Downloads · 30 days
503
5% of all-time downloads
double7_-_vicuna-68m-gguf
RichardErkhov/double7_-_vicuna-68m-gguf
double7_-_vicuna-68m-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
9.6K
Public
Repo size
886 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 20, 2024
- Updated
- Jul 20, 2024
- SHA
- bda67f78
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
vicuna-68m - GGUF
- Model creator: https://huggingface.co/double7/
- Original model: https://huggingface.co/double7/vicuna-68m/
| Name | Quant method | Size |
|---|---|---|
| vicuna-68m.Q2_K.gguf | Q2_K | 0.03GB |
| vicuna-68m.IQ3_XS.gguf | IQ3_XS | 0.04GB |
| vicuna-68m.IQ3_S.gguf | IQ3_S | 0.04GB |
| vicuna-68m.Q3_K_S.gguf | Q3_K_S | 0.04GB |
| vicuna-68m.IQ3_M.gguf | IQ3_M | 0.04GB |
| vicuna-68m.Q3_K.gguf | Q3_K | 0.04GB |
| vicuna-68m.Q3_K_M.gguf | Q3_K_M | 0.04GB |
| vicuna-68m.Q3_K_L.gguf | Q3_K_L | 0.04GB |
| vicuna-68m.IQ4_XS.gguf | IQ4_XS | 0.04GB |
| vicuna-68m.Q4_0.gguf | Q4_0 | 0.04GB |
| vicuna-68m.IQ4_NL.gguf | IQ4_NL | 0.04GB |
| vicuna-68m.Q4_K_S.gguf | Q4_K_S | 0.04GB |
| vicuna-68m.Q4_K.gguf | Q4_K | 0.04GB |
| vicuna-68m.Q4_K_M.gguf | Q4_K_M | 0.04GB |
| vicuna-68m.Q4_1.gguf | Q4_1 | 0.04GB |
| vicuna-68m.Q5_0.gguf | Q5_0 | 0.05GB |
| vicuna-68m.Q5_K_S.gguf | Q5_K_S | 0.05GB |
| vicuna-68m.Q5_K.gguf | Q5_K | 0.05GB |
| vicuna-68m.Q5_K_M.gguf | Q5_K_M | 0.05GB |
| vicuna-68m.Q5_1.gguf | Q5_1 | 0.05GB |
| vicuna-68m.Q6_K.gguf | Q6_K | 0.05GB |
| vicuna-68m.Q8_0.gguf | Q8_0 | 0.07GB |
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 68M parameters, which is fine-tuned from LLaMA-68m on ShareGPT data.
The training setup follows the Vicuna suite.
The model is mainly developed as a base Small Speculative Model in the MCSD paper. As a comparison, it can be better aligned to the Vicuna models than LLaMA-68m 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 | 😃 |
- Created
- Jul 20, 2024
- Updated
- Jul 20, 2024