commit 59e4fb05b0c76c1caf09036aca61ac911ad2ebaf Author: ModelHub XC Date: Sun Jun 14 18:42:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7890b43 --- /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 +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.IQ4_XS.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..978e152 --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54afc8c748197359b30b8adaf7e1cecb061123e9b1bf990cc8b45f64f4edde6c +size 4484363680 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q2_K.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..059f194 --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dfc9a10905258556055bdcc9a6c9d68f99e50e660e0d20f64402a4fc5e98496 +size 3179132320 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_L.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..dfbb901 --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59045eec26bdb749513ad1462797c24620341f3a6e12ba665b1e99401ba344c8 +size 4321957280 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_M.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..beee186 --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b902cfb0f220e31883923249f5c5c1172a1f5d968d1de4047a6ee4e52c5bdf +size 4018918816 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_S.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..fd2b15d --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d767c71010b4d76f3e5254f5fb0d79c629245fcdb4c4bb380dd15c2e93ff52 +size 3664500128 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_M.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..b4f29fd --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3821747fb783b8c9b048d3e74fbecc7c11bea5f514dc410e8112a035dedfb44e +size 4920735136 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_S.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..b2dd69f --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:243c4ceaf381e925d542af460ab5d31e7334f0a54792e2025cf1b3d2e92677a3 +size 4692669856 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_M.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..02e5ecf --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8068e938b5e9c3501a75f0095e5a0017912e22c218273ee38096af64ede6b1db +size 5732988320 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_S.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..ba3ca5f --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d116d535b199c83dbfad44e8bd9a4fed5767186d1450fabba01e22945133192e +size 5599294880 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q6_K.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..0470e4b --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f861f561f0e695f276b090f0e41f8f3725435622af766ffb1281fae9ac73b98 +size 6596007328 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q8_0.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..54e4198 --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4258577036924a995d85055e40c63ed27552c7d0459fd42d09c59dbeed0c5c4 +size 8540771744 diff --git a/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.f16.gguf b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.f16.gguf new file mode 100644 index 0000000..f3a4444 --- /dev/null +++ b/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579f19deb840a44a6fb0fda1f5f1c1cc0aaf9bf0dd576cf049253f988dd3865b +size 16068892064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..409034d --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: 007ankit/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1 +language: +- hi +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/007ankit/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-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/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1-GGUF/resolve/main/JSL-MedLlama-3-8B-v1.0-LLama3-Gaja-Hindi-8B-v0.1.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. + +