commit 3ba06198af921f7a38082abb3ab2265ea92f0961 Author: ModelHub XC Date: Sun Oct 18 23:38:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..30b451b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-128K-QLoRA-Merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_M.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_M.gguf new file mode 100644 index 0000000..c1209fc --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7ee6ad29e73bdded5aa849e2eef57aa28798b9023dbbfa3be5d9f74e66136c +size 3784823264 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_S.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_S.gguf new file mode 100644 index 0000000..a79b899 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31a072e3980b36e7b4f54a1b4ecc4b127bd8ed37f1bb2e1da92264f6096247e +size 3682324960 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_XS.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_XS.gguf new file mode 100644 index 0000000..c2b9319 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfe77683273b5df12494eda5ee4635909e92917c4790caa4e342f626cc09d7c +size 3518747104 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ4_XS.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ4_XS.gguf new file mode 100644 index 0000000..8b8c806 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7358037595fa620e98de595fb229edddda4bd2d269cea31bb244aea72a3a3b18 +size 4484362720 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q2_K.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q2_K.gguf new file mode 100644 index 0000000..24524c1 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc9be4b106032f62f7daa8249dc6e7522f9c839814246f03e85e5993abb96b7 +size 3179131360 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_L.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_L.gguf new file mode 100644 index 0000000..e652cf6 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b46e0c260a892f6a604a9f7ddb0f367fe048bd1933436007d9325717de8fef1 +size 4321956320 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_M.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_M.gguf new file mode 100644 index 0000000..a21912d --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95244294be67bcd2e59fa072fc64f6017eb881990f1cba88cb3fdd471980b81a +size 4018917856 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_S.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_S.gguf new file mode 100644 index 0000000..d60da8b --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16cb6e65c4b8498d377d6c756b1b3da07e3c38c96de6eb9d03b4584d54a582aa +size 3664499168 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_M.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_M.gguf new file mode 100644 index 0000000..376fa0e --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d3e8f69ef2b3725493832de901348e4a318ce7e6e125be2e5eda9fb4c2c010 +size 4920734176 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_S.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_S.gguf new file mode 100644 index 0000000..cec7fcd --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43418679397d278951856250299be4e0c255e7dfef8d80cd6a6406cab629b980 +size 4692668896 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_M.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_M.gguf new file mode 100644 index 0000000..82e3b62 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e82ca053e9b7dbc59afadf0f3b053cc7287c29cd57b97b997337067f169fc00e +size 5732987360 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_S.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_S.gguf new file mode 100644 index 0000000..7a0fe95 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33713e81339cf6e500dab534e01af6729e649050d5667b7d013d2c2a0eb0543b +size 5599293920 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q6_K.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q6_K.gguf new file mode 100644 index 0000000..2df8368 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f29dd2aac582898b7a030f2a3925a10477b0be23cd2370212de891785e83ce2 +size 6596006368 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q8_0.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q8_0.gguf new file mode 100644 index 0000000..0543b3d --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c621d383fc5e7f3e5e2b36b4a3093b80aa7c506f4d3a753e1c8f2359d8ec637 +size 8540770784 diff --git a/Llama-3-8B-Instruct-128K-QLoRA-Merged.f16.gguf b/Llama-3-8B-Instruct-128K-QLoRA-Merged.f16.gguf new file mode 100644 index 0000000..a8fb607 --- /dev/null +++ b/Llama-3-8B-Instruct-128K-QLoRA-Merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be879525a0eaa855fc8548688ff24574987c72a9e6d3bf2e8ebd2c2c762db69a +size 16068891104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7cd4b47 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +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-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-128K-QLoRA-Merged.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-128K-QLoRA-Merged-GGUF/resolve/main/Llama-3-8B-Instruct-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. + +