commit a2b23760b60389fa335153678b42fb3a4ad1b904 Author: ModelHub XC Date: Sat Jun 20 20:42:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3f03dce --- /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 +ChatFinetune-llama-2-7b_V1_7.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.f16.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_7.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ChatFinetune-llama-2-7b_V1_7.IQ4_XS.gguf b/ChatFinetune-llama-2-7b_V1_7.IQ4_XS.gguf new file mode 100644 index 0000000..0e3aef4 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe2703926cbb7ee0a9e2be6e914508eda5dd6ffb428ff05f2d8bf35281718c45 +size 3647517152 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q2_K.gguf b/ChatFinetune-llama-2-7b_V1_7.Q2_K.gguf new file mode 100644 index 0000000..c47fa35 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b02564d4125e1ced5009e242ac3db9e058308d1ddb7fb85e262f8a858940952 +size 2532864480 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q3_K_L.gguf b/ChatFinetune-llama-2-7b_V1_7.Q3_K_L.gguf new file mode 100644 index 0000000..ddffa27 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f211e7573304ea47ecb60b61a30a2f05b8b8171b0ea5172c912b8b7479100868 +size 3597111776 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q3_K_M.gguf b/ChatFinetune-llama-2-7b_V1_7.Q3_K_M.gguf new file mode 100644 index 0000000..1c7e737 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08df2b1df6ab0e58b5c922d1fc6214796e814b328fccc2eae840ac83fe23c77d +size 3298005472 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q3_K_S.gguf b/ChatFinetune-llama-2-7b_V1_7.Q3_K_S.gguf new file mode 100644 index 0000000..c1be44d --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e776efa1a8840add0415af9a960df948dfe4f04bddf62f769e158e4094ea0a +size 2948305376 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q4_K_M.gguf b/ChatFinetune-llama-2-7b_V1_7.Q4_K_M.gguf new file mode 100644 index 0000000..e3007f9 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66320a1534512d0b9df92ae0b893cacfa84ccc10269015f48121382047da3895 +size 4081005024 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q4_K_S.gguf b/ChatFinetune-llama-2-7b_V1_7.Q4_K_S.gguf new file mode 100644 index 0000000..af27e2f --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a9d522d30ab6f570e18ca7405b20d712208822340f6a8c3519d5f8d83e9ef37 +size 3856740832 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q5_K_M.gguf b/ChatFinetune-llama-2-7b_V1_7.Q5_K_M.gguf new file mode 100644 index 0000000..f84bdf1 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3029bd266c3e6ea2560c3b53c8a5fca0f36da0233c329cbfdd50ca76b9d11fe1 +size 4783157728 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q5_K_S.gguf b/ChatFinetune-llama-2-7b_V1_7.Q5_K_S.gguf new file mode 100644 index 0000000..69d5bd4 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd1030b3e6445462ea26b8e6527a8b8063565173dff2954e8d3d7648c6d254d +size 4651692512 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q6_K.gguf b/ChatFinetune-llama-2-7b_V1_7.Q6_K.gguf new file mode 100644 index 0000000..16e389f --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1705a68acfc5322e38f8c66a37833d57828adef790177a2212609b92e7836451 +size 5529194976 diff --git a/ChatFinetune-llama-2-7b_V1_7.Q8_0.gguf b/ChatFinetune-llama-2-7b_V1_7.Q8_0.gguf new file mode 100644 index 0000000..a338623 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6872e8b8f0254e32b7195f837c8aced601a13a991ee40e3d6cbc48513146d268 +size 7161090528 diff --git a/ChatFinetune-llama-2-7b_V1_7.f16.gguf b/ChatFinetune-llama-2-7b_V1_7.f16.gguf new file mode 100644 index 0000000..c2389c5 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_7.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:144da7a28491f72e829e2933e96219b8e8333ae05e4f6c63715f9761b7c21351 +size 13478105568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c670482 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Ravihansa/ChatFinetune-llama-2-7b_V1_7 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Ravihansa/ChatFinetune-llama-2-7b_V1_7 + + +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/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_7-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_7.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. + +