commit afdc50cc67cfee406c6c299108e78a867e2001ad Author: ModelHub XC Date: Tue Jun 9 09:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6ccdbbf --- /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 +RoLlama2-7b-Instruct-2025-04-23.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.f16.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama2-7b-Instruct-2025-04-23.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8d8924 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: OpenLLM-Ro/RoLlama2-7b-Instruct-2025-04-23 +datasets: +- OpenLLM-Ro/ro_sft_alpaca +- OpenLLM-Ro/ro_sft_alpaca_gpt4 +- OpenLLM-Ro/ro_sft_dolly +- OpenLLM-Ro/ro_sft_selfinstruct_gpt4 +- OpenLLM-Ro/ro_sft_norobots +- OpenLLM-Ro/ro_sft_orca +- OpenLLM-Ro/ro_sft_camel +- OpenLLM-Ro/ro_sft_oasst +- OpenLLM-Ro/ro_sft_ultrachat +- OpenLLM-Ro/ro_sft_magpie_mt +- OpenLLM-Ro/ro_sft_magpie_reasoning +language: +- ro +library_name: transformers +license: cc-by-nc-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2025-04-23 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RoLlama2-7b-Instruct-2025-04-23-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-i1-GGUF +## 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/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama2-7b-Instruct-2025-04-23-GGUF/resolve/main/RoLlama2-7b-Instruct-2025-04-23.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. + + diff --git a/RoLlama2-7b-Instruct-2025-04-23.IQ4_XS.gguf b/RoLlama2-7b-Instruct-2025-04-23.IQ4_XS.gguf new file mode 100644 index 0000000..f9560b2 --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63f2fdf4bb2359d0784479eb23c68f3858d91b96ef9296a9868141a58f0f5e9 +size 3647521056 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q2_K.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q2_K.gguf new file mode 100644 index 0000000..50f056e --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c60372c47ffc7322911907782d53d6525d0a16fa764ded55a2afeeba5f9e29 +size 2532868384 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q3_K_L.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q3_K_L.gguf new file mode 100644 index 0000000..cb1f1d1 --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db19f61354a596e7e3505fe2733737beb1e9d155d0cbccb34bd7ed31b23a74b4 +size 3597115680 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q3_K_M.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q3_K_M.gguf new file mode 100644 index 0000000..cf89f25 --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e8d1702d850ccbdf516bb7f23679c98bd40f098f2a0fb60818f7630e077d407 +size 3298009376 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q3_K_S.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q3_K_S.gguf new file mode 100644 index 0000000..fada54b --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fbebfc82e5598e4d269b10c0f686511b1fcaeff974800675744bd82ad2aa998 +size 2948309280 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q4_K_M.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q4_K_M.gguf new file mode 100644 index 0000000..93fb8ed --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d086ab9c3eafc0c2e6e50780e793d8213667ad42b2197d7ecef702904f09c44 +size 4081008928 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q4_K_S.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q4_K_S.gguf new file mode 100644 index 0000000..b65e38e --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968abb4cabe2cb65805e64617a7e04daee588e3cc376607dbcac9819252c8da4 +size 3856744736 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q5_K_M.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q5_K_M.gguf new file mode 100644 index 0000000..e52f624 --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1528fbe8758185dd73e2bef9ee369fd8e4926fd22bac6a644fb7f814250ee508 +size 4783161632 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q5_K_S.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q5_K_S.gguf new file mode 100644 index 0000000..4299137 --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1b8ac19290554fbf01b19b3f1e0f922c311e51104fd8f9e584550028497ce9 +size 4651696416 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q6_K.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q6_K.gguf new file mode 100644 index 0000000..1cdb5c6 --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cba6ae386ba89b42c96be49c77b0a11a7f3dfe672ae6a152838e18e885d4f5a2 +size 5529198880 diff --git a/RoLlama2-7b-Instruct-2025-04-23.Q8_0.gguf b/RoLlama2-7b-Instruct-2025-04-23.Q8_0.gguf new file mode 100644 index 0000000..d4cb83f --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743c7343486fb4142a209e50cbc1407383f6bdb4028041996b2f670237a56045 +size 7161094432 diff --git a/RoLlama2-7b-Instruct-2025-04-23.f16.gguf b/RoLlama2-7b-Instruct-2025-04-23.f16.gguf new file mode 100644 index 0000000..9ff5fbd --- /dev/null +++ b/RoLlama2-7b-Instruct-2025-04-23.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fac3a6abe691d0e07ec5c247e366ebb2f3f702c9400a151156674ceb54e5db1 +size 13478109472