commit 0b9c02f43012e37aa9b812aac4cf7a6b9fa54a03 Author: ModelHub XC Date: Tue Jul 21 22:57:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c118f6f --- /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 +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.f16.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e1dff15 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: winnieyangwannan/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying +language: +- en +library_name: transformers +model_name: Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying +quantized_by: mradermacher +tags: +- generated_from_trainer +- Yi-6B-Chat +- honest_lying +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/winnieyangwannan/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying + + +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/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q2_K.gguf) | Q2_K | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_S.gguf) | Q3_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_L.gguf) | Q3_K_L | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.IQ4_XS.gguf) | IQ4_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_M.gguf) | Q4_K_M | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_S.gguf) | Q5_K_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_M.gguf) | Q5_K_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q6_K.gguf) | Q6_K | 5.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q8_0.gguf) | Q8_0 | 6.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying-GGUF/resolve/main/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.f16.gguf) | f16 | 12.2 | 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. + + diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.IQ4_XS.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.IQ4_XS.gguf new file mode 100644 index 0000000..58c644d --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1998eef148623cf4291eca5cc7b77d9eaf126e3acae7390741893d949eda9745 +size 3336786944 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q2_K.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q2_K.gguf new file mode 100644 index 0000000..25c18f6 --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179a4432e456496c53601a7ad5ffb11dcb7c77bb7a7f6a3e1df15e03792dee14 +size 2337068032 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_L.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_L.gguf new file mode 100644 index 0000000..0935775 --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e60e10435fd2355df8c3643786983e994410174032f6b879ee10f6e39dbd8e2 +size 3236893696 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_M.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_M.gguf new file mode 100644 index 0000000..3483b66 --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97daa14215ebb2bc226c453eb28aa41be595a301418be055be579a427e0e4202 +size 2992837632 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_S.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_S.gguf new file mode 100644 index 0000000..d56a95a --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b124752c6c5bd043894cbe03a7aa8eca6611c27d99a8de54133b81cc6c4d750b +size 2709197824 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_M.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_M.gguf new file mode 100644 index 0000000..49ffb32 --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43da6e282823eb864741c9cb1a05b7a33064cf198037eed6fc8b700130c3fbe8 +size 3673969664 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_S.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_S.gguf new file mode 100644 index 0000000..764bf4c --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9917e56ab2e5babb2d848a1695493bc891a0bbe10daec39fca0dba4b0971c64 +size 3502920704 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_M.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_M.gguf new file mode 100644 index 0000000..e9c6072 --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1930a4c6fcb6240951bd12a32a444f44e7cda283db5fb3bdf2a5053872c331 +size 4304425984 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_S.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_S.gguf new file mode 100644 index 0000000..032d941 --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baa5556cd9e2a87e5391cd25f6c76e0b7abad31a832c22d0b2e7c4893ca2be49 +size 4204155904 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q6_K.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q6_K.gguf new file mode 100644 index 0000000..a7f2e30 --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c2839b7782752dc7a7479a19d113f37e96e40d673081254dff489361553b88 +size 4974285824 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q8_0.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q8_0.gguf new file mode 100644 index 0000000..f87c578 --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2539458e6f9ad9312fdc6a788ccc27550535e82cf17a741db69ff223f75de23 +size 6442128384 diff --git a/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.f16.gguf b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.f16.gguf new file mode 100644 index 0000000..23af54a --- /dev/null +++ b/Yi-6B-Chat-Llama-3.3-70B-Instruct-honest_lying.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89dd90af847812c95ff076fe42928379db90f4617d733aed9145673877173dd0 +size 12124099584