commit 38e8ee2bf629b659157b48b3cc510b5dae42efc2 Author: ModelHub XC Date: Wed May 6 12:20:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52b1240 --- /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 +Telugu-Llama2-7B-v0-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Telugu-Llama2-7B-v0-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1d456ba --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct +datasets: +- Telugu-LLM-Labs/yahma_alpaca_cleaned_telugu_filtered_and_romanized +- Telugu-LLM-Labs/teknium_GPTeacher_general_instruct_telugu_filtered_and_romanized +language: +- te +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct + + +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/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Telugu-Llama2-7B-v0-Instruct-GGUF/resolve/main/Telugu-Llama2-7B-v0-Instruct.f16.gguf) | f16 | 13.6 | 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/Telugu-Llama2-7B-v0-Instruct.IQ4_XS.gguf b/Telugu-Llama2-7B-v0-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..e27f730 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f392525e160c32086e7f465891b91d6d5e5db380ba0c3db397352fd51791da +size 3647518944 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q2_K.gguf b/Telugu-Llama2-7B-v0-Instruct.Q2_K.gguf new file mode 100644 index 0000000..47d86b4 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a10c92cd47d233f881aba44e626c6a8843419391a9ca1359be92fb3a3b146a54 +size 2532866272 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q3_K_L.gguf b/Telugu-Llama2-7B-v0-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..5ac3ef6 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52d557076235326c503bb2bb5f615b09c246eebf5c366bff0b53c0dd334c0bc7 +size 3597113568 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q3_K_M.gguf b/Telugu-Llama2-7B-v0-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..88e3b81 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995557b4b05d46c87ee7f25cc9f773e3aedd200276a98ede7f0491276e16460c +size 3298007264 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q3_K_S.gguf b/Telugu-Llama2-7B-v0-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..f17afe5 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7028c11d994f401c5d14295fef9b4a2f7dff44c2d6deaf309d3aa9c735887c2 +size 2948307168 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q4_K_M.gguf b/Telugu-Llama2-7B-v0-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c846267 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30c75ae2e1d69d6d74260a34adbd9d643ba113ea9c18cdd812b6d37ed86b18e7 +size 4081006816 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q4_K_S.gguf b/Telugu-Llama2-7B-v0-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..265d35a --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f718a0b7e4a49f242243e2fe03729d0d42213352e811d9b02bb26fdeef41ec +size 3856742624 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q5_K_M.gguf b/Telugu-Llama2-7B-v0-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..3d46cda --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc56272850e7b83bd7a3d5deea626c55548f4b91b3c326a9a8d9c7f783c4408b +size 4783159520 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q5_K_S.gguf b/Telugu-Llama2-7B-v0-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..3c11700 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd31373413e1156c6c5c95fd8671aa3abc626a18be6d7b4df0e5b30155629aeb +size 4651694304 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q6_K.gguf b/Telugu-Llama2-7B-v0-Instruct.Q6_K.gguf new file mode 100644 index 0000000..bfaada7 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22a2873847fb701e9a6ca171f0f8f0d3926dbf27bdf0a97c93e2bc07f22d9a3 +size 5529196768 diff --git a/Telugu-Llama2-7B-v0-Instruct.Q8_0.gguf b/Telugu-Llama2-7B-v0-Instruct.Q8_0.gguf new file mode 100644 index 0000000..ad6d9f3 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f72907f38a34dae2f11fa375c03f0b2adb038d548be80f04f29998728068a4e +size 7161092320 diff --git a/Telugu-Llama2-7B-v0-Instruct.f16.gguf b/Telugu-Llama2-7B-v0-Instruct.f16.gguf new file mode 100644 index 0000000..ba7cac5 --- /dev/null +++ b/Telugu-Llama2-7B-v0-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94855d729ff19209069215e38427c8023796329a9e195dc4c89ec9a7b47350e8 +size 13478107360