commit 95d536087b2e02d6bab88fcebc2ff431cebf5491 Author: ModelHub XC Date: Mon Sep 28 14:53:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..06767e6 --- /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-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.IQ4_XS.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.IQ4_XS.gguf new file mode 100644 index 0000000..82abf5f --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ba7360c4a3876fa572ab5500137a3979838f4099de8c0d09ae508c07210722 +size 4484363488 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q2_K.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q2_K.gguf new file mode 100644 index 0000000..e6f4082 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e681e3ace7fcaf0422e3baf7d9649490882bf7a847ed40d619a45ecc38fd536 +size 3179132128 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_L.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_L.gguf new file mode 100644 index 0000000..5210d09 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ccc6528cfd09b280a757b543607434038c1a2de14d8f55aece860604e7512d3 +size 4321957088 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_M.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_M.gguf new file mode 100644 index 0000000..fe69336 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914c6c72f87b83b9985cb25feb1c85f5f135b3df9bdaaaa1977cfd76a9dc583c +size 4018918624 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_S.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_S.gguf new file mode 100644 index 0000000..3c0d9c6 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32ce5280b5296d35387955b0b250e9df6f02f6ac214d4fa88d1dc4433900c980 +size 3664499936 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_M.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_M.gguf new file mode 100644 index 0000000..3384227 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:785ba258040d8874db2eec0dc3b5465fff295d0373f1c48eec8db3d20879d284 +size 4920734944 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_S.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_S.gguf new file mode 100644 index 0000000..c092690 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d4bf0dbdaf0a80436bb663a080fb09bb3e12566a9b15747cb1b1867fe998fa +size 4692669664 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_M.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_M.gguf new file mode 100644 index 0000000..a0cf0f9 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba7c8939b8d83fd89149ae78abb45224bdfd9ce9990bbe077e7a0460e43f982 +size 5732988128 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_S.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_S.gguf new file mode 100644 index 0000000..89ee66c --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d802ede888d0b03298b03bd0e5e2369320e88fc65d4f750a80a789f6921c5a +size 5599294688 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q6_K.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q6_K.gguf new file mode 100644 index 0000000..5a9e65f --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a8fca0f6838033237b563e835a1bf0172d578c1dd189d5c8ab8c34529b6408 +size 6596007136 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q8_0.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q8_0.gguf new file mode 100644 index 0000000..8f0835f --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1ee92a1f6c77d1aafa1bce41b5e0a865c02d87b36f4fed1ae2040d12212faf +size 8540771552 diff --git a/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.f16.gguf b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.f16.gguf new file mode 100644 index 0000000..30361c5 --- /dev/null +++ b/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b472f6b88952699e290d02b72b47a4e9889b522f5b4ead366e041bc26c3a2621 +size 16068891872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5d80ee7 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Ayush-1722/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged +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/Ayush-1722/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged + + +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-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-v0.1-128K-QLoRA-Merged.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. + +