commit 6cc07a4d139290cf1fd38d63f6d12e1eb2b8f552 Author: ModelHub XC Date: Fri Jul 31 20:11:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..100bb77 --- /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 +Reasoning-Llama-3.1-CoT-RE1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7f00d48 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: EpistemeAI/Reasoning-Llama-3.1-CoT-RE1 +datasets: +- bespokelabs/Bespoke-Stratos-17k +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/EpistemeAI/Reasoning-Llama-3.1-CoT-RE1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-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/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1.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. + + diff --git a/Reasoning-Llama-3.1-CoT-RE1.IQ4_XS.gguf b/Reasoning-Llama-3.1-CoT-RE1.IQ4_XS.gguf new file mode 100644 index 0000000..6e1696f --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82999704124fde6dd4d6d47b8b93cee2d11a27d893063ec60e9298a5f1bd25e +size 4484368576 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q2_K.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q2_K.gguf new file mode 100644 index 0000000..e9d215c --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5e102f24d3b69e6cce0f171f73a1e1fd79c37c343a8d80ae26891c88ccdc06 +size 3179137216 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q3_K_L.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q3_K_L.gguf new file mode 100644 index 0000000..fd2ce7f --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:231d2e6b9f49711a2d60365d00b8956f9878519dfcf1026bb9900c1db1259eb0 +size 4321962176 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q3_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q3_K_M.gguf new file mode 100644 index 0000000..de35a38 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3567b34382953c586f0aa29c2e31fb6b4e9911e96865fb1594d414c22cf108d8 +size 4018923712 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q3_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q3_K_S.gguf new file mode 100644 index 0000000..71873d8 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261776df3742a9f6d0a6e8ebe58eba3527675d83b128732f882ad54f95b767a4 +size 3664505024 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q4_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q4_K_M.gguf new file mode 100644 index 0000000..98b3023 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ec026a4792a53c85c5ea289fbb2fd04600be11ff8d8e1443b8f8816d9add6a +size 4920740032 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q4_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q4_K_S.gguf new file mode 100644 index 0000000..ec97d09 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1452af44cee90fa626068cdc41caa26ebe2dd35a08f008958e3c27645ed67f9d +size 4692674752 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q5_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q5_K_M.gguf new file mode 100644 index 0000000..f81d433 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f19afbca95c9fdd1056ddb1d475970ec8075a9dcc0609560add56351b3c24268 +size 5732993216 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q5_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q5_K_S.gguf new file mode 100644 index 0000000..f66ca79 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315f71d504cc44ec74c8430660e2c9eec5c6a7ec169e282394877043a2ce0a9c +size 5599299776 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q6_K.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q6_K.gguf new file mode 100644 index 0000000..0d6bf7b --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc10dc6aa43db7e4b8182e93f44065aeeee487b40abed3f1140ecb52ce9d957 +size 6596012224 diff --git a/Reasoning-Llama-3.1-CoT-RE1.Q8_0.gguf b/Reasoning-Llama-3.1-CoT-RE1.Q8_0.gguf new file mode 100644 index 0000000..87e3141 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba34b95b68bfb1c483cee5042fbba128c41b2f5b8372ccd2991d2b4c8424f07f +size 8540776640 diff --git a/Reasoning-Llama-3.1-CoT-RE1.f16.gguf b/Reasoning-Llama-3.1-CoT-RE1.f16.gguf new file mode 100644 index 0000000..51e3e2f --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d50756d804fbd56e0b4761c346cd4ec9ae431161938fb26361fe02d695f325b +size 16068896960