commit f74a937541427c2cae5badac87300a7e7101b2cb Author: ModelHub XC Date: Fri Apr 24 19:30:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..32b0125 --- /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-lora-hinglish.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-lora-hinglish.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..32c2e3b --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: sudhir2016/llama-3-8b-Instruct-lora-hinglish +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/sudhir2016/llama-3-8b-Instruct-lora-hinglish + + +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-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-lora-hinglish-GGUF/resolve/main/llama-3-8b-Instruct-lora-hinglish.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/llama-3-8b-Instruct-lora-hinglish.IQ4_XS.gguf b/llama-3-8b-Instruct-lora-hinglish.IQ4_XS.gguf new file mode 100644 index 0000000..92ffbc7 --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ad26ea4e51d0e3a5098decf883ca38b6533603ae3c846a91a62fcf47f08456 +size 4484363776 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q2_K.gguf b/llama-3-8b-Instruct-lora-hinglish.Q2_K.gguf new file mode 100644 index 0000000..c1e783b --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ae8dbe9126d3fb019ac09f12a200b66348521f645abda55e0f6d40741d0606 +size 3179132416 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q3_K_L.gguf b/llama-3-8b-Instruct-lora-hinglish.Q3_K_L.gguf new file mode 100644 index 0000000..d40b6cc --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19362b9307398f01933ae6811d2c73f0068ae0458cc9e55354fdd7bf0e701db5 +size 4321957376 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q3_K_M.gguf b/llama-3-8b-Instruct-lora-hinglish.Q3_K_M.gguf new file mode 100644 index 0000000..be8583c --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:748132b3d514d559465c14948e63ddad19cb6551c6b565ccef81194a6f8db395 +size 4018918912 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q3_K_S.gguf b/llama-3-8b-Instruct-lora-hinglish.Q3_K_S.gguf new file mode 100644 index 0000000..bd4d54a --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49a59bf3a29e2209ed924ab663617e316090777aa56670b06a82777ef21c002 +size 3664500224 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q4_K_M.gguf b/llama-3-8b-Instruct-lora-hinglish.Q4_K_M.gguf new file mode 100644 index 0000000..2711359 --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8fcdd46636d5cd7c4710cdc08b4f7f520630fce25a415300ad40d54277dae0 +size 4920735232 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q4_K_S.gguf b/llama-3-8b-Instruct-lora-hinglish.Q4_K_S.gguf new file mode 100644 index 0000000..f5f78e3 --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43674f3abb1eef79c766c7c6587836952be0a8d83e0e038586dab64e6290b43 +size 4692669952 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q5_K_M.gguf b/llama-3-8b-Instruct-lora-hinglish.Q5_K_M.gguf new file mode 100644 index 0000000..81a8efe --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41087b10d3792586d5cb757d59a7d64a0c4a462ce7830682642e74929539b6dd +size 5732988416 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q5_K_S.gguf b/llama-3-8b-Instruct-lora-hinglish.Q5_K_S.gguf new file mode 100644 index 0000000..4c32e2b --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40af360462fdc92712f67a4eb3ac9a736fa2503d478947c962ad93d1c91b5d9a +size 5599294976 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q6_K.gguf b/llama-3-8b-Instruct-lora-hinglish.Q6_K.gguf new file mode 100644 index 0000000..f5872ed --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f495628c8df607f31abe308392e2a916fb43607d001185e7ba13a13b9a7baa00 +size 6596007424 diff --git a/llama-3-8b-Instruct-lora-hinglish.Q8_0.gguf b/llama-3-8b-Instruct-lora-hinglish.Q8_0.gguf new file mode 100644 index 0000000..9127d2d --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36247dc93fc70194f89fbfb617901c194d609c7f653667876dc6dc7705b88a84 +size 8540771840 diff --git a/llama-3-8b-Instruct-lora-hinglish.f16.gguf b/llama-3-8b-Instruct-lora-hinglish.f16.gguf new file mode 100644 index 0000000..3f246cd --- /dev/null +++ b/llama-3-8b-Instruct-lora-hinglish.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1019746ed0d46201e25347ddf9ba6194876db2a2d499958b88814b9ba266d0 +size 16068892160