commit 6da6033b5b261fd8bea9d9647c5abbf8c2ba2ec6 Author: ModelHub XC Date: Tue Sep 29 00:01:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Yarn-Llama-2-7b-16k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..60ed4a0 --- /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 +Yarn-Llama-2-7b-16k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yarn-Llama-2-7b-16k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7265ef3 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: WangResearchLab/Yarn-Llama-2-7b-16k +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/WangResearchLab/Yarn-Llama-2-7b-16k + + +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/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Yarn-Llama-2-7b-16k-GGUF/resolve/main/Yarn-Llama-2-7b-16k.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. + + diff --git a/Yarn-Llama-2-7b-16k.IQ4_XS.gguf b/Yarn-Llama-2-7b-16k.IQ4_XS.gguf new file mode 100644 index 0000000..930f118 --- /dev/null +++ b/Yarn-Llama-2-7b-16k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9d4215ce25ad5c9a7e33e75351596c27049b8d244548ea3fc6f186b7d57381 +size 3647517280 diff --git a/Yarn-Llama-2-7b-16k.Q2_K.gguf b/Yarn-Llama-2-7b-16k.Q2_K.gguf new file mode 100644 index 0000000..7c95a4e --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bcff85692a29a0a187f8fd21ae451d7d6170a8c011512a20d61f1ed8566d862 +size 2532864608 diff --git a/Yarn-Llama-2-7b-16k.Q3_K_L.gguf b/Yarn-Llama-2-7b-16k.Q3_K_L.gguf new file mode 100644 index 0000000..8051599 --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f62e2305529155bbfcf622f3bb0d6d23e7f677ffaf456d220b3b3f30940a62f +size 3597111904 diff --git a/Yarn-Llama-2-7b-16k.Q3_K_M.gguf b/Yarn-Llama-2-7b-16k.Q3_K_M.gguf new file mode 100644 index 0000000..06c6b93 --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6e1024b2a5cbb83d7f6e9a925994a9a5ec05cd8890e16977b48af81aa6172d +size 3298005600 diff --git a/Yarn-Llama-2-7b-16k.Q3_K_S.gguf b/Yarn-Llama-2-7b-16k.Q3_K_S.gguf new file mode 100644 index 0000000..5fa65da --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5dcf676095b37d960b5ede39256a22f8d9431f41f0fc0e0174493633bbbdb54 +size 2948305504 diff --git a/Yarn-Llama-2-7b-16k.Q4_K_M.gguf b/Yarn-Llama-2-7b-16k.Q4_K_M.gguf new file mode 100644 index 0000000..dc552eb --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b9edae30d03a036ccbd24282e764b1599153d1368c55a500f24fa55351041de +size 4081005152 diff --git a/Yarn-Llama-2-7b-16k.Q4_K_S.gguf b/Yarn-Llama-2-7b-16k.Q4_K_S.gguf new file mode 100644 index 0000000..8afb8b2 --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50156bf048af222cec26db5326d72d2ae63188c2001fce8883cecbd27e21b4a4 +size 3856740960 diff --git a/Yarn-Llama-2-7b-16k.Q5_K_M.gguf b/Yarn-Llama-2-7b-16k.Q5_K_M.gguf new file mode 100644 index 0000000..06889cc --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24028445417e397004f063a7d2b8c5225c94631a5352efd3388f7dc0371459cb +size 4783157856 diff --git a/Yarn-Llama-2-7b-16k.Q5_K_S.gguf b/Yarn-Llama-2-7b-16k.Q5_K_S.gguf new file mode 100644 index 0000000..90c703d --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4604f80ffddd9d8e24a25014daafd51d394407f09a1f60bb695cf24968ca641 +size 4651692640 diff --git a/Yarn-Llama-2-7b-16k.Q6_K.gguf b/Yarn-Llama-2-7b-16k.Q6_K.gguf new file mode 100644 index 0000000..d262a84 --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f994a8d9985fd66cce061ce9d12747ebe10f6833027e4a048d7e35b4bfccdbb0 +size 5529195104 diff --git a/Yarn-Llama-2-7b-16k.Q8_0.gguf b/Yarn-Llama-2-7b-16k.Q8_0.gguf new file mode 100644 index 0000000..7bb3e7f --- /dev/null +++ b/Yarn-Llama-2-7b-16k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abb1e2144af6e830375165e106715be9c224d3816cade874394efc989d60ba0 +size 7161090656 diff --git a/Yarn-Llama-2-7b-16k.f16.gguf b/Yarn-Llama-2-7b-16k.f16.gguf new file mode 100644 index 0000000..19774fe --- /dev/null +++ b/Yarn-Llama-2-7b-16k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a40d95fa7fa083517b101f301963b697a492f96a923c379b93e5477ffd0084f +size 13478105696