commit d1df1d0708b6074e9a7b47a0b43c7c4a8dbda173 Author: ModelHub XC Date: Sat Jun 13 05:51:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-chat-xgpt-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d02360d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Llama-2-7b-chat-xgpt.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-xgpt.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-chat-xgpt.IQ3_M.gguf b/Llama-2-7b-chat-xgpt.IQ3_M.gguf new file mode 100644 index 0000000..2eb18a8 --- /dev/null +++ b/Llama-2-7b-chat-xgpt.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbab8bea88672fe21710e8bd64066c90a808d51a4b3147f6338fa5357ac7d654 +size 3114865248 diff --git a/Llama-2-7b-chat-xgpt.IQ3_S.gguf b/Llama-2-7b-chat-xgpt.IQ3_S.gguf new file mode 100644 index 0000000..07a1b59 --- /dev/null +++ b/Llama-2-7b-chat-xgpt.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73cf4a35c08e861755ff52f9f6a305eb6f74b517b6e4ab535074eb00f23d5f04 +size 2948305504 diff --git a/Llama-2-7b-chat-xgpt.IQ3_XS.gguf b/Llama-2-7b-chat-xgpt.IQ3_XS.gguf new file mode 100644 index 0000000..1ca1590 --- /dev/null +++ b/Llama-2-7b-chat-xgpt.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18fac64e2dfa1203f75198a37430f5dddee9ec56d2c90bae63482f5e5609433a +size 2796524128 diff --git a/Llama-2-7b-chat-xgpt.IQ4_XS.gguf b/Llama-2-7b-chat-xgpt.IQ4_XS.gguf new file mode 100644 index 0000000..5731d3e --- /dev/null +++ b/Llama-2-7b-chat-xgpt.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee60876874e844dbb87aa920b9ac1ab2008a729616b4ea93bb49ddb9694a634a +size 3647517280 diff --git a/Llama-2-7b-chat-xgpt.Q2_K.gguf b/Llama-2-7b-chat-xgpt.Q2_K.gguf new file mode 100644 index 0000000..f93a6e4 --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ade0108597e3e3db8167fa40280ada6dd39cfa5b469c1d612afdff1aeb5270 +size 2532864608 diff --git a/Llama-2-7b-chat-xgpt.Q3_K_L.gguf b/Llama-2-7b-chat-xgpt.Q3_K_L.gguf new file mode 100644 index 0000000..6e5609a --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1766b4d43e739926e276d0abdcf633d32060d30a9b2ab58fb14556c4bd694980 +size 3597111904 diff --git a/Llama-2-7b-chat-xgpt.Q3_K_M.gguf b/Llama-2-7b-chat-xgpt.Q3_K_M.gguf new file mode 100644 index 0000000..8156e0e --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd67513a89be1a81df674f86a54569b49784d88bff6149cad9b4d3351fc8bc68 +size 3298005600 diff --git a/Llama-2-7b-chat-xgpt.Q3_K_S.gguf b/Llama-2-7b-chat-xgpt.Q3_K_S.gguf new file mode 100644 index 0000000..13717a8 --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f02257a76586d79d93deb93b54e1eefccb5497732989cbe21ca3c2d6ee9ecb8 +size 2948305504 diff --git a/Llama-2-7b-chat-xgpt.Q4_K_M.gguf b/Llama-2-7b-chat-xgpt.Q4_K_M.gguf new file mode 100644 index 0000000..466be2b --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5929a04db3a0720bd3bb1edf6f14bd0c43d433403dde3cf0e1a09f830baf3e56 +size 4081005152 diff --git a/Llama-2-7b-chat-xgpt.Q4_K_S.gguf b/Llama-2-7b-chat-xgpt.Q4_K_S.gguf new file mode 100644 index 0000000..ef173da --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d4ac132c873f52b81ef60a061356e8d85adda6329f96753d292801c051cb7c +size 3856740960 diff --git a/Llama-2-7b-chat-xgpt.Q5_K_M.gguf b/Llama-2-7b-chat-xgpt.Q5_K_M.gguf new file mode 100644 index 0000000..0e033ab --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02fca429e6fcef9ae4ad50b4b35f47682f9da639c332e225abd40b00c9275b4a +size 4783157856 diff --git a/Llama-2-7b-chat-xgpt.Q5_K_S.gguf b/Llama-2-7b-chat-xgpt.Q5_K_S.gguf new file mode 100644 index 0000000..0026b10 --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2de4a5fa3d6480b1e67bd66d9e9524ffff740e930c65330a1c80077be8c1485 +size 4651692640 diff --git a/Llama-2-7b-chat-xgpt.Q6_K.gguf b/Llama-2-7b-chat-xgpt.Q6_K.gguf new file mode 100644 index 0000000..40b44e5 --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b06f9224a8266285339452c14ded9cdd34a69a18847373d0c458d20a754bae +size 5529195104 diff --git a/Llama-2-7b-chat-xgpt.Q8_0.gguf b/Llama-2-7b-chat-xgpt.Q8_0.gguf new file mode 100644 index 0000000..ffc48cf --- /dev/null +++ b/Llama-2-7b-chat-xgpt.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f54f5fb768bc59e28e43b49dcc97651eae062ca296f5c27d7fdfcd04918d69e8 +size 7161090656 diff --git a/Llama-2-7b-chat-xgpt.f16.gguf b/Llama-2-7b-chat-xgpt.f16.gguf new file mode 100644 index 0000000..c377a86 --- /dev/null +++ b/Llama-2-7b-chat-xgpt.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f556499d340400ffb0df1512cee57594747dbe02c594b2f78270ba89c4200bf9 +size 13478105696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..333ebc8 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: kenshinx/Llama-2-7b-chat-xgpt +datasets: +- kenshinx/netlab-blogs +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/kenshinx/Llama-2-7b-chat-xgpt + + +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/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-xgpt-GGUF/resolve/main/Llama-2-7b-chat-xgpt.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. + +