commit 56ea24fc34dafd8cf387eb69de7a17715f48be32 Author: ModelHub XC Date: Sun Jun 14 20:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FinID-8B-Chat-FP16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5e279f2 --- /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 +FinID-8B-Chat-FP16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.f16.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FinID-8B-Chat-FP16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FinID-8B-Chat-FP16.IQ4_XS.gguf b/FinID-8B-Chat-FP16.IQ4_XS.gguf new file mode 100644 index 0000000..5e73bb5 --- /dev/null +++ b/FinID-8B-Chat-FP16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77aaaa1d8cdfbfe7645652b00f37bd1955a35b1e167643e8835d4881aba8b302 +size 4756845632 diff --git a/FinID-8B-Chat-FP16.Q2_K.gguf b/FinID-8B-Chat-FP16.Q2_K.gguf new file mode 100644 index 0000000..1cc21ce --- /dev/null +++ b/FinID-8B-Chat-FP16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3386c5f158a658b08747ee47750862fe60f3b4a711f4da6a140d4effffde4382 +size 3355996224 diff --git a/FinID-8B-Chat-FP16.Q3_K_L.gguf b/FinID-8B-Chat-FP16.Q3_K_L.gguf new file mode 100644 index 0000000..3afc3c0 --- /dev/null +++ b/FinID-8B-Chat-FP16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:904f3275732b06dd75f247138bf74c5474fa980451370aec94f534bae05dac3c +size 4573778496 diff --git a/FinID-8B-Chat-FP16.Q3_K_M.gguf b/FinID-8B-Chat-FP16.Q3_K_M.gguf new file mode 100644 index 0000000..298f7fc --- /dev/null +++ b/FinID-8B-Chat-FP16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea78e25f2eb9b5f5ef0dbd74afcfb2507df6060477a2c2f7f61aaf13197c870c +size 4260909632 diff --git a/FinID-8B-Chat-FP16.Q3_K_S.gguf b/FinID-8B-Chat-FP16.Q3_K_S.gguf new file mode 100644 index 0000000..d86c1ae --- /dev/null +++ b/FinID-8B-Chat-FP16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76b23d546e3f06f57effecc12c98e40bf29ffc62787758ba7cefd405542e4be +size 3892531776 diff --git a/FinID-8B-Chat-FP16.Q4_K_M.gguf b/FinID-8B-Chat-FP16.Q4_K_M.gguf new file mode 100644 index 0000000..26b623e --- /dev/null +++ b/FinID-8B-Chat-FP16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9883f97d6b5a282d5f7e58285631829b5970efccfa3542e4275327371572376 +size 5242936384 diff --git a/FinID-8B-Chat-FP16.Q4_K_S.gguf b/FinID-8B-Chat-FP16.Q4_K_S.gguf new file mode 100644 index 0000000..f090119 --- /dev/null +++ b/FinID-8B-Chat-FP16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07dd329a44a1c6cf6e8b614db9e9e98b2739a56c03f052c11550c2a369a485d +size 4990164032 diff --git a/FinID-8B-Chat-FP16.Q5_K_M.gguf b/FinID-8B-Chat-FP16.Q5_K_M.gguf new file mode 100644 index 0000000..c068555 --- /dev/null +++ b/FinID-8B-Chat-FP16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df8fc4313ea694cbb4253774d614c4a8e6838d84d192910a50e918f326e9a8a6 +size 6103727168 diff --git a/FinID-8B-Chat-FP16.Q5_K_S.gguf b/FinID-8B-Chat-FP16.Q5_K_S.gguf new file mode 100644 index 0000000..a3e4a40 --- /dev/null +++ b/FinID-8B-Chat-FP16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9872d34d35f791d9b6c680b606a0987d8c23363cac95493089897d61f4bb63 +size 5955550272 diff --git a/FinID-8B-Chat-FP16.Q6_K.gguf b/FinID-8B-Chat-FP16.Q6_K.gguf new file mode 100644 index 0000000..f276daa --- /dev/null +++ b/FinID-8B-Chat-FP16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06c6edc031b9c9909e4b97604decc68e77ec5e06ff3464af18d1dced5efafca +size 7018317376 diff --git a/FinID-8B-Chat-FP16.Q8_0.gguf b/FinID-8B-Chat-FP16.Q8_0.gguf new file mode 100644 index 0000000..d6635fb --- /dev/null +++ b/FinID-8B-Chat-FP16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47f8b0cf5d94fb418a3cbcb9366817c1d592dd5f42e8cbdafda0d932805422d +size 9088184896 diff --git a/FinID-8B-Chat-FP16.f16.gguf b/FinID-8B-Chat-FP16.f16.gguf new file mode 100644 index 0000000..46a01e0 --- /dev/null +++ b/FinID-8B-Chat-FP16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e813a6c38484cbd3ebb8c5b0ee3fa5ca8df303483e25c4136f99db168b457d +size 17100575296 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e992674 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: FOLZi/FinID-8B-Chat-FP16 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/FOLZi/FinID-8B-Chat-FP16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#FinID-8B-Chat-FP16-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/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q3_K_L.gguf) | Q3_K_L | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q4_K_M.gguf) | Q4_K_M | 5.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q5_K_S.gguf) | Q5_K_S | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FinID-8B-Chat-FP16-GGUF/resolve/main/FinID-8B-Chat-FP16.f16.gguf) | f16 | 17.2 | 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. + +