commit aea7ad93e79126f0bf35c10a8197944be1c99901 Author: ModelHub XC Date: Tue Jun 23 12:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7b416cc --- /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 +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.IQ4_XS.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..b49b7db --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:848a39e4f219a58b7fb3a7193a5838011a9608f71f7bad1605fe31f06ac319c4 +size 4484369504 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q2_K.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..1a777b3 --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd132b7e3175bab154739e581d8731bf02094e41141d33cdda9b1ee6c5fddcc +size 3179138144 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_L.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..52e621a --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9d29ebde5ecbf28d2fa080b1a505d3053a9957ecc2a8e006eba32219f32cbc +size 4321963104 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_M.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..0faed4a --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25975923ae85165c1440c5f2b426eab2343f4fce07a97874ba8b41a50e441d0f +size 4018924640 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_S.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..0fc8f95 --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba63bab77bbab8d613cfb975535b83d4bd6860d4844ff25ce678b8b1edd4ec63 +size 3664505952 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_M.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..0961d33 --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7339203fadc032c50a41b7c240f9cff05b0c33e5f163a180937b696ef287623 +size 4920740960 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_S.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..24c2e3b --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d0c75843d87a3a9df7cc001968fcf39bceff5b04390a64778e1a0f0bd3477a7 +size 4692675680 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_M.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..49f983f --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7cd85c9162d8b24245c712c0266e671511164bbee7bf2d58139b04750acea7 +size 5732994144 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_S.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..db449c7 --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1a145e638d1eb6da4e6efdf0f419bae650ef89793f4c019ab5161005487cd86 +size 5599300704 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q6_K.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..abaee0d --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b877a0aacac267f30307f8b07d267bf69c2e5d970973a60983afb28509abf2 +size 6596013152 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q8_0.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..60c7e06 --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b4023f2579c1826a2dea26a4f8cd2b292271ee3d2c709017636ad62d1d41da +size 8540777568 diff --git a/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.f16.gguf b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.f16.gguf new file mode 100644 index 0000000..e4dea43 --- /dev/null +++ b/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab151d691687e5ebb94017b46dedc86302e13fba208c43b1d3801540229e357e +size 16068897888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d1cb164 --- /dev/null +++ b/README.md @@ -0,0 +1,115 @@ +--- +base_model: DavidAU/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning +datasets: +- TeichAI/claude-4.5-opus-high-reasoning-250x +language: +- en +- fr +- de +- es +- it +- pt +- zh +- ja +- ru +- ko +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- thinking +- reasoning +- instruct +- Claude4.5-Opus +- creative +- creative writing +- fiction writing +- plot generation +- sub-plot generation +- fiction writing +- story generation +- scene continue +- storytelling +- fiction story +- science fiction +- romance +- all genres +- story +- writing +- vivid prosing +- vivid writing +- fiction +- roleplaying +- bfloat16 +- role play +- 128k context +- llama3.3 +- llama-3 +- llama-3.3 +- unsloth +- finetune +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DavidAU/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-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/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF/resolve/main/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning.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. + +