commit 1ce0755c3f907afa260db9ee613ccf928b982e96 Author: ModelHub XC Date: Mon Nov 2 14:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Emollama-chat-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..76b4666 --- /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 +Emollama-chat-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +Emollama-chat-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Emollama-chat-7b.IQ4_XS.gguf b/Emollama-chat-7b.IQ4_XS.gguf new file mode 100644 index 0000000..e30e216 --- /dev/null +++ b/Emollama-chat-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7dc5aeee1a5446a2592725e82b4879f3407cad9af5411b57d901dd5804fb74f +size 3647517152 diff --git a/Emollama-chat-7b.Q2_K.gguf b/Emollama-chat-7b.Q2_K.gguf new file mode 100644 index 0000000..bad8f32 --- /dev/null +++ b/Emollama-chat-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6991cfd91a157bbd52f989fa7709b30f5b7eb7ebcaeea2a5817d8b99ea332f3d +size 2532864480 diff --git a/Emollama-chat-7b.Q3_K_L.gguf b/Emollama-chat-7b.Q3_K_L.gguf new file mode 100644 index 0000000..1911748 --- /dev/null +++ b/Emollama-chat-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104858eac9c19b4798ea7960cf9423b2382bf44d64041eb461fc53b10083fa77 +size 3597111776 diff --git a/Emollama-chat-7b.Q3_K_M.gguf b/Emollama-chat-7b.Q3_K_M.gguf new file mode 100644 index 0000000..3b6ebf7 --- /dev/null +++ b/Emollama-chat-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22068cd9a9aeeed6232de9710b49e7c7855e3854fe121840a26a134b5dfcdd30 +size 3298005472 diff --git a/Emollama-chat-7b.Q3_K_S.gguf b/Emollama-chat-7b.Q3_K_S.gguf new file mode 100644 index 0000000..5222347 --- /dev/null +++ b/Emollama-chat-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a34b7e1b4c7d5d5ad7659ac78f01fce42b81e87044ada9ae4791ecc9a3ab34fd +size 2948305376 diff --git a/Emollama-chat-7b.Q4_K_M.gguf b/Emollama-chat-7b.Q4_K_M.gguf new file mode 100644 index 0000000..acb761d --- /dev/null +++ b/Emollama-chat-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85eb78e8c1f579b6414aab9175a4dd88f7b7740ef6d1efe19b2b550f015448e +size 4081005024 diff --git a/Emollama-chat-7b.Q4_K_S.gguf b/Emollama-chat-7b.Q4_K_S.gguf new file mode 100644 index 0000000..e48b04c --- /dev/null +++ b/Emollama-chat-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d51d47e94cab48fcef0e6d1640eaea04f4302322b669cf9fe2ebd247ec495368 +size 3856740832 diff --git a/Emollama-chat-7b.Q5_K_M.gguf b/Emollama-chat-7b.Q5_K_M.gguf new file mode 100644 index 0000000..473a879 --- /dev/null +++ b/Emollama-chat-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f292c64eaf40f6fff135fde4e4cdae7fced612f86c46fea3f35333fa93c21ad2 +size 4783157728 diff --git a/Emollama-chat-7b.Q5_K_S.gguf b/Emollama-chat-7b.Q5_K_S.gguf new file mode 100644 index 0000000..991643a --- /dev/null +++ b/Emollama-chat-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b14b36265cd3818e4141e0fecd5ef417766704b850f439c9bac34763af08124 +size 4651692512 diff --git a/Emollama-chat-7b.Q6_K.gguf b/Emollama-chat-7b.Q6_K.gguf new file mode 100644 index 0000000..0827c92 --- /dev/null +++ b/Emollama-chat-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5280f105e1e665728ac7396abcfe6169b61a585a9d57cc7c8a62934a81effe41 +size 5529194976 diff --git a/Emollama-chat-7b.Q8_0.gguf b/Emollama-chat-7b.Q8_0.gguf new file mode 100644 index 0000000..808ad04 --- /dev/null +++ b/Emollama-chat-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76a4ed9b188c16bb99857ae30e8d527cddfc64a9878fd6e1ddda258bbe89da60 +size 7161090528 diff --git a/Emollama-chat-7b.f16.gguf b/Emollama-chat-7b.f16.gguf new file mode 100644 index 0000000..56918d0 --- /dev/null +++ b/Emollama-chat-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f40fad9a749cf6f47d1eadf510d19aa88c68e2c0c0ef2ee55ecc2905212bf1e9 +size 13478105568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d86ded3 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: lzw1008/Emollama-chat-7b +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lzw1008/Emollama-chat-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Emollama-chat-7b-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/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Emollama-chat-7b-GGUF/resolve/main/Emollama-chat-7b.f16.gguf) | f16 | 13.6 | 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. + +