commit bd1731ab6bff73bb6e8486637a4a50fffd179d09 Author: ModelHub XC Date: Thu Jun 4 20:18:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fb180af --- /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 +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b371451 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: juweriya/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/juweriya/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-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/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.f16.gguf) | f16 | 2.3 | 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/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.IQ4_XS.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.IQ4_XS.gguf new file mode 100644 index 0000000..5c9c4e5 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458554505fbe794c5b2e4f81f3d322bcc38b7d1ae2d49f6c1223efa0f317a5eb +size 609808288 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q2_K.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q2_K.gguf new file mode 100644 index 0000000..a2a4b42 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a89a1a0066ac799b14d9dbe0e67c47c6bea3a6b8dec9e064202a4ee216a2348b +size 432132000 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_L.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_L.gguf new file mode 100644 index 0000000..8c0b3ab --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c40fb5cab2102aae28ffbaff484b54e3c7f77e6e66991c8cc9616ec118a4ea0c +size 591527840 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_M.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_M.gguf new file mode 100644 index 0000000..b6d23e5 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f783039ba6b24269a40cf403200f9616c01e388bf2470d3040421e9ced970ec1 +size 548405152 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_S.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_S.gguf new file mode 100644 index 0000000..9caa4d6 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ca0e8c65f073f095d5f297011da3965e267654dc7794495f855488419c7db8 +size 499343264 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_M.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_M.gguf new file mode 100644 index 0000000..b8e8ebd --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924d0a3e67df3d33ed37880c1e6e9428757a3991b4e84d6cdcfde856e84dc61d +size 667815840 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_S.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_S.gguf new file mode 100644 index 0000000..245aea9 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d458b79018fb06da53449b80e1ef83323d66c9d353a38e99ae105432872c0aaf +size 639872928 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_M.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_M.gguf new file mode 100644 index 0000000..444f42c --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e59ad0e77a617b4e36d86b559f0f23a30581cbc7e66424d317ae9685a07453 +size 782045088 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_S.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_S.gguf new file mode 100644 index 0000000..e18df09 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:943b1bf9f44cf84430bf18cec9a1ab56cc0e879426ec1de412dfab239cfe15d3 +size 766029728 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q6_K.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q6_K.gguf new file mode 100644 index 0000000..b930c5e --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b81bd8827e5499040c7302e9b2e7c58a980ae997ef11ccd395ab37248408bc +size 903413664 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q8_0.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q8_0.gguf new file mode 100644 index 0000000..ebdc9f0 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebabaa358b8da35b6aae3c8d8019cfc4631da236f64c7f07fca9a16689f21a61 +size 1169809312 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.f16.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.f16.gguf new file mode 100644 index 0000000..5998d8d --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-DPO-ultrafeedback.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b51057c1466f6c6394f8eb5a013ebced44e3c920a961b059c706259231110af +size 2201018272