Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) RedPajama-INCITE-Chat-Instruct-3B-V1 - GGUF - Model creator: https://huggingface.co/acrastt/ - Original model: https://huggingface.co/acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1/ | Name | Quant method | Size | | ---- | ---- | ---- | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q2_K.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q2_K.gguf) | Q2_K | 1.01GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.IQ3_XS.gguf) | IQ3_XS | 1.14GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.IQ3_S.gguf) | IQ3_S | 1.16GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q3_K_S.gguf) | Q3_K_S | 1.16GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.IQ3_M.gguf) | IQ3_M | 1.28GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q3_K.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q3_K.gguf) | Q3_K | 1.38GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q3_K_M.gguf) | Q3_K_M | 1.38GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q3_K_L.gguf) | Q3_K_L | 1.49GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.IQ4_XS.gguf) | IQ4_XS | 1.43GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_0.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_0.gguf) | Q4_0 | 1.49GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.IQ4_NL.gguf) | IQ4_NL | 1.5GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_K_S.gguf) | Q4_K_S | 1.5GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_K.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_K.gguf) | Q4_K | 1.66GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_K_M.gguf) | Q4_K_M | 1.66GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_1.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q4_1.gguf) | Q4_1 | 1.64GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_0.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_0.gguf) | Q5_0 | 1.8GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_K_S.gguf) | Q5_K_S | 1.8GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_K.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_K.gguf) | Q5_K | 1.93GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_K_M.gguf) | Q5_K_M | 1.93GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_1.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q5_1.gguf) | Q5_1 | 1.95GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q6_K.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q6_K.gguf) | Q6_K | 2.13GB | | [RedPajama-INCITE-Chat-Instruct-3B-V1.Q8_0.gguf](https://huggingface.co/RichardErkhov/acrastt_-_RedPajama-INCITE-Chat-Instruct-3B-V1-gguf/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1.Q8_0.gguf) | Q8_0 | 2.75GB | Original model description: --- language: - en license: apache-2.0 library_name: transformers datasets: - togethercomputer/RedPajama-Data-1T - databricks/databricks-dolly-15k - OpenAssistant/oasst1 - Muennighoff/natural-instructions - Muennighoff/P3 pipeline_tag: text-generation model-index: - name: RedPajama-INCITE-Chat-Instruct-3B-V1 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 42.58 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 67.48 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 25.99 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 33.62 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 64.8 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 0.91 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1 name: Open LLM Leaderboard --- Buy Me A Coffee This is an experimental merge of models [RedPajama-INCITE-Chat-3B-V1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1) and [RedPajama-INCITE-Instruct-3B-V1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1).
This model is adaptive to prompt templates, but this template is recommended: ``` HUMAN: {prompt} ASSISTANT: ``` Feel free to change HUMAN or ASSISTANT. It will not change much.
GGML versions [here](https://huggingface.co/adadbbb/pajama_ggml) (Note that this is only compatible with [koboldcpp](https://github.com/LostRuins/koboldcpp)). # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_acrastt__RedPajama-INCITE-Chat-Instruct-3B-V1) | Metric | Value | |-----------------------|---------------------------| | Avg. | 39.23 | | ARC (25-shot) | 42.58 | | HellaSwag (10-shot) | 67.48 | | MMLU (5-shot) | 25.99 | | TruthfulQA (0-shot) | 33.62 | | Winogrande (5-shot) | 64.8 | | GSM8K (5-shot) | 0.91 | # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_acrastt__RedPajama-INCITE-Chat-Instruct-3B-V1) | Metric |Value| |---------------------------------|----:| |Avg. |39.23| |AI2 Reasoning Challenge (25-Shot)|42.58| |HellaSwag (10-Shot) |67.48| |MMLU (5-Shot) |25.99| |TruthfulQA (0-shot) |33.62| |Winogrande (5-shot) |64.80| |GSM8k (5-shot) | 0.91|