Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) vicuna-160m - GGUF - Model creator: https://huggingface.co/double7/ - Original model: https://huggingface.co/double7/vicuna-160m/ | Name | Quant method | Size | | ---- | ---- | ---- | | [vicuna-160m.Q2_K.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q2_K.gguf) | Q2_K | 0.07GB | | [vicuna-160m.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.IQ3_XS.gguf) | IQ3_XS | 0.07GB | | [vicuna-160m.IQ3_S.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.IQ3_S.gguf) | IQ3_S | 0.07GB | | [vicuna-160m.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q3_K_S.gguf) | Q3_K_S | 0.07GB | | [vicuna-160m.IQ3_M.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.IQ3_M.gguf) | IQ3_M | 0.08GB | | [vicuna-160m.Q3_K.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q3_K.gguf) | Q3_K | 0.08GB | | [vicuna-160m.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q3_K_M.gguf) | Q3_K_M | 0.08GB | | [vicuna-160m.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q3_K_L.gguf) | Q3_K_L | 0.08GB | | [vicuna-160m.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.IQ4_XS.gguf) | IQ4_XS | 0.09GB | | [vicuna-160m.Q4_0.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q4_0.gguf) | Q4_0 | 0.09GB | | [vicuna-160m.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.IQ4_NL.gguf) | IQ4_NL | 0.09GB | | [vicuna-160m.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q4_K_S.gguf) | Q4_K_S | 0.09GB | | [vicuna-160m.Q4_K.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q4_K.gguf) | Q4_K | 0.1GB | | [vicuna-160m.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q4_K_M.gguf) | Q4_K_M | 0.1GB | | [vicuna-160m.Q4_1.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q4_1.gguf) | Q4_1 | 0.1GB | | [vicuna-160m.Q5_0.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q5_0.gguf) | Q5_0 | 0.11GB | | [vicuna-160m.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q5_K_S.gguf) | Q5_K_S | 0.11GB | | [vicuna-160m.Q5_K.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q5_K.gguf) | Q5_K | 0.11GB | | [vicuna-160m.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q5_K_M.gguf) | Q5_K_M | 0.11GB | | [vicuna-160m.Q5_1.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q5_1.gguf) | Q5_1 | 0.12GB | | [vicuna-160m.Q6_K.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q6_K.gguf) | Q6_K | 0.12GB | | [vicuna-160m.Q8_0.gguf](https://huggingface.co/RichardErkhov/double7_-_vicuna-160m-gguf/blob/main/vicuna-160m.Q8_0.gguf) | Q8_0 | 0.16GB | Original model description: --- license: apache-2.0 datasets: - anon8231489123/ShareGPT_Vicuna_unfiltered language: - en pipeline_tag: text-generation --- ## Model description This is a Vicuna-like model with only 160M parameters, which is fine-tuned from [LLaMA-160m](https://huggingface.co/JackFram/llama-160m) on [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) data. The training setup follows the [Vicuna suite](https://github.com/lm-sys/FastChat). The model is mainly developed as a base Small Speculative Model in [MCSD paper](https://arxiv.org/pdf/2401.06706.pdf). As a comparison, it can be better aligned to the Vicuna models than LLaMA-160m with little loss of alignment to the LLaMA models. | Draft Model | Target Model | Alignment | | -------------- | ------------- | --------- | | LLaMA-68/160M | LLaMA-13/33B | 😃 | | LLaMA-68/160M | Vicuna-13/33B | 😟 | | Vicuna-68/160M | LLaMA-13/33B | 😃 | | Vicuna-68/160M | Vicuna-13/33B | 😃 |