commit 5fd970bda42f5fdea40b0d33f57e3af07727746e Author: ModelHub XC Date: Sun Sep 6 01:37:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/open_llama_3b_v2_chat_dolly-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9501873 --- /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 +open_llama_3b_v2_chat_dolly.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +open_llama_3b_v2_chat_dolly.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..897e04d --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ddahlmeier/open_llama_3b_v2_chat_dolly +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ddahlmeier/open_llama_3b_v2_chat_dolly + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#open_llama_3b_v2_chat_dolly-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/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q2_K.gguf) | Q2_K | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q3_K_S.gguf) | Q3_K_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.IQ4_XS.gguf) | IQ4_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q4_K_M.gguf) | Q4_K_M | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/open_llama_3b_v2_chat_dolly-GGUF/resolve/main/open_llama_3b_v2_chat_dolly.f16.gguf) | f16 | 7.0 | 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/open_llama_3b_v2_chat_dolly.IQ4_XS.gguf b/open_llama_3b_v2_chat_dolly.IQ4_XS.gguf new file mode 100644 index 0000000..19595d4 --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abd574a71aaed5966bb57c68e39e3c5617f7981d52d2a8599a2658f1df242ee +size 1995476928 diff --git a/open_llama_3b_v2_chat_dolly.Q2_K.gguf b/open_llama_3b_v2_chat_dolly.Q2_K.gguf new file mode 100644 index 0000000..bf63842 --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5af856a71573c119dd347c6c9c410ce48bb60a941617f81ba61ba604980f8d +size 1979924928 diff --git a/open_llama_3b_v2_chat_dolly.Q3_K_L.gguf b/open_llama_3b_v2_chat_dolly.Q3_K_L.gguf new file mode 100644 index 0000000..62eb3ea --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32aff2774f770f63d497040b59a7abc9dd404d49f0a71208cc6197318bd8196 +size 2214548928 diff --git a/open_llama_3b_v2_chat_dolly.Q3_K_M.gguf b/open_llama_3b_v2_chat_dolly.Q3_K_M.gguf new file mode 100644 index 0000000..4bff723 --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459a16013231aa0a7b57dcca40882d9f8e41063e5a1fceb7227383fddc2ede54 +size 2139348928 diff --git a/open_llama_3b_v2_chat_dolly.Q3_K_S.gguf b/open_llama_3b_v2_chat_dolly.Q3_K_S.gguf new file mode 100644 index 0000000..dbeb60e --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbd6b50fc886448bd9f6eabbcfea06f5c686ed41283d6380572b9fcffceb07ae +size 1979924928 diff --git a/open_llama_3b_v2_chat_dolly.Q4_K_M.gguf b/open_llama_3b_v2_chat_dolly.Q4_K_M.gguf new file mode 100644 index 0000000..e84c4eb --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f35fb7a4c817e9c9e7389c42ebd9a89e88474cfc44949b3e5c08ce6290a561e +size 2580116928 diff --git a/open_llama_3b_v2_chat_dolly.Q4_K_S.gguf b/open_llama_3b_v2_chat_dolly.Q4_K_S.gguf new file mode 100644 index 0000000..b7c45e9 --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90abb904b5487050476c0704124f08a587b15a78d766c89f331ff2f2712efe60 +size 2403156928 diff --git a/open_llama_3b_v2_chat_dolly.Q5_K_M.gguf b/open_llama_3b_v2_chat_dolly.Q5_K_M.gguf new file mode 100644 index 0000000..4c2b9d1 --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a9f2f41e38f192975bf455fe46dd564b899c73887d3999d36df2a380db7e410 +size 2757076928 diff --git a/open_llama_3b_v2_chat_dolly.Q5_K_S.gguf b/open_llama_3b_v2_chat_dolly.Q5_K_S.gguf new file mode 100644 index 0000000..ea66d2e --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a59e33234224e5e8225273e477a7554caa48e2fb6c6bcaafe1f8e7823c804b +size 2603156928 diff --git a/open_llama_3b_v2_chat_dolly.Q6_K.gguf b/open_llama_3b_v2_chat_dolly.Q6_K.gguf new file mode 100644 index 0000000..e63f704 --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef7bb2cd306c6334c5c1d36e609734c0267213e328d2e09c952f6423c9c8a3f2 +size 3641876928 diff --git a/open_llama_3b_v2_chat_dolly.Q8_0.gguf b/open_llama_3b_v2_chat_dolly.Q8_0.gguf new file mode 100644 index 0000000..9e44ff8 --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf1359f9576ca6da1fb47933355766528a0a523911d0af6e9d5fd19cbb03959 +size 3641876928 diff --git a/open_llama_3b_v2_chat_dolly.f16.gguf b/open_llama_3b_v2_chat_dolly.f16.gguf new file mode 100644 index 0000000..d4f8bf7 --- /dev/null +++ b/open_llama_3b_v2_chat_dolly.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ccc885a59f655a133f8192b4e52dbeb1458f09faf6836cbb45a20a6dcaf60f +size 6854036928