commit f6417a817b941837212270f4cb4c02851aea2260 Author: ModelHub XC Date: Sun Jul 5 20:58:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2d5b3a8 --- /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 +Logical-elyza-llama2-7b-fast-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Logical-elyza-llama2-7b-fast-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Logical-elyza-llama2-7b-fast-instruct.IQ3_M.gguf b/Logical-elyza-llama2-7b-fast-instruct.IQ3_M.gguf new file mode 100644 index 0000000..91cd69f --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afb15641b9d794c53f2ac4b947c6298d7fc74c4c6dee755b8808cafeea8ada9c +size 3114865088 diff --git a/Logical-elyza-llama2-7b-fast-instruct.IQ3_S.gguf b/Logical-elyza-llama2-7b-fast-instruct.IQ3_S.gguf new file mode 100644 index 0000000..b6a9361 --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6892742aca644b738f46cc1c14bd01677d195caa83bbdd4c1fc29567353abf37 +size 2948305344 diff --git a/Logical-elyza-llama2-7b-fast-instruct.IQ3_XS.gguf b/Logical-elyza-llama2-7b-fast-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..202ac81 --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5676cc71e1ccc118837eb62cfcedabc59c26775e9f9f96c08dcaced260c30f3d +size 2796523968 diff --git a/Logical-elyza-llama2-7b-fast-instruct.IQ4_XS.gguf b/Logical-elyza-llama2-7b-fast-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..ab093c4 --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699281c6a2bbd53bd74b90a80c94022d8dd487307a87a6eb55eff15285111ef3 +size 3647517120 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q2_K.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q2_K.gguf new file mode 100644 index 0000000..253e0ac --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e0179924d05c8153a08859666c0b5c3b7a5a39c29370cff9ed8e8fbf3fd654 +size 2532864448 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q3_K_L.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..fe98dea --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db839e1885a905b03229b286d7d507552e60ab5af882c03f11a2514c766cb8a +size 3597111744 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q3_K_M.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..624a764 --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c3e36b2a79a5b43cb64be18efa4ce7c3b67701d3603a49a096fde3cb179cbe +size 3298005440 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q3_K_S.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..1ee6c98 --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcdcd157258908cb99e5177eb612654d011e2256c5e461925d9d92e1db28d100 +size 2948305344 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q4_K_M.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..82a185a --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ebfac0e908043f7137db966e5c39640b0805ce08218cae3649175cacffcbba +size 4081004992 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q4_K_S.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..338263b --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2037517e89b9625fba42a5c63fe04b3ec2edb3e1722ac43713658fcfcb640ca +size 3856740800 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q5_K_M.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..e989aa6 --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a30fe978cc77fd5738479a1a3d03a1a7c67be12daaeb2a6828b09b9369eb9ff +size 4783157696 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q5_K_S.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..4a85e8f --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37ef87e506896f6882ab3ca43e9a852cc95cfc207d892dbe5079a0dd48b0bf1b +size 4651692480 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q6_K.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q6_K.gguf new file mode 100644 index 0000000..7902834 --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c194576df68d5e4c9a442d8c5720012c4f28e930cbfa01a00619557a249de038 +size 5529194944 diff --git a/Logical-elyza-llama2-7b-fast-instruct.Q8_0.gguf b/Logical-elyza-llama2-7b-fast-instruct.Q8_0.gguf new file mode 100644 index 0000000..8163e09 --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9382eb34b78b46b3db8f37c5bb15776b2e700ebc8c4d15fd4375cca428d95643 +size 7161090496 diff --git a/Logical-elyza-llama2-7b-fast-instruct.f16.gguf b/Logical-elyza-llama2-7b-fast-instruct.f16.gguf new file mode 100644 index 0000000..1390acc --- /dev/null +++ b/Logical-elyza-llama2-7b-fast-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b322497215e870d9b10c6f2b2b373b55f58ae6bb9d04930f469f84e6036d8ee8 +size 13478105536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4df3dea --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: Manual-Dataset-Creation-Project/Raicho-7B-v0.1 +datasets: +- Manual-Dataset-Creation-Project/Malum-130 +- sudy-super/CoTangent +- llm-jp/oasst1-21k-ja +- llm-jp/oasst2-33k-ja +- Aratako/Rosebleu-1on1-Dialogues-RP +- baobab-trees/wikipedia-human-retrieval-ja +- aixsatoshi/Longcontext-aozora-summary +- aixsatoshi/Longcontext-aozora-instruction +- kunishou/amenokaku-code-instruct +- HachiML/Evol-hh-rlhf-gen3-1k +- minnade/chat-daily +- HachiML/Hachi-Alpaca +- Kendamarron/jimba-wiki-instruction-calm3 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Manual-Dataset-Creation-Project/Raicho-7B-v0.1 + + +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/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-instruct.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Logical-elyza-llama2-7b-fast-instruct-GGUF/resolve/main/Logical-elyza-llama2-7b-fast-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. + +