc203fe5223a4b859aaa65048d3c8ff418edaa9f46d28f41b8f4687d44 +size 4783157504 diff --git a/EssplgptLlama2-7b.Q5_K_S.gguf b/EssplgptLlama2-7b.Q5_K_S.gguf new file mode 100644 index 0000000..64b8515 --- /dev/null +++ b/EssplgptLlama2-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520c6b0043b7d1c9203e0f0565d0724c2c9cd5acca06b6030d2ed112fbdeab9b +size 4651692288 diff --git a/EssplgptLlama2-7b.Q6_K.gguf b/EssplgptLlama2-7b.Q6_K.gguf new file mode 100644 index 0000000..e60f725 --- /dev/null +++ b/EssplgptLlama2-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad3e63de44019f10e5eaa70edec54a0c4caae33d0853688aedf53432c68250a +size 5529194752 diff --git a/EssplgptLlama2-7b.Q8_0.gguf b/EssplgptLlama2-7b.Q8_0.gguf new file mode 100644 index 0000000..6cfc32d --- /dev/null +++ b/EssplgptLlama2-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5f8efcdf052694112d06fa36a65582d7ff5de6004c5e9315ca4696ea09ed60 +size 7161090304 diff --git a/EssplgptLlama2-7b.f16.gguf b/EssplgptLlama2-7b.f16.gguf new file mode 100644 index 0000000..3f4c2f9 --- /dev/null +++ b/EssplgptLlama2-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5836001de06d6b58e27af754109f2894bb0e0867fb49861970d4f99352c10717 +size 13478105344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..515ac34 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: sunilswain/EssplgptLlama2-7b +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/sunilswain/EssplgptLlama2-7b + + +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/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/EssplgptLlama2-7b-GGUF/resolve/main/EssplgptLlama2-7b.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. + +