commit a91ec57fdabfacf310216a962f0b20f30aa34d3e Author: ModelHub XC Date: Wed Oct 7 15:41:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/thinking-llama-8b-specific-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bce5ec0 --- /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 +thinking-llama-8b-specific.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.f16.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +thinking-llama-8b-specific.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..ed97e8a --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: jdchang/thinking-llama-8b-specific +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/jdchang/thinking-llama-8b-specific + + +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-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/thinking-llama-8b-specific-GGUF/resolve/main/thinking-llama-8b-specific.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-specific.IQ4_XS.gguf b/thinking-llama-8b-specific.IQ4_XS.gguf new file mode 100644 index 0000000..a138c67 --- /dev/null +++ b/thinking-llama-8b-specific.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d12300c0d694518b88c56c6d6598cb819d96efde613e0b0f2f729d2a7d09b91d +size 4484367776 diff --git a/thinking-llama-8b-specific.Q2_K.gguf b/thinking-llama-8b-specific.Q2_K.gguf new file mode 100644 index 0000000..655d879 --- /dev/null +++ b/thinking-llama-8b-specific.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020c2e8d77347f40a8d6386e00757eddc03ac306560615c4e2793c402d49a6ae +size 3179136416 diff --git a/thinking-llama-8b-specific.Q3_K_L.gguf b/thinking-llama-8b-specific.Q3_K_L.gguf new file mode 100644 index 0000000..009dadd --- /dev/null +++ b/thinking-llama-8b-specific.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2b44926745e676e6bc3160ef4bd35d2241f9f43236ce481d9a653a2d7e8322 +size 4321961376 diff --git a/thinking-llama-8b-specific.Q3_K_M.gguf b/thinking-llama-8b-specific.Q3_K_M.gguf new file mode 100644 index 0000000..993b1c7 --- /dev/null +++ b/thinking-llama-8b-specific.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df2a4c83b9df8d858589cad4aac194760dc6de468bdd22b6e90c406d1b885ed5 +size 4018922912 diff --git a/thinking-llama-8b-specific.Q3_K_S.gguf b/thinking-llama-8b-specific.Q3_K_S.gguf new file mode 100644 index 0000000..77fc7b2 --- /dev/null +++ b/thinking-llama-8b-specific.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4266551c28091a28e07916fa62ee58ef95478f7fff4f052636f4275671430a4 +size 3664504224 diff --git a/thinking-llama-8b-specific.Q4_0_4_4.gguf b/thinking-llama-8b-specific.Q4_0_4_4.gguf new file mode 100644 index 0000000..da2f4a6 --- /dev/null +++ b/thinking-llama-8b-specific.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6f798d90589ae56d7203e5dce436ec5e64a7c41c68162ba72f26c3851bc586 +size 4661216672 diff --git a/thinking-llama-8b-specific.Q4_K_M.gguf b/thinking-llama-8b-specific.Q4_K_M.gguf new file mode 100644 index 0000000..b4fba12 --- /dev/null +++ b/thinking-llama-8b-specific.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eb8880c5f61fb4ff9c5577d56b995a4e1e3644f995e0b4af825fb49c6b2d3b8 +size 4920739232 diff --git a/thinking-llama-8b-specific.Q4_K_S.gguf b/thinking-llama-8b-specific.Q4_K_S.gguf new file mode 100644 index 0000000..438d431 --- /dev/null +++ b/thinking-llama-8b-specific.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22852f4132f4ecb1191b429e2e7fc6c6de2229c9b4841c44325008c0f7bcf616 +size 4692673952 diff --git a/thinking-llama-8b-specific.Q5_K_M.gguf b/thinking-llama-8b-specific.Q5_K_M.gguf new file mode 100644 index 0000000..fb64431 --- /dev/null +++ b/thinking-llama-8b-specific.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e9a40b5bf098c1d0291470dbcbb1fc16a3701b4b12b497e152ec7341a42abd +size 5732992416 diff --git a/thinking-llama-8b-specific.Q5_K_S.gguf b/thinking-llama-8b-specific.Q5_K_S.gguf new file mode 100644 index 0000000..00458e9 --- /dev/null +++ b/thinking-llama-8b-specific.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bc93a678962b8751cdf83290b555201960cfafea6f5879e73cc04f1d16c5f1e +size 5599298976 diff --git a/thinking-llama-8b-specific.Q6_K.gguf b/thinking-llama-8b-specific.Q6_K.gguf new file mode 100644 index 0000000..3259606 --- /dev/null +++ b/thinking-llama-8b-specific.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2100f110255f5433917203ab9f49a8c864ba23bf74f9c4c230441f08374274d4 +size 6596011424 diff --git a/thinking-llama-8b-specific.Q8_0.gguf b/thinking-llama-8b-specific.Q8_0.gguf new file mode 100644 index 0000000..6cd6e8e --- /dev/null +++ b/thinking-llama-8b-specific.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:413b447a62a806ef483a7d72922ab1222eda5682258cb6e7c76d18da59179819 +size 8540775840 diff --git a/thinking-llama-8b-specific.f16.gguf b/thinking-llama-8b-specific.f16.gguf new file mode 100644 index 0000000..3a8ad4b --- /dev/null +++ b/thinking-llama-8b-specific.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62453b6c7d516b481b7692564e21a92d595a03d407f155509c4c6c21aa3dbdf4 +size 16068896160