commit 6b2bbe16eaad8e29786b85be6aa36fd69e47312f Author: ModelHub XC Date: Thu Jun 25 17:56:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Fin-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..90a45cd --- /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 +Llama-Fin-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Fin-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Fin-8b.IQ4_XS.gguf b/Llama-Fin-8b.IQ4_XS.gguf new file mode 100644 index 0000000..a0f1d7f --- /dev/null +++ b/Llama-Fin-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9304117daa486ed823fc2af115cbd93f87bb7f56e015e4b8db5700466e3d9a2 +size 4484363456 diff --git a/Llama-Fin-8b.Q2_K.gguf b/Llama-Fin-8b.Q2_K.gguf new file mode 100644 index 0000000..0867b91 --- /dev/null +++ b/Llama-Fin-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8219c1439399a30f1233ab6ff54d95a0dea87a495284c19e34875aa86f15c14 +size 3179132096 diff --git a/Llama-Fin-8b.Q3_K_L.gguf b/Llama-Fin-8b.Q3_K_L.gguf new file mode 100644 index 0000000..78da525 --- /dev/null +++ b/Llama-Fin-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad31b1a694418db459ed71b46e22d0f5153f669001b1f921f6467194382fb8d2 +size 4321957056 diff --git a/Llama-Fin-8b.Q3_K_M.gguf b/Llama-Fin-8b.Q3_K_M.gguf new file mode 100644 index 0000000..1221843 --- /dev/null +++ b/Llama-Fin-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142f85809a9fdd36d6cc95063c81172459011e18444beb2c6c4e5322f0921abb +size 4018918592 diff --git a/Llama-Fin-8b.Q3_K_S.gguf b/Llama-Fin-8b.Q3_K_S.gguf new file mode 100644 index 0000000..c3ee210 --- /dev/null +++ b/Llama-Fin-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fefbf6b5e17a5917b8908e602d167899d28b28f23f1c9a9178cf9ba31fde35b +size 3664499904 diff --git a/Llama-Fin-8b.Q4_K_M.gguf b/Llama-Fin-8b.Q4_K_M.gguf new file mode 100644 index 0000000..a199c59 --- /dev/null +++ b/Llama-Fin-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a48f14ca153da3c4d00d1eaa5f2fae6e0f32febea216f942feccd69307635a +size 4920734912 diff --git a/Llama-Fin-8b.Q4_K_S.gguf b/Llama-Fin-8b.Q4_K_S.gguf new file mode 100644 index 0000000..c5a8b99 --- /dev/null +++ b/Llama-Fin-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7d4fada10a70ca61926d84c4c09188f6b0b78ffa85909379ac4bb5ac7695fd +size 4692669632 diff --git a/Llama-Fin-8b.Q5_K_M.gguf b/Llama-Fin-8b.Q5_K_M.gguf new file mode 100644 index 0000000..a17d7b8 --- /dev/null +++ b/Llama-Fin-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a10ec42c782e582fd3a050efa31a20ea6e1c4024e72e8d89ff7d07c8e70f288 +size 5732988096 diff --git a/Llama-Fin-8b.Q5_K_S.gguf b/Llama-Fin-8b.Q5_K_S.gguf new file mode 100644 index 0000000..007b335 --- /dev/null +++ b/Llama-Fin-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72fd88c9b5b7e5e5dfcd7d9a64369c41b7107eb8e7b32fe23e80917ad40ec9e +size 5599294656 diff --git a/Llama-Fin-8b.Q6_K.gguf b/Llama-Fin-8b.Q6_K.gguf new file mode 100644 index 0000000..1d8d015 --- /dev/null +++ b/Llama-Fin-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa7ea25b6dd0b23fedcd1537ad5b0dbe968ba10d438f01d45f0387a5688005d +size 6596007104 diff --git a/Llama-Fin-8b.Q8_0.gguf b/Llama-Fin-8b.Q8_0.gguf new file mode 100644 index 0000000..31eb106 --- /dev/null +++ b/Llama-Fin-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98530d324b0968a73c121357fcda08e0b1f27cfab3ddded2ac840e49d489dc1 +size 8540771520 diff --git a/Llama-Fin-8b.f16.gguf b/Llama-Fin-8b.f16.gguf new file mode 100644 index 0000000..b904fe5 --- /dev/null +++ b/Llama-Fin-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bdfa02a0f6dca1ec4a9aaa180683764f3db9a819e68e6e1414f2772766271c4 +size 16068891840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd732e9 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Salesforce/Llama-Fin-8b +datasets: +- Salesforce/FinTrain +- Salesforce/FinEval +language: +- en +library_name: transformers +license: cc-by-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Salesforce/Llama-Fin-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-Fin-8b-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/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Fin-8b-GGUF/resolve/main/Llama-Fin-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. + +