commit 0f6ef0387f2d27d259edc9ffe92215eb8fb82dd8 Author: ModelHub XC Date: Wed Apr 22 03:17:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marcoroni-neural-chat-7B-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2e0e7cc --- /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 +Marcoroni-neural-chat-7B-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marcoroni-neural-chat-7B-v2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marcoroni-neural-chat-7B-v2.IQ4_XS.gguf b/Marcoroni-neural-chat-7B-v2.IQ4_XS.gguf new file mode 100644 index 0000000..e4fb4c7 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5707df04b97491bac89d74ef8ee92c5ed750780d4ca42cd9204f5ddbf4c4acd +size 3944389120 diff --git a/Marcoroni-neural-chat-7B-v2.Q2_K.gguf b/Marcoroni-neural-chat-7B-v2.Q2_K.gguf new file mode 100644 index 0000000..7bde491 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5348babf6966ac66b5ecb2a0cde4ff8f1adcd3223a31b24fc539ef1cc02796d +size 2719242752 diff --git a/Marcoroni-neural-chat-7B-v2.Q3_K_L.gguf b/Marcoroni-neural-chat-7B-v2.Q3_K_L.gguf new file mode 100644 index 0000000..87031b9 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88cc4431f5b5666e713eedc73ffe0e8510be6d0f76b9417225eb99b46ad6afa +size 3822025216 diff --git a/Marcoroni-neural-chat-7B-v2.Q3_K_M.gguf b/Marcoroni-neural-chat-7B-v2.Q3_K_M.gguf new file mode 100644 index 0000000..11dcf36 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5170da599375640afb4dc449ba1784328b4ef28aca74a9ebc35fb13bc16f97d +size 3518986752 diff --git a/Marcoroni-neural-chat-7B-v2.Q3_K_S.gguf b/Marcoroni-neural-chat-7B-v2.Q3_K_S.gguf new file mode 100644 index 0000000..e6bfdd1 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab13f3d4cec834954dc679b1f79d793a324bf0c7d2c0035477e31815e3565ca9 +size 3164568064 diff --git a/Marcoroni-neural-chat-7B-v2.Q4_0_4_4.gguf b/Marcoroni-neural-chat-7B-v2.Q4_0_4_4.gguf new file mode 100644 index 0000000..a9e4140 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02053101224c7bdb0a5608b0b4e212b68c5f14831792dfc45da3d0bfb336d0e9 +size 4108917248 diff --git a/Marcoroni-neural-chat-7B-v2.Q4_K_M.gguf b/Marcoroni-neural-chat-7B-v2.Q4_K_M.gguf new file mode 100644 index 0000000..6c3de0e --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aa82aad23807b02699f401f675977bf2f70eb0624080f3b8a42f05e85cffd5c +size 4368439808 diff --git a/Marcoroni-neural-chat-7B-v2.Q4_K_S.gguf b/Marcoroni-neural-chat-7B-v2.Q4_K_S.gguf new file mode 100644 index 0000000..4614c85 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e4e96370caa961463bdcfcd4fe81d24477db6fcfaec48e56ad61690b911055 +size 4140374528 diff --git a/Marcoroni-neural-chat-7B-v2.Q5_K_M.gguf b/Marcoroni-neural-chat-7B-v2.Q5_K_M.gguf new file mode 100644 index 0000000..e4e03a6 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c4adf68f19448d60d5d425d32dba7fc68bf5fa38f706447d1d598e1cc679a1 +size 5131409920 diff --git a/Marcoroni-neural-chat-7B-v2.Q5_K_S.gguf b/Marcoroni-neural-chat-7B-v2.Q5_K_S.gguf new file mode 100644 index 0000000..63578f3 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b286a41746f6684f44acd93aac71872ffa12fa79310690cb3ebbd18266395f3a +size 4997716480 diff --git a/Marcoroni-neural-chat-7B-v2.Q6_K.gguf b/Marcoroni-neural-chat-7B-v2.Q6_K.gguf new file mode 100644 index 0000000..3518e49 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49aa630be7874d696475459890ea94021d512205cb1b567dc48dd3a5f71f682f +size 5942065664 diff --git a/Marcoroni-neural-chat-7B-v2.Q8_0.gguf b/Marcoroni-neural-chat-7B-v2.Q8_0.gguf new file mode 100644 index 0000000..4ad1adb --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a633e6099d40412504e68588b93dfbbc16dc13dd1d006523e740ebce823a7d07 +size 7695858176 diff --git a/Marcoroni-neural-chat-7B-v2.f16.gguf b/Marcoroni-neural-chat-7B-v2.f16.gguf new file mode 100644 index 0000000..1265e16 --- /dev/null +++ b/Marcoroni-neural-chat-7B-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b6c915faee742d7c78afe9661e30ccefb22c8f0002935ca3a8f88c62f26c84 +size 14484732416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5411aa4 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Toten5/Marcoroni-neural-chat-7B-v2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Toten5/Marcoroni-neural-chat-7B-v2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-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/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Marcoroni-neural-chat-7B-v2-GGUF/resolve/main/Marcoroni-neural-chat-7B-v2.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. + +