commit 1aee8efebb350fa6546546f3e751df9f55434e10 Author: ModelHub XC Date: Mon Jun 15 01:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..256d067 --- /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 +Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-ultrachat-peers-pool.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.IQ4_XS.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.IQ4_XS.gguf new file mode 100644 index 0000000..a9d52c1 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022e2667cde654370961b29378cd59deea03a4a43c77f98a9ec3b5f7548098c0 +size 4484364032 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q2_K.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q2_K.gguf new file mode 100644 index 0000000..2bd2b24 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796f3b8c5b74bb4d80eabedabb5c8b5a9192cd59abcc4adcbcede43ccc0b3f05 +size 3179132672 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_L.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_L.gguf new file mode 100644 index 0000000..e0581da --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7124e659b5312dc8d4c4edcbc1e076a59d53009e34a3089e96df187954fdf39c +size 4321957632 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_M.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_M.gguf new file mode 100644 index 0000000..8abc977 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d24d76fc310629eea1b9f3ed1796a81b479553919796635eb205f4e02a3ed3c8 +size 4018919168 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_S.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_S.gguf new file mode 100644 index 0000000..6308064 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6389837e7e5516c9eeec049a2455cde25545bd2bc74bb0018947eba1b4434d9 +size 3664500480 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_M.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_M.gguf new file mode 100644 index 0000000..6f59200 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdbcee75bb26dc96a4dde38c4d310fc31e4d3829675d48f0494d8cf1c57d57d1 +size 4920735488 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_S.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_S.gguf new file mode 100644 index 0000000..0baf135 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:017da4108ffffcf17a35277877bc9b6cdb83c447f3e54313a7ccb4c9751822c9 +size 4692670208 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_M.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_M.gguf new file mode 100644 index 0000000..5c74948 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27256a92a989c7620a1927d2b5b92ee90d5d30c5d4ea9e8ff2ecfc9b00043569 +size 5732988672 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_S.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_S.gguf new file mode 100644 index 0000000..55335f7 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05a2dbdc6de73977565d4f5b184c3da9b84de885d1a2949d26dbfe700f3b62e +size 5599295232 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q6_K.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q6_K.gguf new file mode 100644 index 0000000..85114cc --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:892f4fb2c0a154d5bbe467277aa0a1d16f7e8efbe25e4a4edc143fd63c7f9f7c +size 6596007680 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.Q8_0.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q8_0.gguf new file mode 100644 index 0000000..008949f --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d7a0ae963dd68cd558db80282878785b7ca285c04b2b0b68c7733aabda7259 +size 8540772096 diff --git a/Llama-3.1-8B-sft-ultrachat-peers-pool.f16.gguf b/Llama-3.1-8B-sft-ultrachat-peers-pool.f16.gguf new file mode 100644 index 0000000..eeba253 --- /dev/null +++ b/Llama-3.1-8B-sft-ultrachat-peers-pool.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8c65051987edf1f790fea850f800fea0953cc4af1017985c82f511b997725f +size 16068892416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8c5788f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-ultrachat-peers-pool +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-ultrachat-peers-pool +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-sft-ultrachat-peers-pool + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-sft-ultrachat-peers-pool-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/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-ultrachat-peers-pool-GGUF/resolve/main/Llama-3.1-8B-sft-ultrachat-peers-pool.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. + +