commit 5881b17b1f8fcfbd069c1afcd970a46f99e9537b Author: ModelHub XC Date: Sun Jun 14 07:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/emma-500-llama2-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1f7859 --- /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 +emma-500-llama2-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +emma-500-llama2-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..17d4fd2 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: MaLA-LM/emma-500-llama2-7b +datasets: +- MaLA-LM/mala-monolingual-split +language: +- en +library_name: transformers +license: llama2 +no_imatrix: nan detected in blk.31.attn_q.weight +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/MaLA-LM/emma-500-llama2-7b + + +## 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/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/emma-500-llama2-7b-GGUF/resolve/main/emma-500-llama2-7b.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. + + diff --git a/emma-500-llama2-7b.IQ4_XS.gguf b/emma-500-llama2-7b.IQ4_XS.gguf new file mode 100644 index 0000000..1527619 --- /dev/null +++ b/emma-500-llama2-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d14e34109d20399f7a4662bf9d7d520476129be2c90eb227a7e5b52c840da7f +size 3647517504 diff --git a/emma-500-llama2-7b.Q2_K.gguf b/emma-500-llama2-7b.Q2_K.gguf new file mode 100644 index 0000000..653c786 --- /dev/null +++ b/emma-500-llama2-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8107402598193492b5699bae74f737158758c88ca745dbd73e789a8321eecc +size 2532864832 diff --git a/emma-500-llama2-7b.Q3_K_L.gguf b/emma-500-llama2-7b.Q3_K_L.gguf new file mode 100644 index 0000000..d7b1c9e --- /dev/null +++ b/emma-500-llama2-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b311e57c075ea013b8b84374c95ee3a5b58d3468edbc66628264cba3df3c25e1 +size 3597112128 diff --git a/emma-500-llama2-7b.Q3_K_M.gguf b/emma-500-llama2-7b.Q3_K_M.gguf new file mode 100644 index 0000000..b1096c6 --- /dev/null +++ b/emma-500-llama2-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633f41ac0cf6d075d126b7c78f5352c667c51c78bc69e1318d129120d4860da1 +size 3298005824 diff --git a/emma-500-llama2-7b.Q3_K_S.gguf b/emma-500-llama2-7b.Q3_K_S.gguf new file mode 100644 index 0000000..0ca8af7 --- /dev/null +++ b/emma-500-llama2-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb397109714737ac8b691178d2c68018eacc400f7f71e38c06a9471fb2d6b61c +size 2948305728 diff --git a/emma-500-llama2-7b.Q4_0_4_4.gguf b/emma-500-llama2-7b.Q4_0_4_4.gguf new file mode 100644 index 0000000..79cd699 --- /dev/null +++ b/emma-500-llama2-7b.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b1a54d93640de5f13753085d384c3575f7d7c063fea45a3403e81e4342723f +size 3825808192 diff --git a/emma-500-llama2-7b.Q4_K_M.gguf b/emma-500-llama2-7b.Q4_K_M.gguf new file mode 100644 index 0000000..8fbec7d --- /dev/null +++ b/emma-500-llama2-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4112c800fd7ed089eb3e63a61afaeecbb54f1ae99db54ce7023f78f77d16005c +size 4081005376 diff --git a/emma-500-llama2-7b.Q4_K_S.gguf b/emma-500-llama2-7b.Q4_K_S.gguf new file mode 100644 index 0000000..16b3dc3 --- /dev/null +++ b/emma-500-llama2-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db4bfd0ff70f131b7edb9976a341bef9bf9cb6bdd2f5a861d0814d42ffc2c82a +size 3856741184 diff --git a/emma-500-llama2-7b.Q5_K_M.gguf b/emma-500-llama2-7b.Q5_K_M.gguf new file mode 100644 index 0000000..51130a6 --- /dev/null +++ b/emma-500-llama2-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ce8315f7e3f782f0acf8d3ddb0294bc5a786019bcea2ff0cfe1ea216c230e8 +size 4783158080 diff --git a/emma-500-llama2-7b.Q5_K_S.gguf b/emma-500-llama2-7b.Q5_K_S.gguf new file mode 100644 index 0000000..ac6415d --- /dev/null +++ b/emma-500-llama2-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea39e7d5f168f5d676ebb7f6f43c11493403eabbb6edeb43ac25f36cf32a911 +size 4651692864 diff --git a/emma-500-llama2-7b.Q6_K.gguf b/emma-500-llama2-7b.Q6_K.gguf new file mode 100644 index 0000000..4d95bda --- /dev/null +++ b/emma-500-llama2-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcdd8c9a3d56dfe854fd19c328834c339f9443c1434460954a313e6e7c1d9117 +size 5529195328 diff --git a/emma-500-llama2-7b.Q8_0.gguf b/emma-500-llama2-7b.Q8_0.gguf new file mode 100644 index 0000000..b4775f1 --- /dev/null +++ b/emma-500-llama2-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4fb7e2e6042faff79f769b26e96df95d28e7c9c6994273a949462b1ea8b6b7 +size 7161090880 diff --git a/emma-500-llama2-7b.f16.gguf b/emma-500-llama2-7b.f16.gguf new file mode 100644 index 0000000..a4494f2 --- /dev/null +++ b/emma-500-llama2-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26cf07f147b502670a9ac75e7880d2515952f29c40e4e747f95ce4498577b84a +size 13478105920