commit 1f37a540f449cdabf376b14ec8f5984821a7df6f Author: ModelHub XC Date: Tue Sep 8 19:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FineLlama-3.1-8B_instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e8d6ffb --- /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 +FineLlama-3.1-8B_instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B_instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FineLlama-3.1-8B_instruct.IQ4_XS.gguf b/FineLlama-3.1-8B_instruct.IQ4_XS.gguf new file mode 100644 index 0000000..6fd12ed --- /dev/null +++ b/FineLlama-3.1-8B_instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca328e24e2490f83cdc8f24bf059c03345eb76aceef4caca62b53dd8c95a7c0e +size 4484364576 diff --git a/FineLlama-3.1-8B_instruct.Q2_K.gguf b/FineLlama-3.1-8B_instruct.Q2_K.gguf new file mode 100644 index 0000000..218da0d --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d2f4fff447732ba7b96559179c9a05d5d81833a44966c223971981ad9edb58 +size 3179133216 diff --git a/FineLlama-3.1-8B_instruct.Q3_K_L.gguf b/FineLlama-3.1-8B_instruct.Q3_K_L.gguf new file mode 100644 index 0000000..47a373c --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d6234fd1426261739935d3e55d8f344339b205b09c83b482e77b89617e059fc +size 4321958176 diff --git a/FineLlama-3.1-8B_instruct.Q3_K_M.gguf b/FineLlama-3.1-8B_instruct.Q3_K_M.gguf new file mode 100644 index 0000000..76e846b --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80a1b27d6de39991cdbf01449a028de6dcfa08ff5be58dd977d574b955c195f +size 4018919712 diff --git a/FineLlama-3.1-8B_instruct.Q3_K_S.gguf b/FineLlama-3.1-8B_instruct.Q3_K_S.gguf new file mode 100644 index 0000000..b0b59e1 --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd801ebc70ac7257fa48f0f22fd1780f955ab254403100e7b7aa3b62bbf73cd1 +size 3664501024 diff --git a/FineLlama-3.1-8B_instruct.Q4_0_4_4.gguf b/FineLlama-3.1-8B_instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..4140961 --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b83dac5e2281fb21efd655fd259847b4eff86d64bb33e4ed34f7815c95177a +size 4661213472 diff --git a/FineLlama-3.1-8B_instruct.Q4_K_M.gguf b/FineLlama-3.1-8B_instruct.Q4_K_M.gguf new file mode 100644 index 0000000..43ae749 --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfcaac5a6a092751e09a2e6043e31ea9c0d44e6823beaa1c3729cc8f72a7bf70 +size 4920736032 diff --git a/FineLlama-3.1-8B_instruct.Q4_K_S.gguf b/FineLlama-3.1-8B_instruct.Q4_K_S.gguf new file mode 100644 index 0000000..eb20661 --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e68d9834374b87891e6a0fcde331dd097a7f7f9d64eb66dce0376314ba3293 +size 4692670752 diff --git a/FineLlama-3.1-8B_instruct.Q5_K_M.gguf b/FineLlama-3.1-8B_instruct.Q5_K_M.gguf new file mode 100644 index 0000000..c0e508b --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:857ef7663a0b242859897138171a8a51ab945e7fd31f1a4a9ac2297e3cdd50d5 +size 5732989216 diff --git a/FineLlama-3.1-8B_instruct.Q5_K_S.gguf b/FineLlama-3.1-8B_instruct.Q5_K_S.gguf new file mode 100644 index 0000000..9f13ba0 --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8213685a4095d0b5e3092be03c16ac3b8a2fa98c20177cee6c414225484aa815 +size 5599295776 diff --git a/FineLlama-3.1-8B_instruct.Q6_K.gguf b/FineLlama-3.1-8B_instruct.Q6_K.gguf new file mode 100644 index 0000000..5240cb6 --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa43ad6ffd05eadceab38f4d6abfdbb9b66ae20d51fab00f5a3d353fa1f9fead +size 6596008224 diff --git a/FineLlama-3.1-8B_instruct.Q8_0.gguf b/FineLlama-3.1-8B_instruct.Q8_0.gguf new file mode 100644 index 0000000..0d50dd0 --- /dev/null +++ b/FineLlama-3.1-8B_instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f4c8a5918d69ec35df069d2a3009abfd6af6047d8d0423b6a643312b1a6c93 +size 8540772640 diff --git a/FineLlama-3.1-8B_instruct.f16.gguf b/FineLlama-3.1-8B_instruct.f16.gguf new file mode 100644 index 0000000..dbb3332 --- /dev/null +++ b/FineLlama-3.1-8B_instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b026a39f701d47830aba7ba8505edc7d2a732b5735f1a623f17d2e3a2f71fa70 +size 16068892960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..90d39f2 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: phogen/FineLlama-3.1-8B_instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/phogen/FineLlama-3.1-8B_instruct + + +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/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B_instruct-GGUF/resolve/main/FineLlama-3.1-8B_instruct.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. + +