commit 99f69ba8a1d6e5d7889237456d00393705eaf464 Author: ModelHub XC Date: Sat Aug 1 08:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c0fc18 --- /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-3-1-8b-answer-generator-ft-2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-1-8b-answer-generator-ft-2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4922b0b --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: terencezhang2024/llama-3-1-8b-answer-generator-ft-2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/terencezhang2024/llama-3-1-8b-answer-generator-ft-2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3-1-8b-answer-generator-ft-2-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-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-1-8b-answer-generator-ft-2-GGUF/resolve/main/llama-3-1-8b-answer-generator-ft-2.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/llama-3-1-8b-answer-generator-ft-2.IQ4_XS.gguf b/llama-3-1-8b-answer-generator-ft-2.IQ4_XS.gguf new file mode 100644 index 0000000..1f3adeb --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453602a9113db49cd315050039389e04ea01470a3cbec68e74d7027f6e97d72e +size 4484368000 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q2_K.gguf b/llama-3-1-8b-answer-generator-ft-2.Q2_K.gguf new file mode 100644 index 0000000..4271b88 --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26ec968e1b089209e462ce3cb9cebe3f53b02d06b8b78fc790d7d0ce0621bced +size 3179136640 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q3_K_L.gguf b/llama-3-1-8b-answer-generator-ft-2.Q3_K_L.gguf new file mode 100644 index 0000000..2bd6750 --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe12a0b2051035eef9fb6be66b3ed88a41c900a76867fb2ad66be221b57a6278 +size 4321961600 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q3_K_M.gguf b/llama-3-1-8b-answer-generator-ft-2.Q3_K_M.gguf new file mode 100644 index 0000000..a36d3c1 --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2bb8bae93c02871ef427e1fefccd5c942f7642be635155435e2c292084f7269 +size 4018923136 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q3_K_S.gguf b/llama-3-1-8b-answer-generator-ft-2.Q3_K_S.gguf new file mode 100644 index 0000000..92183cf --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d239929abfec20401487dd6525f82f03f79ad380353d8c2c0b9676e545d848b5 +size 3664504448 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q4_K_M.gguf b/llama-3-1-8b-answer-generator-ft-2.Q4_K_M.gguf new file mode 100644 index 0000000..378a373 --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a664e94e3b8e3566d41db38301a42880f59d96c3c443ee5a2b27ae5decbce4d0 +size 4920739456 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q4_K_S.gguf b/llama-3-1-8b-answer-generator-ft-2.Q4_K_S.gguf new file mode 100644 index 0000000..ba08169 --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f0f6849754db8c428bd4ee9283c31fe1dc99789270469904a95a126925b69ed +size 4692674176 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q5_K_M.gguf b/llama-3-1-8b-answer-generator-ft-2.Q5_K_M.gguf new file mode 100644 index 0000000..4dc151c --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e458028eb1ee47f66b6d9feb9a918b49b5227bd9cdacd40fedfc69100d676d77 +size 5732992640 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q5_K_S.gguf b/llama-3-1-8b-answer-generator-ft-2.Q5_K_S.gguf new file mode 100644 index 0000000..a1ab293 --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214f6da1b0d0d718d31e11ac3c2957b98f1d3966bb057370360ec82a38ad3c38 +size 5599299200 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q6_K.gguf b/llama-3-1-8b-answer-generator-ft-2.Q6_K.gguf new file mode 100644 index 0000000..a35c50a --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8623214eff967d067cbc5f4f5440693f6e44a266b481227f1ceaa7e262cc10 +size 6596011648 diff --git a/llama-3-1-8b-answer-generator-ft-2.Q8_0.gguf b/llama-3-1-8b-answer-generator-ft-2.Q8_0.gguf new file mode 100644 index 0000000..a0c06de --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b67a1e66e5ed228824e27a76da10621fc1c56442bc8d7b9626089889bea51d12 +size 8540776064 diff --git a/llama-3-1-8b-answer-generator-ft-2.f16.gguf b/llama-3-1-8b-answer-generator-ft-2.f16.gguf new file mode 100644 index 0000000..ea78f6b --- /dev/null +++ b/llama-3-1-8b-answer-generator-ft-2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4cde6e8afc9302ebe858db9249f5b0c3c076c14231c674ac49f634bcdd2fd94 +size 16068896384