commit d600c530e4ef975c68a27061c16d4a691910ff76 Author: ModelHub XC Date: Mon Jun 1 17:49:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-8b-tulutalk-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..04f9bb8 --- /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 +llama3.1-8b-tulutalk.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-tulutalk.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d00d6f5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: ketchup123/llama3.1-8b-tulutalk +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ketchup123/llama3.1-8b-tulutalk + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.1-8b-tulutalk-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/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-tulutalk-GGUF/resolve/main/llama3.1-8b-tulutalk.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. + + diff --git a/llama3.1-8b-tulutalk.IQ4_XS.gguf b/llama3.1-8b-tulutalk.IQ4_XS.gguf new file mode 100644 index 0000000..8ce1a68 --- /dev/null +++ b/llama3.1-8b-tulutalk.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d4e6a909b9b4add8552fb5463bbbeb091e2589ac07c13961a98d1f514f786e +size 4484408192 diff --git a/llama3.1-8b-tulutalk.Q2_K.gguf b/llama3.1-8b-tulutalk.Q2_K.gguf new file mode 100644 index 0000000..1eb9f61 --- /dev/null +++ b/llama3.1-8b-tulutalk.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c19f049fc11bd43761fee661c4dcb6db6c1c4996b0a948a9bce05bf82558f0 +size 3179170176 diff --git a/llama3.1-8b-tulutalk.Q3_K_L.gguf b/llama3.1-8b-tulutalk.Q3_K_L.gguf new file mode 100644 index 0000000..5287332 --- /dev/null +++ b/llama3.1-8b-tulutalk.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408d3939654b05f74a4a3abdbaf272ae93b48daefda7de4e180e537345983fd3 +size 4321998464 diff --git a/llama3.1-8b-tulutalk.Q3_K_M.gguf b/llama3.1-8b-tulutalk.Q3_K_M.gguf new file mode 100644 index 0000000..ba91442 --- /dev/null +++ b/llama3.1-8b-tulutalk.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c618fa13ea2d4e1baba4b88714389c6fc82b41298a22865d2b5ab60d41594665 +size 4018960000 diff --git a/llama3.1-8b-tulutalk.Q3_K_S.gguf b/llama3.1-8b-tulutalk.Q3_K_S.gguf new file mode 100644 index 0000000..c842111 --- /dev/null +++ b/llama3.1-8b-tulutalk.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff4fa036d6f2e707e3ed945720e81637bffba0651405a9d69a274b591f78f4fa +size 3664541312 diff --git a/llama3.1-8b-tulutalk.Q4_K_M.gguf b/llama3.1-8b-tulutalk.Q4_K_M.gguf new file mode 100644 index 0000000..1988b94 --- /dev/null +++ b/llama3.1-8b-tulutalk.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1517615b9ec5dd275dbae133f06396a1c8ffdc89fded77227f1bd04e027182 +size 4920780672 diff --git a/llama3.1-8b-tulutalk.Q4_K_S.gguf b/llama3.1-8b-tulutalk.Q4_K_S.gguf new file mode 100644 index 0000000..5b5119a --- /dev/null +++ b/llama3.1-8b-tulutalk.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9bd2064636d7543dbb9581716e352deb80d4b5a77472d811e69f029e542b078 +size 4692715392 diff --git a/llama3.1-8b-tulutalk.Q5_K_M.gguf b/llama3.1-8b-tulutalk.Q5_K_M.gguf new file mode 100644 index 0000000..3043beb --- /dev/null +++ b/llama3.1-8b-tulutalk.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f8b5f0dc2fffe4050b6a92262336f28f210ea43b930d915a5d9132acf823d2 +size 5733037952 diff --git a/llama3.1-8b-tulutalk.Q5_K_S.gguf b/llama3.1-8b-tulutalk.Q5_K_S.gguf new file mode 100644 index 0000000..cb365c3 --- /dev/null +++ b/llama3.1-8b-tulutalk.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fbdddde99eef1c114bc38329ccede17052a68879ce2c38485b2aca5e81beaef +size 5599344512 diff --git a/llama3.1-8b-tulutalk.Q6_K.gguf b/llama3.1-8b-tulutalk.Q6_K.gguf new file mode 100644 index 0000000..4f19526 --- /dev/null +++ b/llama3.1-8b-tulutalk.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e2832edba764f3aa0ac60df95855ef8cb7f038167ef8b52eb7cfa7be39d4fb +size 6596061312 diff --git a/llama3.1-8b-tulutalk.Q8_0.gguf b/llama3.1-8b-tulutalk.Q8_0.gguf new file mode 100644 index 0000000..260ae19 --- /dev/null +++ b/llama3.1-8b-tulutalk.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd3e458da31ae6565333bca46739da4a576aecde4b3269b212eff310243dbeb +size 8540841600 diff --git a/llama3.1-8b-tulutalk.f16.gguf b/llama3.1-8b-tulutalk.f16.gguf new file mode 100644 index 0000000..7ecbadd --- /dev/null +++ b/llama3.1-8b-tulutalk.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee3b886e9a10e8beb75cb17db5e6b035c4ccc057efdde7086c3d7a19c137186 +size 16069023360