commit 3a6264778b0ddef4d6ceb69ef8a930ee2365d28c Author: ModelHub XC Date: Sat Jun 13 04:56:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..006c62b --- /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 +Mistral-7B-Instruct-v0.2NEURAL.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2NEURAL.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-Instruct-v0.2NEURAL.IQ4_XS.gguf b/Mistral-7B-Instruct-v0.2NEURAL.IQ4_XS.gguf new file mode 100644 index 0000000..110af6c --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac93dceb8e9f3ee8b91b084f33c29f435752c45615ec1927b4ab81cd9cc7acc +size 3944390336 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q2_K.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q2_K.gguf new file mode 100644 index 0000000..dd50e47 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427bdce1276577a5d54fc98fc34bc64b795eec1b8be14540b0b22dc543f6b5c4 +size 2719243968 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_L.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_L.gguf new file mode 100644 index 0000000..0bdb552 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e03f8303cf478de574735c462a46478d4fbc3ef5f9691121a10d959915f6e44 +size 3822026432 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_M.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_M.gguf new file mode 100644 index 0000000..61177aa --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c2f1a4056aad50acd805fccbacd417dd7540786930d90775fed6cd3f332d839 +size 3518987968 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_S.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_S.gguf new file mode 100644 index 0000000..1e94940 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57fdf4e49a03c9ac8b7fae4f1009b3f3cde6832249dc83b2c4e9f90ddb15e659 +size 3164569280 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q4_0_4_4.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q4_0_4_4.gguf new file mode 100644 index 0000000..dd3a001 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319a442a4ff2fb58dbf21327c3fb693e3ca7907617f6671907ad1572ba642d79 +size 4108918464 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q4_K_M.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q4_K_M.gguf new file mode 100644 index 0000000..2b821f0 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389ca009b2341e8ff4ae64c75ea6471774bd7a8a75f4197ee73b9efb41fefde2 +size 4368441024 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q4_K_S.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q4_K_S.gguf new file mode 100644 index 0000000..09aa693 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8b74fc4602b7464da547d2f00f0195534da6c1101186fead9231549edd656a2 +size 4140375744 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q5_K_M.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q5_K_M.gguf new file mode 100644 index 0000000..252f9f3 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ebe629f184eee001b6f9fc9601e347dfacbab7e4ec56baa222ddffab741a371 +size 5131411136 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q5_K_S.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q5_K_S.gguf new file mode 100644 index 0000000..c882bf2 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d991a9e4f2cf806e1f18707ed74139f0f9bd98d30eae09c3ad6efdd206cf188 +size 4997717696 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q6_K.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q6_K.gguf new file mode 100644 index 0000000..0c55c23 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f243eb8a4957c41ed8e609506cb297473768b4aa5b920495047ef53fa91031 +size 5942066880 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.Q8_0.gguf b/Mistral-7B-Instruct-v0.2NEURAL.Q8_0.gguf new file mode 100644 index 0000000..018369b --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914c521cd84be5b3a00fd49b5714b84d2adfee75d0a57d54e1fa5b87c360a1c5 +size 7695859392 diff --git a/Mistral-7B-Instruct-v0.2NEURAL.f16.gguf b/Mistral-7B-Instruct-v0.2NEURAL.f16.gguf new file mode 100644 index 0000000..9a2d640 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2NEURAL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae7cb4eb4cc1807386cb3ab11a32114246bac8c01d1c500fbac5b7cca7882b8d +size 14484733632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa63d67 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: RaduGabriel/Mistral-7B-Instruct-v0.2NEURAL +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- mistralai/Mistral-7B-Instruct-v0.2 +- CultriX/NeuralTrix-7B-dpo +--- +## About + + + + + + +static quants of https://huggingface.co/RaduGabriel/Mistral-7B-Instruct-v0.2NEURAL + + +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/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2NEURAL-GGUF/resolve/main/Mistral-7B-Instruct-v0.2NEURAL.f16.gguf) | f16 | 14.6 | 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. + +