commit 5f07bc25155bc3c6290602d70b497b1da2133bf7 Author: ModelHub XC Date: Sat Aug 29 06:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/thinking-llama-8b-general-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..852a3b6 --- /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 +thinking-llama-8b-general.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.f16.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-general.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..90863ec --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: jdchang/thinking-llama-8b-general +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/jdchang/thinking-llama-8b-general + + +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/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-general-GGUF/resolve/main/thinking-llama-8b-general.f16.gguf) | f16 | 16.2 | 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. + + diff --git a/thinking-llama-8b-general.IQ4_XS.gguf b/thinking-llama-8b-general.IQ4_XS.gguf new file mode 100644 index 0000000..475024a --- /dev/null +++ b/thinking-llama-8b-general.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db02bb57cee0d006738ca246e79b185a86604e3dd58c6a153043f161d189b89 +size 4484367776 diff --git a/thinking-llama-8b-general.Q2_K.gguf b/thinking-llama-8b-general.Q2_K.gguf new file mode 100644 index 0000000..177817b --- /dev/null +++ b/thinking-llama-8b-general.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b368de211d0ce1f0fbf2280cce990ce5e8e616c47c1966d9062e15491780c336 +size 3179136416 diff --git a/thinking-llama-8b-general.Q3_K_L.gguf b/thinking-llama-8b-general.Q3_K_L.gguf new file mode 100644 index 0000000..6913082 --- /dev/null +++ b/thinking-llama-8b-general.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ede21905232110052cce0e39f0e460f8de39f3c85f2db36e3ba0d00cc3778bc0 +size 4321961376 diff --git a/thinking-llama-8b-general.Q3_K_M.gguf b/thinking-llama-8b-general.Q3_K_M.gguf new file mode 100644 index 0000000..ced5c6f --- /dev/null +++ b/thinking-llama-8b-general.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d475313dd7dc828e65417f9589630550d34da748e2ce8753ea77a5eeec992fb +size 4018922912 diff --git a/thinking-llama-8b-general.Q3_K_S.gguf b/thinking-llama-8b-general.Q3_K_S.gguf new file mode 100644 index 0000000..c648e91 --- /dev/null +++ b/thinking-llama-8b-general.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae42ddc1f603762bdd69a267a80ee59b785297884103efe163881a7c9d4231a +size 3664504224 diff --git a/thinking-llama-8b-general.Q4_0_4_4.gguf b/thinking-llama-8b-general.Q4_0_4_4.gguf new file mode 100644 index 0000000..7831beb --- /dev/null +++ b/thinking-llama-8b-general.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e351e643636704d7064b01fd0182dda20bd240333921ce9d4261c637796f3f34 +size 4661216672 diff --git a/thinking-llama-8b-general.Q4_K_M.gguf b/thinking-llama-8b-general.Q4_K_M.gguf new file mode 100644 index 0000000..7ab1e6f --- /dev/null +++ b/thinking-llama-8b-general.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b6aa2c5a0ebb459583be81e8ab0e872787c95101a6a4d6fb0fbdcbd76af583f +size 4920739232 diff --git a/thinking-llama-8b-general.Q4_K_S.gguf b/thinking-llama-8b-general.Q4_K_S.gguf new file mode 100644 index 0000000..15fc7b5 --- /dev/null +++ b/thinking-llama-8b-general.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80bcd2de939dc6f2bb8b4ebc2cc5e7354a3ce138c996e2fddf772d6bc93a9989 +size 4692673952 diff --git a/thinking-llama-8b-general.Q5_K_M.gguf b/thinking-llama-8b-general.Q5_K_M.gguf new file mode 100644 index 0000000..baba920 --- /dev/null +++ b/thinking-llama-8b-general.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa80ca0c9d4d1dc2f3911bf078f61563ba2985c6f3a4ee7fdc28a9e817dd6db +size 5732992416 diff --git a/thinking-llama-8b-general.Q5_K_S.gguf b/thinking-llama-8b-general.Q5_K_S.gguf new file mode 100644 index 0000000..c9d4eab --- /dev/null +++ b/thinking-llama-8b-general.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21cd4d4320a0c5205d22e8c4398e134e5ebe42aa9e5b71083aefa81436692bca +size 5599298976 diff --git a/thinking-llama-8b-general.Q6_K.gguf b/thinking-llama-8b-general.Q6_K.gguf new file mode 100644 index 0000000..b7fe20f --- /dev/null +++ b/thinking-llama-8b-general.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a40c1a448b301bdaf49607bcc58c8f6ee262bfde43788b01211b56f152aa77 +size 6596011424 diff --git a/thinking-llama-8b-general.Q8_0.gguf b/thinking-llama-8b-general.Q8_0.gguf new file mode 100644 index 0000000..24bde76 --- /dev/null +++ b/thinking-llama-8b-general.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bbbbe555e069ff1f4abda238131e3a52c55f3b4c8a9c992c72eeec34e0b5831 +size 8540775840 diff --git a/thinking-llama-8b-general.f16.gguf b/thinking-llama-8b-general.f16.gguf new file mode 100644 index 0000000..3662912 --- /dev/null +++ b/thinking-llama-8b-general.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8c8c054063d389993026516e30b6068e733d8433148e8b0030b6841e640aba8 +size 16068896160