commit 0701a99a899e25a424b5d30b5d7056a5eb77986a Author: ModelHub XC Date: Sun Jul 19 12:05:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..da566f2 --- /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 +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.IQ4_XS.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..60a76c2 --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c13845936eeae28471af7f56dc28edbdda9eec2fa0c42770c67ac6443834aefe +size 3647517984 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q2_K.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q2_K.gguf new file mode 100644 index 0000000..532e44b --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fbf09d64c0fd2947692f01014d0e6f102003d21756d3eb03cd6d6d62d4e35ec +size 2532865312 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_L.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c874a76 --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41f2d7f5b79b2f5b5bf4aab126f0ae90137381b4ace39647973363cf0dda64c +size 3597112608 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_M.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..933b33f --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b21b800beecb83a2b527e0a55f3be8a91c3025be409164e9aa51f4a31af531b6 +size 3298006304 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_S.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c1d9c37 --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629f8b889d58ed2941a604eee9bd1b8b374e65b6fa12b0ae4817b09b2baf566c +size 2948306208 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_0_4_4.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..3a47230 --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c4d7046c2076f5413329b82482be443475fa753bab7824e99e68520d445caf6 +size 3825808672 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_M.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..7b0b523 --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c462b4874cc09bdfa6c95cf7ec53ed50e02f8ddf884cc35ea191a36bac7bee72 +size 4081005856 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_S.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..08fbfbb --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a084adac093ded95efd29dc1ac21f1327f5abf22e3aba0fa0ed8940e999972a0 +size 3856741664 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_M.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..6ff76b3 --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827eec65691cb50663f02782fc67d717159f59aba576402e5692e87afa7c70c7 +size 4783158560 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_S.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..6d9935d --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e68c8afbf6babfe2d115a6778de06dca661fb739dcf3e25be94288cb29f6aa +size 4651693344 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q6_K.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q6_K.gguf new file mode 100644 index 0000000..26fe82d --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a506200d8b87086b1c1546e638724282992eac607bc13b1666e6becaf2277e +size 5529195808 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q8_0.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q8_0.gguf new file mode 100644 index 0000000..4a15a28 --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aa3d7d7aa77cbc179bf5747c23fc44efc26ab14dddb0def9ae443e22dc672d0 +size 7161091360 diff --git a/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.f16.gguf b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.f16.gguf new file mode 100644 index 0000000..0aba6a4 --- /dev/null +++ b/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27da865f529ff734ff1f88bce094e7c642994645835c2f8f56d0501cd941f9a +size 13478106400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f4068e2 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct + + +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/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct-GGUF/resolve/main/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct.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. + +