Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Replete-LLM-V2.5-Qwen-14b - GGUF - Model creator: https://huggingface.co/Replete-AI/ - Original model: https://huggingface.co/Replete-AI/Replete-LLM-V2.5-Qwen-14b/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Replete-LLM-V2.5-Qwen-14b.Q2_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q2_K.gguf) | Q2_K | 5.37GB | | [Replete-LLM-V2.5-Qwen-14b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ3_XS.gguf) | IQ3_XS | 5.94GB | | [Replete-LLM-V2.5-Qwen-14b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ3_S.gguf) | IQ3_S | 6.23GB | | [Replete-LLM-V2.5-Qwen-14b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q3_K_S.gguf) | Q3_K_S | 6.2GB | | [Replete-LLM-V2.5-Qwen-14b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ3_M.gguf) | IQ3_M | 6.44GB | | [Replete-LLM-V2.5-Qwen-14b.Q3_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q3_K.gguf) | Q3_K | 6.84GB | | [Replete-LLM-V2.5-Qwen-14b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q3_K_M.gguf) | Q3_K_M | 6.84GB | | [Replete-LLM-V2.5-Qwen-14b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q3_K_L.gguf) | Q3_K_L | 7.38GB | | [Replete-LLM-V2.5-Qwen-14b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ4_XS.gguf) | IQ4_XS | 7.62GB | | [Replete-LLM-V2.5-Qwen-14b.Q4_0.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_0.gguf) | Q4_0 | 7.93GB | | [Replete-LLM-V2.5-Qwen-14b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ4_NL.gguf) | IQ4_NL | 8.01GB | | [Replete-LLM-V2.5-Qwen-14b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_K_S.gguf) | Q4_K_S | 7.98GB | | [Replete-LLM-V2.5-Qwen-14b.Q4_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_K.gguf) | Q4_K | 8.37GB | | [Replete-LLM-V2.5-Qwen-14b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_K_M.gguf) | Q4_K_M | 8.37GB | | [Replete-LLM-V2.5-Qwen-14b.Q4_1.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_1.gguf) | Q4_1 | 8.75GB | | [Replete-LLM-V2.5-Qwen-14b.Q5_0.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_0.gguf) | Q5_0 | 9.56GB | | [Replete-LLM-V2.5-Qwen-14b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_K_S.gguf) | Q5_K_S | 9.56GB | | [Replete-LLM-V2.5-Qwen-14b.Q5_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_K.gguf) | Q5_K | 9.79GB | | [Replete-LLM-V2.5-Qwen-14b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_K_M.gguf) | Q5_K_M | 9.79GB | | [Replete-LLM-V2.5-Qwen-14b.Q5_1.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_1.gguf) | Q5_1 | 10.38GB | | [Replete-LLM-V2.5-Qwen-14b.Q6_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q6_K.gguf) | Q6_K | 11.29GB | | [Replete-LLM-V2.5-Qwen-14b.Q8_0.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q8_0.gguf) | Q8_0 | 14.62GB | Original model description: --- license: apache-2.0 library_name: transformers base_model: - Qwen/Qwen2.5-14B-Instruct model-index: - name: Replete-LLM-V2.5-Qwen-14b 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: 58.4 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b 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: 49.39 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b 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: 15.63 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b 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: 16.22 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b 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: 18.83 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b 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: 48.62 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b name: Open LLM Leaderboard --- # Replete-LLM-V2.5-Qwen-14b ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/ihnWXDEgV-ZKN_B036U1J.png) Replete-LLM-V2.5-Qwen-14b is a continues finetuned version of Qwen2.5-14B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the *Ties* merge method This version of the model shows higher performance than the original instruct and base models. Quants: GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-14b-GGUF Benchmarks: # [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_Replete-AI__Replete-LLM-V2.5-Qwen-14b) | Metric |Value| |-------------------|----:| |Avg. |34.52| |IFEval (0-Shot) |58.40| |BBH (3-Shot) |49.39| |MATH Lvl 5 (4-Shot)|15.63| |GPQA (0-shot) |16.22| |MuSR (0-shot) |18.83| |MMLU-PRO (5-shot) |48.62|