Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Yi-34Bx2-MoE-60B-DPO - GGUF - Model creator: https://huggingface.co/cloudyu/ - Original model: https://huggingface.co/cloudyu/Yi-34Bx2-MoE-60B-DPO/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Yi-34Bx2-MoE-60B-DPO.Q2_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q2_K.gguf) | Q2_K | 20.85GB | | [Yi-34Bx2-MoE-60B-DPO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ3_XS.gguf) | IQ3_XS | 23.26GB | | [Yi-34Bx2-MoE-60B-DPO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ3_S.gguf) | IQ3_S | 2.54GB | | [Yi-34Bx2-MoE-60B-DPO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q3_K_S.gguf) | Q3_K_S | 24.51GB | | [Yi-34Bx2-MoE-60B-DPO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ3_M.gguf) | IQ3_M | 25.2GB | | [Yi-34Bx2-MoE-60B-DPO.Q3_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q3_K.gguf) | Q3_K | 27.23GB | | [Yi-34Bx2-MoE-60B-DPO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q3_K_M.gguf) | Q3_K_M | 27.23GB | | [Yi-34Bx2-MoE-60B-DPO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q3_K_L.gguf) | Q3_K_L | 29.58GB | | [Yi-34Bx2-MoE-60B-DPO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ4_XS.gguf) | IQ4_XS | 30.58GB | | [Yi-34Bx2-MoE-60B-DPO.Q4_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_0.gguf) | Q4_0 | 31.97GB | | [Yi-34Bx2-MoE-60B-DPO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ4_NL.gguf) | IQ4_NL | 24.73GB | | [Yi-34Bx2-MoE-60B-DPO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_K_S.gguf) | Q4_K_S | 12.69GB | | [Yi-34Bx2-MoE-60B-DPO.Q4_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_K.gguf) | Q4_K | 34.14GB | | [Yi-34Bx2-MoE-60B-DPO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_K_M.gguf) | Q4_K_M | 34.14GB | | [Yi-34Bx2-MoE-60B-DPO.Q4_1.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_1.gguf) | Q4_1 | 35.49GB | | [Yi-34Bx2-MoE-60B-DPO.Q5_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) | Q5_0 | 39.0GB | | [Yi-34Bx2-MoE-60B-DPO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) | Q5_K_S | 39.0GB | | [Yi-34Bx2-MoE-60B-DPO.Q5_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) | Q5_K | 40.12GB | | [Yi-34Bx2-MoE-60B-DPO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) | Q5_K_M | 40.12GB | | [Yi-34Bx2-MoE-60B-DPO.Q5_1.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) | Q5_1 | 42.51GB | | [Yi-34Bx2-MoE-60B-DPO.Q6_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) | Q6_K | 46.47GB | | [Yi-34Bx2-MoE-60B-DPO.Q8_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) | Q8_0 | 60.18GB | Original model description: --- license: apache-2.0 tags: - yi - moe - DPO model-index: - name: Yi-34Bx2-MoE-60B-DPO results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 53.19 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 31.26 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 6.19 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 9.62 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 14.32 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 40.85 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard --- * [This is DPO improved version of cloudyu/Yi-34Bx2-MoE-60B](https://huggingface.co/cloudyu/Yi-34Bx2-MoE-60B) * [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer) * metrics not test! # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cloudyu__Yi-34Bx2-MoE-60B-DPO) | Metric |Value| |-------------------|----:| |Avg. |25.91| |IFEval (0-Shot) |53.19| |BBH (3-Shot) |31.26| |MATH Lvl 5 (4-Shot)| 6.19| |GPQA (0-shot) | 9.62| |MuSR (0-shot) |14.32| |MMLU-PRO (5-shot) |40.85|