commit 060d26fb98b054c136cb719850e9e830bac0b812 Author: ModelHub XC Date: Sat Aug 1 01:21:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA2-7B-RFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4a97a85 --- /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 +LLaMA2-7B-RFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B-RFT.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA2-7B-RFT.IQ4_XS.gguf b/LLaMA2-7B-RFT.IQ4_XS.gguf new file mode 100644 index 0000000..10c9348 --- /dev/null +++ b/LLaMA2-7B-RFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72416bea61566bbec968642fc870640bb70dc038d43ae135c5f30edfe4db7ad +size 3647517536 diff --git a/LLaMA2-7B-RFT.Q2_K.gguf b/LLaMA2-7B-RFT.Q2_K.gguf new file mode 100644 index 0000000..c404b97 --- /dev/null +++ b/LLaMA2-7B-RFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f26036a6e030469fccdc9c99679c1716b5e3dff40725b83ebb44f5cdaf30fbe8 +size 2532864864 diff --git a/LLaMA2-7B-RFT.Q3_K_L.gguf b/LLaMA2-7B-RFT.Q3_K_L.gguf new file mode 100644 index 0000000..6fc51f8 --- /dev/null +++ b/LLaMA2-7B-RFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38017a63d2178ebf1ab481ecd15d2098fd74cf47e44f3450e742dab2a0175c45 +size 3597112160 diff --git a/LLaMA2-7B-RFT.Q3_K_M.gguf b/LLaMA2-7B-RFT.Q3_K_M.gguf new file mode 100644 index 0000000..6aece37 --- /dev/null +++ b/LLaMA2-7B-RFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91235cb88034a9a0ef77c05c4270f14af51218374ed8cf89de2e159b98d5cb7 +size 3298005856 diff --git a/LLaMA2-7B-RFT.Q3_K_S.gguf b/LLaMA2-7B-RFT.Q3_K_S.gguf new file mode 100644 index 0000000..20e00d9 --- /dev/null +++ b/LLaMA2-7B-RFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7612b3f6881822116b33b7bf54dd33e7dfb720894ca2b33af8e89515c3ad6fcd +size 2948305760 diff --git a/LLaMA2-7B-RFT.Q4_0_4_4.gguf b/LLaMA2-7B-RFT.Q4_0_4_4.gguf new file mode 100644 index 0000000..b4fc2a5 --- /dev/null +++ b/LLaMA2-7B-RFT.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc4381b9a4078c6ed9b09c189e6a6aa3df086e6630db6a744482cc259f35793 +size 3825808224 diff --git a/LLaMA2-7B-RFT.Q4_K_M.gguf b/LLaMA2-7B-RFT.Q4_K_M.gguf new file mode 100644 index 0000000..755e2c0 --- /dev/null +++ b/LLaMA2-7B-RFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c4458c449e11458257e1a68a77599c9307907bd125724f4b04070a053efc64 +size 4081005408 diff --git a/LLaMA2-7B-RFT.Q4_K_S.gguf b/LLaMA2-7B-RFT.Q4_K_S.gguf new file mode 100644 index 0000000..c67751c --- /dev/null +++ b/LLaMA2-7B-RFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:850c7ce7980f8db11291404ab9f2d06f5ac0268cf638bd6afbbda4f1a7c0e690 +size 3856741216 diff --git a/LLaMA2-7B-RFT.Q5_K_M.gguf b/LLaMA2-7B-RFT.Q5_K_M.gguf new file mode 100644 index 0000000..0869142 --- /dev/null +++ b/LLaMA2-7B-RFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99be933cdf4acb1b92ba7424e108336e50541ad9ac7517bde6a13b6cbdb4224e +size 4783158112 diff --git a/LLaMA2-7B-RFT.Q5_K_S.gguf b/LLaMA2-7B-RFT.Q5_K_S.gguf new file mode 100644 index 0000000..56334d4 --- /dev/null +++ b/LLaMA2-7B-RFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c49c943a527fe7eb23a6520956404e0cd915890c8b82c2effcb676723be21d6 +size 4651692896 diff --git a/LLaMA2-7B-RFT.Q6_K.gguf b/LLaMA2-7B-RFT.Q6_K.gguf new file mode 100644 index 0000000..6d8a328 --- /dev/null +++ b/LLaMA2-7B-RFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a90363b3adf6e51e0a8b8ad3ff1b57f9a051155bdeb6ba5d2316fe73e443601d +size 5529195360 diff --git a/LLaMA2-7B-RFT.Q8_0.gguf b/LLaMA2-7B-RFT.Q8_0.gguf new file mode 100644 index 0000000..2e7122e --- /dev/null +++ b/LLaMA2-7B-RFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06b73f92e1fff2c6699e14d5819533aa04323289003eee0409492e8514797bf +size 7161090912 diff --git a/LLaMA2-7B-RFT.f16.gguf b/LLaMA2-7B-RFT.f16.gguf new file mode 100644 index 0000000..fa91064 --- /dev/null +++ b/LLaMA2-7B-RFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227f730568773248b39eec21bcfd82854c1394ec471f6de378d0c62351f9bfb5 +size 13478105952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d05769c --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: GraphWiz/LLaMA2-7B-RFT +datasets: +- GraphWiz/GraphInstruct-RFT-72K +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- graph problem +--- +## About + + + + + + +static quants of https://huggingface.co/GraphWiz/LLaMA2-7B-RFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLaMA2-7B-RFT-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/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-RFT-GGUF/resolve/main/LLaMA2-7B-RFT.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +