commit 6145ee985b2c4cd4ea8251bdb4763a8e503556a6 Author: ModelHub XC Date: Sun Aug 30 12:15:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/hermes-llama3-roleplay-2000-v4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e601245 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +hermes-llama3-roleplay-2000-v4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.f16.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +hermes-llama3-roleplay-2000-v4.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..388c115 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Deev124/hermes-llama3-roleplay-2000-v4 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Deev124/hermes-llama3-roleplay-2000-v4 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-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/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v4-GGUF/resolve/main/hermes-llama3-roleplay-2000-v4.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/hermes-llama3-roleplay-2000-v4.IQ4_XS.gguf b/hermes-llama3-roleplay-2000-v4.IQ4_XS.gguf new file mode 100644 index 0000000..020a516 --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:209b01cc6b9b5d18585f9553d174f481cd775a3846e3a9820b78cb08bf8ebdd0 +size 4484374528 diff --git a/hermes-llama3-roleplay-2000-v4.Q2_K.gguf b/hermes-llama3-roleplay-2000-v4.Q2_K.gguf new file mode 100644 index 0000000..3930f96 --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25087c5d6db96fa3a784f1fe76930c422a5ddc4822e8d7b2bdc5c930956e91ea +size 3179141504 diff --git a/hermes-llama3-roleplay-2000-v4.Q3_K_L.gguf b/hermes-llama3-roleplay-2000-v4.Q3_K_L.gguf new file mode 100644 index 0000000..2d74979 --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28d0f4a0b126433a5d3906a62e36e4b1cbc38dc4d1d8ce40dcf198e5d7c01bc0 +size 4321967296 diff --git a/hermes-llama3-roleplay-2000-v4.Q3_K_M.gguf b/hermes-llama3-roleplay-2000-v4.Q3_K_M.gguf new file mode 100644 index 0000000..012adef --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266c0cc61d4154c7d3dd550b8c4f84d9d07a6f56b0856331241e5ff173e71770 +size 4018928832 diff --git a/hermes-llama3-roleplay-2000-v4.Q3_K_S.gguf b/hermes-llama3-roleplay-2000-v4.Q3_K_S.gguf new file mode 100644 index 0000000..42fa89a --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0efebb95f872c171654718b3024693769e9b733fcba0e54fe02b13e43e88dd70 +size 3664510144 diff --git a/hermes-llama3-roleplay-2000-v4.Q4_0_4_4.gguf b/hermes-llama3-roleplay-2000-v4.Q4_0_4_4.gguf new file mode 100644 index 0000000..764a08c --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4613d9e8b1b45834083ae47808a1394889d281cc16240195e3176111ba87f2 +size 4661223680 diff --git a/hermes-llama3-roleplay-2000-v4.Q4_K_M.gguf b/hermes-llama3-roleplay-2000-v4.Q4_K_M.gguf new file mode 100644 index 0000000..6d9f247 --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1f982626442dffa8d4baa92bd267d0f661813306ada669d78544cee047dcd41 +size 4920746240 diff --git a/hermes-llama3-roleplay-2000-v4.Q4_K_S.gguf b/hermes-llama3-roleplay-2000-v4.Q4_K_S.gguf new file mode 100644 index 0000000..00ae2ce --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2322ef0966190ca4cf6b236952854b5a969ef153a846001de1f354d7469a3dfa +size 4692680960 diff --git a/hermes-llama3-roleplay-2000-v4.Q5_K_M.gguf b/hermes-llama3-roleplay-2000-v4.Q5_K_M.gguf new file mode 100644 index 0000000..915f806 --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd2a43a08024db9c248d92cbaffd93a795b3d59cb3af0cef7383bc099c449c6 +size 5733000448 diff --git a/hermes-llama3-roleplay-2000-v4.Q5_K_S.gguf b/hermes-llama3-roleplay-2000-v4.Q5_K_S.gguf new file mode 100644 index 0000000..75571fa --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a57be58b8665a30e1f3b5af50388981b96bb47b0e37fe17f6661492108d08e41 +size 5599307008 diff --git a/hermes-llama3-roleplay-2000-v4.Q6_K.gguf b/hermes-llama3-roleplay-2000-v4.Q6_K.gguf new file mode 100644 index 0000000..7bed064 --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378b98b56b09ea68ef6fa4b2515f70bc6400b9efbbe235f1d8b6639104232e29 +size 6596020544 diff --git a/hermes-llama3-roleplay-2000-v4.Q8_0.gguf b/hermes-llama3-roleplay-2000-v4.Q8_0.gguf new file mode 100644 index 0000000..cc5c5a7 --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c763b7cc6bfea5f20f22ba1b0e7784437c943027362ae500998783b1294387 +size 8540788928 diff --git a/hermes-llama3-roleplay-2000-v4.f16.gguf b/hermes-llama3-roleplay-2000-v4.f16.gguf new file mode 100644 index 0000000..4d4cd96 --- /dev/null +++ b/hermes-llama3-roleplay-2000-v4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbdfe958cf77866ed49b4bba843276d98f783a760e9da93e88f58ecb637913be +size 16068924608