commit fd9d79f31729687ce1bb4532c9002c9f594651b9 Author: ModelHub XC Date: Wed Sep 30 16:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Emollama-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c0dcaf --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Emollama-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Emollama-7b.IQ4_XS.gguf b/Emollama-7b.IQ4_XS.gguf new file mode 100644 index 0000000..cd968e8 --- /dev/null +++ b/Emollama-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a25d923e5d38baa8bb8617d858efc9e79ade8d075832274974f89af2fc4fdd77 +size 3647517120 diff --git a/Emollama-7b.Q2_K.gguf b/Emollama-7b.Q2_K.gguf new file mode 100644 index 0000000..3a253c5 --- /dev/null +++ b/Emollama-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e49819142209e14679a03a2f279277a051adb6db600a531aea7420013f2c07a +size 2532864448 diff --git a/Emollama-7b.Q3_K_L.gguf b/Emollama-7b.Q3_K_L.gguf new file mode 100644 index 0000000..b3e9d50 --- /dev/null +++ b/Emollama-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feff2ab32d701365e79c39b96bee2bf4cbac1315fc8690cc463c27b3a8b20393 +size 3597111744 diff --git a/Emollama-7b.Q3_K_M.gguf b/Emollama-7b.Q3_K_M.gguf new file mode 100644 index 0000000..8b05f37 --- /dev/null +++ b/Emollama-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0da548b3e59a9577b8436d0ec0b07c26171926328c5337a0ba51bf17d99ae8 +size 3298005440 diff --git a/Emollama-7b.Q3_K_S.gguf b/Emollama-7b.Q3_K_S.gguf new file mode 100644 index 0000000..0f6de16 --- /dev/null +++ b/Emollama-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c60e8f22f39749147855a929a411d1905eda17c9a65ef7d515dbde1dbdcca08 +size 2948305344 diff --git a/Emollama-7b.Q4_K_M.gguf b/Emollama-7b.Q4_K_M.gguf new file mode 100644 index 0000000..0a7878f --- /dev/null +++ b/Emollama-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff0fdf2c3643f2f98fd954f7c68f52e241e6771672020d6fba6c929bcdb87276 +size 4081004992 diff --git a/Emollama-7b.Q4_K_S.gguf b/Emollama-7b.Q4_K_S.gguf new file mode 100644 index 0000000..71db0d1 --- /dev/null +++ b/Emollama-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee30e1cec64df542b32406d3a594ccac3cb84f3bec89b9d80ba433d90137735d +size 3856740800 diff --git a/Emollama-7b.Q5_K_M.gguf b/Emollama-7b.Q5_K_M.gguf new file mode 100644 index 0000000..253f3c5 --- /dev/null +++ b/Emollama-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86fb5036823c0f17771bb1393a3a31ddc502bf72322dbbe15efe2df8a7bd214d +size 4783157696 diff --git a/Emollama-7b.Q5_K_S.gguf b/Emollama-7b.Q5_K_S.gguf new file mode 100644 index 0000000..7e7962b --- /dev/null +++ b/Emollama-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2a07ccc72b633f161babd792639c9663701d9879c60db1fe1a2fc91ff066397 +size 4651692480 diff --git a/Emollama-7b.Q6_K.gguf b/Emollama-7b.Q6_K.gguf new file mode 100644 index 0000000..ca4873d --- /dev/null +++ b/Emollama-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a778d110a06b70bb5f1ad0c7e460bbf7a990d857fae6128989d96c30c92f3066 +size 5529194944 diff --git a/Emollama-7b.Q8_0.gguf b/Emollama-7b.Q8_0.gguf new file mode 100644 index 0000000..2bff29c --- /dev/null +++ b/Emollama-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534645a3bb7d5c8654f872feefb9b9f76c842e247025d6fa5ef6bb5d1b90a0a6 +size 7161090496 diff --git a/Emollama-7b.f16.gguf b/Emollama-7b.f16.gguf new file mode 100644 index 0000000..a40eb27 --- /dev/null +++ b/Emollama-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38de387311c79a0ccd03a4446e265de138905b90158689fb02a5e59878727f5d +size 13478105536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4516134 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: lzw1008/Emollama-7b +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lzw1008/Emollama-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Emollama-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/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Emollama-7b-GGUF/resolve/main/Emollama-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. + +