commit 7dc0cf4727245325ea08963f34e8c21a5bc35bdd Author: ModelHub XC Date: Mon Jul 6 11:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ConvAI-9b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..89a07e2 --- /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 +ConvAI-9b.f16.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ConvAI-9b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ConvAI-9b.IQ4_XS.gguf b/ConvAI-9b.IQ4_XS.gguf new file mode 100644 index 0000000..d809569 --- /dev/null +++ b/ConvAI-9b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc8a0be84fee8485d182adaf6d2e2129da9c8cf8491ab5c5dddea3019d02154 +size 4886015840 diff --git a/ConvAI-9b.Q2_K.gguf b/ConvAI-9b.Q2_K.gguf new file mode 100644 index 0000000..93394a5 --- /dev/null +++ b/ConvAI-9b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119e09a28d399b3150f11070f623378f7b7212d5bc0ed4adf59d876b0f3c2fe7 +size 3361238880 diff --git a/ConvAI-9b.Q3_K_L.gguf b/ConvAI-9b.Q3_K_L.gguf new file mode 100644 index 0000000..89ecc04 --- /dev/null +++ b/ConvAI-9b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11025d3f4e4afee45c7a69cf12f3a2da6a6dddcb8e91586e02879e80079ca0db +size 4736388960 diff --git a/ConvAI-9b.Q3_K_M.gguf b/ConvAI-9b.Q3_K_M.gguf new file mode 100644 index 0000000..9e48e43 --- /dev/null +++ b/ConvAI-9b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37450d561740d0e6d29dad7374cd9d72fc149c9708949aeab95b447930a00a35 +size 4353658720 diff --git a/ConvAI-9b.Q3_K_S.gguf b/ConvAI-9b.Q3_K_S.gguf new file mode 100644 index 0000000..38eaa17 --- /dev/null +++ b/ConvAI-9b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ea4c695e58afab65884ff2498f15c203feb10f62090defb121494b527ad001 +size 3914567520 diff --git a/ConvAI-9b.Q4_K_M.gguf b/ConvAI-9b.Q4_K_M.gguf new file mode 100644 index 0000000..7301699 --- /dev/null +++ b/ConvAI-9b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1d1f9d765ebcce4e3c996d2fe8e93ae8f89b74c6c1d61214fde049520598fb +size 5415055200 diff --git a/ConvAI-9b.Q4_K_S.gguf b/ConvAI-9b.Q4_K_S.gguf new file mode 100644 index 0000000..cf2640f --- /dev/null +++ b/ConvAI-9b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7513bf31a4193809aface4c4f47d199d82778bceea6e9b0f580b56d73a0af05f +size 5129449312 diff --git a/ConvAI-9b.Q5_K_M.gguf b/ConvAI-9b.Q5_K_M.gguf new file mode 100644 index 0000000..6f79ef6 --- /dev/null +++ b/ConvAI-9b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c0b1ece3f97a87bf0316a35296776a20370ff14c579e2f280f09a6b054fcf1 +size 6364671840 diff --git a/ConvAI-9b.Q5_K_S.gguf b/ConvAI-9b.Q5_K_S.gguf new file mode 100644 index 0000000..7f78222 --- /dev/null +++ b/ConvAI-9b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b6d7e4944e42a56ab082c836560347feea20bee4b9fc933105217531ed82c6 +size 6197555040 diff --git a/ConvAI-9b.Q6_K.gguf b/ConvAI-9b.Q6_K.gguf new file mode 100644 index 0000000..4deb55c --- /dev/null +++ b/ConvAI-9b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5128cf176a2cebdf73652c8f53f577b1128eae4f21b022e0f4a032dd5d3a34a0 +size 7373639520 diff --git a/ConvAI-9b.Q8_0.gguf b/ConvAI-9b.Q8_0.gguf new file mode 100644 index 0000000..2db7926 --- /dev/null +++ b/ConvAI-9b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a678dfdb8b28e1cae2df7429611d2457796655d3d5fda1e0571a5ac1a7183f2 +size 9550008160 diff --git a/ConvAI-9b.f16.gguf b/ConvAI-9b.f16.gguf new file mode 100644 index 0000000..cb64b91 --- /dev/null +++ b/ConvAI-9b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c61636424d542525c6302616eced55844475680fd4401d65e661179ef6eafdb +size 17974660960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8a956f2 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: CreitinGameplays/ConvAI-9b +datasets: +- CreitinGameplays/merged-data-v2 +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/CreitinGameplays/ConvAI-9b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ConvAI-9b-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/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.IQ4_XS.gguf) | IQ4_XS | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q5_K_S.gguf) | Q5_K_S | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q5_K_M.gguf) | Q5_K_M | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q6_K.gguf) | Q6_K | 7.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ConvAI-9b-GGUF/resolve/main/ConvAI-9b.f16.gguf) | f16 | 18.1 | 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. + +