commit 4ed682f7e545730dbaed1f708d73ac45b943aa7a Author: ModelHub XC Date: Sun Jun 14 01:29:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/deepseek-r1-llama-8b-gold-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7ae55b4 --- /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 +deepseek-r1-llama-8b-gold.f16.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-llama-8b-gold.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..dcf2937 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: haorandai/deepseek-r1-llama-8b-gold +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/haorandai/deepseek-r1-llama-8b-gold + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#deepseek-r1-llama-8b-gold-GGUF).*** + +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/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-llama-8b-gold-GGUF/resolve/main/deepseek-r1-llama-8b-gold.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/deepseek-r1-llama-8b-gold.IQ4_XS.gguf b/deepseek-r1-llama-8b-gold.IQ4_XS.gguf new file mode 100644 index 0000000..1ecad5f --- /dev/null +++ b/deepseek-r1-llama-8b-gold.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5798f26b084a5f0750c50ad176215b6d48b2e3348d8ed1ab638716828d70147e +size 4484365600 diff --git a/deepseek-r1-llama-8b-gold.Q2_K.gguf b/deepseek-r1-llama-8b-gold.Q2_K.gguf new file mode 100644 index 0000000..cc629aa --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de609d1ced545ef5da718464e77b7094eead7b554a71d60a1870db9de5b60f1b +size 3179134240 diff --git a/deepseek-r1-llama-8b-gold.Q3_K_L.gguf b/deepseek-r1-llama-8b-gold.Q3_K_L.gguf new file mode 100644 index 0000000..fd4fa77 --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d7e80f31a1a72a3a0c1f876d959e5c9d08c300fefbcd06b4158e3620096f75 +size 4321959200 diff --git a/deepseek-r1-llama-8b-gold.Q3_K_M.gguf b/deepseek-r1-llama-8b-gold.Q3_K_M.gguf new file mode 100644 index 0000000..f2e5a8f --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e1c9b4baa9cbab7930343f6724a5a3d5869101928e407e3e24face6d5b504d +size 4018920736 diff --git a/deepseek-r1-llama-8b-gold.Q3_K_S.gguf b/deepseek-r1-llama-8b-gold.Q3_K_S.gguf new file mode 100644 index 0000000..0ef40e3 --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50eb29e11f7d77bc341998c5827be08d850fa418c095979f1c8a06314a48c44 +size 3664502048 diff --git a/deepseek-r1-llama-8b-gold.Q4_K_M.gguf b/deepseek-r1-llama-8b-gold.Q4_K_M.gguf new file mode 100644 index 0000000..8fd3d0e --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a333bf1197922c6c06a2122c94917ff5d8490587472a14e7d58608832ecf14b0 +size 4920737056 diff --git a/deepseek-r1-llama-8b-gold.Q4_K_S.gguf b/deepseek-r1-llama-8b-gold.Q4_K_S.gguf new file mode 100644 index 0000000..9111096 --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76fbe4ad6289ba388f65dd3eee5d0f8f384659577b04c382b25f9f23f940743 +size 4692671776 diff --git a/deepseek-r1-llama-8b-gold.Q5_K_M.gguf b/deepseek-r1-llama-8b-gold.Q5_K_M.gguf new file mode 100644 index 0000000..2667604 --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a87b047f54112668f7bd78d4d6b11bb39913137b5f18317470d4b0bbc939b98 +size 5732990240 diff --git a/deepseek-r1-llama-8b-gold.Q5_K_S.gguf b/deepseek-r1-llama-8b-gold.Q5_K_S.gguf new file mode 100644 index 0000000..66febab --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa86e27da940017dce4435eb0f664868dbee9be00959a18c58b94d85fc2113cf +size 5599296800 diff --git a/deepseek-r1-llama-8b-gold.Q6_K.gguf b/deepseek-r1-llama-8b-gold.Q6_K.gguf new file mode 100644 index 0000000..51af5c2 --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e392a2a6542991c28e59806f1577f5be75644676614bd3b9121a7179bb3846 +size 6596009248 diff --git a/deepseek-r1-llama-8b-gold.Q8_0.gguf b/deepseek-r1-llama-8b-gold.Q8_0.gguf new file mode 100644 index 0000000..4539634 --- /dev/null +++ b/deepseek-r1-llama-8b-gold.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b880867685c0cb822da50549f48568b8de48cfe80bdd5458f2615c7f67f17e70 +size 8540773664 diff --git a/deepseek-r1-llama-8b-gold.f16.gguf b/deepseek-r1-llama-8b-gold.f16.gguf new file mode 100644 index 0000000..480d003 --- /dev/null +++ b/deepseek-r1-llama-8b-gold.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba692694be63c11bb8db2ee7da155f0ee2cd1598850c570cd054e5103c1ee568 +size 16068893984