commit 879ced083c9d1938824fb72ae24b5bbbe6e96459 Author: ModelHub XC Date: Fri Apr 17 10:57:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4d72e85 --- /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 +Infinity-Instruct-3M-0613-Mistral-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0613-Mistral-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.IQ4_XS.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.IQ4_XS.gguf new file mode 100644 index 0000000..1b914be --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9002e315ab87f77eb3aa05d48b07b9d1c7f78ecec05dd06dbbdc422294832fa +size 3944400640 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q2_K.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q2_K.gguf new file mode 100644 index 0000000..456b9ae --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29506064f022b242c964fc105525d51b744ae541286616bbdde905600732d682 +size 2719252608 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_L.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_L.gguf new file mode 100644 index 0000000..d045747 --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc5bd1c00e4aa49828f07cf9ba00e8f8280195ccb3620e1400bf6afebcca525 +size 3822035904 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_M.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_M.gguf new file mode 100644 index 0000000..b826354 --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36d139258ce4da7c9ed7142cd1446c585fc1b742284285842fb1d62f6b5e79b7 +size 3518997440 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_S.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_S.gguf new file mode 100644 index 0000000..5df58fb --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165623183a9761079154c0d00fa38f9b5e0d641d8ac2ed0a80303024c2ca164f +size 3164578752 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_M.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_M.gguf new file mode 100644 index 0000000..b702d15 --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cbdc6749ec7435d723acde8bfd0e0df798934799e02e9122a54068472a5061b +size 4368451584 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_S.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_S.gguf new file mode 100644 index 0000000..3b6b52b --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f349e0b10314c30dfd7ec4dc5e67427222f8e9d111e15556705858a50b8ef51 +size 4140386304 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_M.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_M.gguf new file mode 100644 index 0000000..9494e1b --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e22f29ea973e6f3418ea197c0e288d208ddea19ae343ed25d443cc4ca67375a0 +size 5131422720 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_S.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_S.gguf new file mode 100644 index 0000000..d880d53 --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd80c58885bd60d04504f517d412be34e24303deadd25af7b367a8ec7f92ee3f +size 4997729280 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q6_K.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q6_K.gguf new file mode 100644 index 0000000..f04f428 --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049dc17066cfa08244614e95e4f585af09b88288e0695ba94c9b982dd32127a7 +size 5942079552 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.Q8_0.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.Q8_0.gguf new file mode 100644 index 0000000..bbfc203 --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0b073c92b82746ff213c643ec21358e82ecc44bfcc419d41ae594b00c8e846f +size 7695876032 diff --git a/Infinity-Instruct-3M-0613-Mistral-7B.f16.gguf b/Infinity-Instruct-3M-0613-Mistral-7B.f16.gguf new file mode 100644 index 0000000..2908e5c --- /dev/null +++ b/Infinity-Instruct-3M-0613-Mistral-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788186949989429ad7e3bbf7ddcc164423cae6d57196721a58eb9bef4be249af +size 14484765632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..26199ec --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: BAAI/Infinity-Instruct-3M-0613-Mistral-7B +datasets: +- BAAI/Infinity-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/BAAI/Infinity-Instruct-3M-0613-Mistral-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-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/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0613-Mistral-7B-GGUF/resolve/main/Infinity-Instruct-3M-0613-Mistral-7B.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. + +