commit f0c0787800cb32498c4286cb25ad6e95dac92713 Author: ModelHub XC Date: Tue Jun 30 08:30:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Fireball-R1-Llama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1f69ae1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Fireball-R1-Llama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Fireball-R1-Llama-3.1-8B.IQ4_XS.gguf b/Fireball-R1-Llama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..b023eb0 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a1af546c0c420b3ef93359bf02641665b3062be9370295080ea66ba86054efe +size 4484373056 diff --git a/Fireball-R1-Llama-3.1-8B.Q2_K.gguf b/Fireball-R1-Llama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..1c7969d --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf76288fa20e63d8ff838ee73477020a96128c2dcc194989c8658e09b12412b0 +size 3179141696 diff --git a/Fireball-R1-Llama-3.1-8B.Q3_K_L.gguf b/Fireball-R1-Llama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0e8b7dd --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04205e494ece650380263811732318040d068eff98c434720e07da5e89b2dba9 +size 4321966656 diff --git a/Fireball-R1-Llama-3.1-8B.Q3_K_M.gguf b/Fireball-R1-Llama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..1929572 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111734eaee1776d0fa295b2debbb65da5168e26faa791d00b09acf433b6b67ce +size 4018928192 diff --git a/Fireball-R1-Llama-3.1-8B.Q3_K_S.gguf b/Fireball-R1-Llama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..6a8b12a --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fbcc0668e8ef3eb9804c8297e575acac03c1814fb6edaebe02d653d465da26c +size 3664509504 diff --git a/Fireball-R1-Llama-3.1-8B.Q4_K_M.gguf b/Fireball-R1-Llama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..aedd2bf --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41f892f60c1bde5c7a30b912f47ad22497274ef9bfcd75bab465c50a10e6dc8c +size 4920744512 diff --git a/Fireball-R1-Llama-3.1-8B.Q4_K_S.gguf b/Fireball-R1-Llama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..e4bdab8 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1216d56f9cfdde0f8db9ce5aa44187882a78f74cbe4ad0fccb64065dfeca4f +size 4692679232 diff --git a/Fireball-R1-Llama-3.1-8B.Q5_K_M.gguf b/Fireball-R1-Llama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..4237d0c --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4f87d050152491da168d5e22094699cadfeae2077ecac69d24924355c4ca49 +size 5732997696 diff --git a/Fireball-R1-Llama-3.1-8B.Q5_K_S.gguf b/Fireball-R1-Llama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..0b6c3a8 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddcfad6446d2a06145c2933691b5bde9ce21258f2c3dd915d03fac781c2ed60c +size 5599304256 diff --git a/Fireball-R1-Llama-3.1-8B.Q6_K.gguf b/Fireball-R1-Llama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..b567bac --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6439fe58da4f4387d650ed173581117f4bf2c5939a7873a1e2b13eb31c6095 +size 6596016704 diff --git a/Fireball-R1-Llama-3.1-8B.Q8_0.gguf b/Fireball-R1-Llama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..ac4f963 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31e13afa10348f5d4d6d44d89299b0bde181bc51c5255395c93b970e9fdadf2 +size 8540781120 diff --git a/Fireball-R1-Llama-3.1-8B.f16.gguf b/Fireball-R1-Llama-3.1-8B.f16.gguf new file mode 100644 index 0000000..0be2307 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:338d76a1f0380a3e06cd699b3dc5bb6c9aae47fe20e7ee11df76ad01d1cddc20 +size 16068901440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c7a2c08 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: EpistemeAI/Fireball-R1-Llama-3.1-8B +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/EpistemeAI/Fireball-R1-Llama-3.1-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-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/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B.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. + +