commit 944b9fcabf5426d08ac4ab9565f0fe4c50923dfb Author: ModelHub XC Date: Sun Sep 27 16:53:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce8c84a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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_8.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.f16.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatFinetune-llama-2-7b_V1_8.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ChatFinetune-llama-2-7b_V1_8.IQ4_XS.gguf b/ChatFinetune-llama-2-7b_V1_8.IQ4_XS.gguf new file mode 100644 index 0000000..f6f08ab --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:affbde9f73a0ea1630840b2f563dd38785901af1a034709e0361ce8ee10bd913 +size 3647517152 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q2_K.gguf b/ChatFinetune-llama-2-7b_V1_8.Q2_K.gguf new file mode 100644 index 0000000..374a58d --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4fdf0ee4ef22b586887cf68c506a0bfc3e20fb274bc17cb0d44a9d95c1cd6a +size 2532864480 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q3_K_L.gguf b/ChatFinetune-llama-2-7b_V1_8.Q3_K_L.gguf new file mode 100644 index 0000000..273bc54 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b75abd87cd8a90b44db87c3647b57e0c5f0ed4d0240e26a83c7b79afce5643 +size 3597111776 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q3_K_M.gguf b/ChatFinetune-llama-2-7b_V1_8.Q3_K_M.gguf new file mode 100644 index 0000000..babb213 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c39aa5bb7aaf27aa3d59c9f4404794ca095c4954767b3c4b551751b3ae973514 +size 3298005472 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q3_K_S.gguf b/ChatFinetune-llama-2-7b_V1_8.Q3_K_S.gguf new file mode 100644 index 0000000..5e310b5 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0a40a1b5717bce3f44e97e306655b0b1390588337c381bc15d95b32d5fe697 +size 2948305376 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q4_K_M.gguf b/ChatFinetune-llama-2-7b_V1_8.Q4_K_M.gguf new file mode 100644 index 0000000..8c02cab --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7517c4a2cd6758993bae3bcf4217ed1e9a0c61dac5554104f6dc267110aa9677 +size 4081005024 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q4_K_S.gguf b/ChatFinetune-llama-2-7b_V1_8.Q4_K_S.gguf new file mode 100644 index 0000000..bf57107 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e37daa2a1518cb99b19da37dba3be3ae150538a0c53812eb399f8b52dcb787b +size 3856740832 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q5_K_M.gguf b/ChatFinetune-llama-2-7b_V1_8.Q5_K_M.gguf new file mode 100644 index 0000000..cbdf380 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ccef58fbcca146620e4f652e6090213b249a9d0b843de5440cab9e346dc97af +size 4783157728 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q5_K_S.gguf b/ChatFinetune-llama-2-7b_V1_8.Q5_K_S.gguf new file mode 100644 index 0000000..7abd8a8 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc0cb7f2556237525b214d925f676445b13a50af18299ca8060b352673115fab +size 4651692512 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q6_K.gguf b/ChatFinetune-llama-2-7b_V1_8.Q6_K.gguf new file mode 100644 index 0000000..8c4f340 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd14a97eb68c6499f2b8dbd877a52519f102b55fb3fcc48dbeff55f06b0607b8 +size 5529194976 diff --git a/ChatFinetune-llama-2-7b_V1_8.Q8_0.gguf b/ChatFinetune-llama-2-7b_V1_8.Q8_0.gguf new file mode 100644 index 0000000..1ba83e9 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d3ee3eaf424c36f1851f275907fdbd312862294cb32163fb9e5070e97558f8 +size 7161090528 diff --git a/ChatFinetune-llama-2-7b_V1_8.f16.gguf b/ChatFinetune-llama-2-7b_V1_8.f16.gguf new file mode 100644 index 0000000..8312114 --- /dev/null +++ b/ChatFinetune-llama-2-7b_V1_8.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fded8333e9326f527ed55e665627bc7b15f7e82290d362fd532eada9711fb663 +size 13478105568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a970fac --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Ravihansa/ChatFinetune-llama-2-7b_V1_8 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Ravihansa/ChatFinetune-llama-2-7b_V1_8 + + +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_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ChatFinetune-llama-2-7b_V1_8-GGUF/resolve/main/ChatFinetune-llama-2-7b_V1_8.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. + +