commit 8a7cbef5335cbf0f01d8705e510ecf9cbb68e494 Author: ModelHub XC Date: Thu Oct 8 16:55:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TWLLM-Llama2-Extend-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..781f512 --- /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 +TWLLM-Llama2-Extend.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.f16.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TWLLM-Llama2-Extend.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..85a0d32 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Zhao-Ching/TWLLM-Llama2-Extend +language: +- zh +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Zhao-Ching/TWLLM-Llama2-Extend + + +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/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TWLLM-Llama2-Extend-GGUF/resolve/main/TWLLM-Llama2-Extend.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/TWLLM-Llama2-Extend.IQ3_M.gguf b/TWLLM-Llama2-Extend.IQ3_M.gguf new file mode 100644 index 0000000..1619ce4 --- /dev/null +++ b/TWLLM-Llama2-Extend.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a152b55e4acbb36556bcdef20244b7b66b6b626180325d1bc96960f4d7a12af6 +size 3114866400 diff --git a/TWLLM-Llama2-Extend.IQ3_S.gguf b/TWLLM-Llama2-Extend.IQ3_S.gguf new file mode 100644 index 0000000..22935c5 --- /dev/null +++ b/TWLLM-Llama2-Extend.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab5e82ccd8be5263270cd6973fb112db80d792b3548b1e72342511b0e490a1a +size 2948306656 diff --git a/TWLLM-Llama2-Extend.IQ3_XS.gguf b/TWLLM-Llama2-Extend.IQ3_XS.gguf new file mode 100644 index 0000000..6801e1a --- /dev/null +++ b/TWLLM-Llama2-Extend.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b665f868983fb39987c4c67668aa9d2cdb6077a99bb5bbb743b42d5d6b5972b +size 2796525280 diff --git a/TWLLM-Llama2-Extend.IQ4_XS.gguf b/TWLLM-Llama2-Extend.IQ4_XS.gguf new file mode 100644 index 0000000..d43314d --- /dev/null +++ b/TWLLM-Llama2-Extend.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6928a0982d746462ad6f95342b1fb3d1f7d96afa128f3df2be7dd34a9d0bdff6 +size 3647518432 diff --git a/TWLLM-Llama2-Extend.Q2_K.gguf b/TWLLM-Llama2-Extend.Q2_K.gguf new file mode 100644 index 0000000..e1c1402 --- /dev/null +++ b/TWLLM-Llama2-Extend.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded26e141d6bf7290fa13e8e5db34f79703894f7deb4ae22549d2f0e0cc22cdd +size 2532865760 diff --git a/TWLLM-Llama2-Extend.Q3_K_L.gguf b/TWLLM-Llama2-Extend.Q3_K_L.gguf new file mode 100644 index 0000000..afdd095 --- /dev/null +++ b/TWLLM-Llama2-Extend.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:311560bdcef980074cdd59b74478607784244d7dbfe7802bd1138084f285826c +size 3597113056 diff --git a/TWLLM-Llama2-Extend.Q3_K_M.gguf b/TWLLM-Llama2-Extend.Q3_K_M.gguf new file mode 100644 index 0000000..7ba6c05 --- /dev/null +++ b/TWLLM-Llama2-Extend.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:945fe86fd17ac918b4cbdbf32800c7fc61c36e29cd3b52f9bcfc05dcbd075e5d +size 3298006752 diff --git a/TWLLM-Llama2-Extend.Q3_K_S.gguf b/TWLLM-Llama2-Extend.Q3_K_S.gguf new file mode 100644 index 0000000..eaa0f41 --- /dev/null +++ b/TWLLM-Llama2-Extend.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ad6f582db666a4d2ac40b21f67862e7767dc71c428551acd71c064342ce62c8 +size 2948306656 diff --git a/TWLLM-Llama2-Extend.Q4_K_M.gguf b/TWLLM-Llama2-Extend.Q4_K_M.gguf new file mode 100644 index 0000000..65b6e55 --- /dev/null +++ b/TWLLM-Llama2-Extend.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1332a0310911e67b7e0ebf352c09c7c871ec035a97811cbe711aaac491fa30 +size 4081006304 diff --git a/TWLLM-Llama2-Extend.Q4_K_S.gguf b/TWLLM-Llama2-Extend.Q4_K_S.gguf new file mode 100644 index 0000000..eabcc92 --- /dev/null +++ b/TWLLM-Llama2-Extend.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fb1a91375340faf82a3f4f73991c1b6b5b0e144507ef0abcdba55d001579dd +size 3856742112 diff --git a/TWLLM-Llama2-Extend.Q5_K_M.gguf b/TWLLM-Llama2-Extend.Q5_K_M.gguf new file mode 100644 index 0000000..c4b699f --- /dev/null +++ b/TWLLM-Llama2-Extend.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24e288e504bb66cb94bff4ee9b8173e41d9e813cc7825b7946c51834c1c8c48 +size 4783159008 diff --git a/TWLLM-Llama2-Extend.Q5_K_S.gguf b/TWLLM-Llama2-Extend.Q5_K_S.gguf new file mode 100644 index 0000000..a1e7b38 --- /dev/null +++ b/TWLLM-Llama2-Extend.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4301fe16d3bdbe62effad58a6e322c4f8807ecf16f593bf625aaf1865b97fbf9 +size 4651693792 diff --git a/TWLLM-Llama2-Extend.Q6_K.gguf b/TWLLM-Llama2-Extend.Q6_K.gguf new file mode 100644 index 0000000..ab7749b --- /dev/null +++ b/TWLLM-Llama2-Extend.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5315279f7a5a8d2ad150062c43488c4ccaaf0e11365259e7743febfed2c26e51 +size 5529196256 diff --git a/TWLLM-Llama2-Extend.Q8_0.gguf b/TWLLM-Llama2-Extend.Q8_0.gguf new file mode 100644 index 0000000..08cb3a3 --- /dev/null +++ b/TWLLM-Llama2-Extend.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98bb773fef2fcdc4128c9963a4d90f1c90c5f1dd1ea5925d9bb3b87a8d0eb575 +size 7161091808 diff --git a/TWLLM-Llama2-Extend.f16.gguf b/TWLLM-Llama2-Extend.f16.gguf new file mode 100644 index 0000000..d644c01 --- /dev/null +++ b/TWLLM-Llama2-Extend.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82804ae5353a1a52afa24362f5fbb879053815818aba8d28d1be8fb0741b9f7 +size 13478106848