commit 5be461a4d7051e6fd93bbdc831dac869b5fe8074 Author: ModelHub XC Date: Fri May 15 01:49:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLMWriter-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33020d4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +LLMWriter-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLMWriter-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLMWriter-8B.IQ4_XS.gguf b/LLMWriter-8B.IQ4_XS.gguf new file mode 100644 index 0000000..4371fb6 --- /dev/null +++ b/LLMWriter-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:958cd312708a2cc8dc0ae96c1dfe8d60eba2e7dac24201ac246260fe1042eb81 +size 4484363584 diff --git a/LLMWriter-8B.Q2_K.gguf b/LLMWriter-8B.Q2_K.gguf new file mode 100644 index 0000000..546d635 --- /dev/null +++ b/LLMWriter-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32f6c6e939e7831a892e8e6204c8bb05d10e36e9d69930bee4923ec45b3b681 +size 3179132224 diff --git a/LLMWriter-8B.Q3_K_L.gguf b/LLMWriter-8B.Q3_K_L.gguf new file mode 100644 index 0000000..eff7207 --- /dev/null +++ b/LLMWriter-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73246824426f58deeb5569c7c5567ee8994796c6a98989d4b88cc0f6d5251096 +size 4321957184 diff --git a/LLMWriter-8B.Q3_K_M.gguf b/LLMWriter-8B.Q3_K_M.gguf new file mode 100644 index 0000000..fd762dd --- /dev/null +++ b/LLMWriter-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28631a94a5d58c2fa9efcdfb2e3ecf1a0f193913d905184ca641cdfee104785e +size 4018918720 diff --git a/LLMWriter-8B.Q3_K_S.gguf b/LLMWriter-8B.Q3_K_S.gguf new file mode 100644 index 0000000..9321d26 --- /dev/null +++ b/LLMWriter-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93b35ea9c4aa9b12954baabf9e35e1859ba6923a727b8a5a310d27970d2de06 +size 3664500032 diff --git a/LLMWriter-8B.Q4_K_M.gguf b/LLMWriter-8B.Q4_K_M.gguf new file mode 100644 index 0000000..5c62509 --- /dev/null +++ b/LLMWriter-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16114e62650686171db80ae2cea9a4e4ac4f9b07aa51be17b7c4616ba0b10a2f +size 4920735040 diff --git a/LLMWriter-8B.Q4_K_S.gguf b/LLMWriter-8B.Q4_K_S.gguf new file mode 100644 index 0000000..550d635 --- /dev/null +++ b/LLMWriter-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3985cd0084ea42e9c09e94c2db472fe7cd214d027f947ab5e0a8b74b21fe2840 +size 4692669760 diff --git a/LLMWriter-8B.Q5_K_M.gguf b/LLMWriter-8B.Q5_K_M.gguf new file mode 100644 index 0000000..5587715 --- /dev/null +++ b/LLMWriter-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7444188be5fc780355a440ccf2e2844046495616c61e1e331ff4e35c411276e5 +size 5732988224 diff --git a/LLMWriter-8B.Q5_K_S.gguf b/LLMWriter-8B.Q5_K_S.gguf new file mode 100644 index 0000000..40a0afa --- /dev/null +++ b/LLMWriter-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d9e859c551d1b523f1a70219ea31b6b1cada77de010f43bd8f68fad6e3dc26 +size 5599294784 diff --git a/LLMWriter-8B.Q6_K.gguf b/LLMWriter-8B.Q6_K.gguf new file mode 100644 index 0000000..bac2322 --- /dev/null +++ b/LLMWriter-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2bd91885224f0b11df76969df5bb8ca4f5afd355d1c2228c97859ab207d21c8 +size 6596007232 diff --git a/LLMWriter-8B.Q8_0.gguf b/LLMWriter-8B.Q8_0.gguf new file mode 100644 index 0000000..1531e06 --- /dev/null +++ b/LLMWriter-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3949151a1da4b764de7318aa36dfe42f3fd84c59537aa3e6323ea14783d1329e +size 8540771648 diff --git a/LLMWriter-8B.f16.gguf b/LLMWriter-8B.f16.gguf new file mode 100644 index 0000000..d155ad0 --- /dev/null +++ b/LLMWriter-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453bca71d0441b254b188ac7d1c2328e1f3ec29fa742fecd6a0208a620e665d6 +size 16068891968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..48a3c34 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: aldenirsrv/LLMWriter-8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/aldenirsrv/LLMWriter-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLMWriter-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLMWriter-8B-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/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLMWriter-8B-GGUF/resolve/main/LLMWriter-8B.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. + +