69 lines
4.0 KiB
Markdown
69 lines
4.0 KiB
Markdown
Quantization made by Richard Erkhov.
|
|
|
|
[Github](https://github.com/RichardErkhov)
|
|
|
|
[Discord](https://discord.gg/pvy7H8DZMG)
|
|
|
|
[Request more models](https://github.com/RichardErkhov/quant_request)
|
|
|
|
|
|
VLLM-new - GGUF
|
|
- Model creator: https://huggingface.co/Diksha2001/
|
|
- Original model: https://huggingface.co/Diksha2001/VLLM-new/
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [VLLM-new.Q2_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q2_K.gguf) | Q2_K | 2.96GB |
|
|
| [VLLM-new.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
|
|
| [VLLM-new.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ3_S.gguf) | IQ3_S | 3.43GB |
|
|
| [VLLM-new.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
|
|
| [VLLM-new.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ3_M.gguf) | IQ3_M | 3.52GB |
|
|
| [VLLM-new.Q3_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q3_K.gguf) | Q3_K | 3.74GB |
|
|
| [VLLM-new.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
|
|
| [VLLM-new.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
|
|
| [VLLM-new.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
|
|
| [VLLM-new.Q4_0.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_0.gguf) | Q4_0 | 4.34GB |
|
|
| [VLLM-new.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
|
|
| [VLLM-new.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
|
|
| [VLLM-new.Q4_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_K.gguf) | Q4_K | 4.58GB |
|
|
| [VLLM-new.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
|
|
| [VLLM-new.Q4_1.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_1.gguf) | Q4_1 | 4.78GB |
|
|
| [VLLM-new.Q5_0.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_0.gguf) | Q5_0 | 5.21GB |
|
|
| [VLLM-new.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
|
|
| [VLLM-new.Q5_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_K.gguf) | Q5_K | 5.34GB |
|
|
| [VLLM-new.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
|
|
| [VLLM-new.Q5_1.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_1.gguf) | Q5_1 | 5.65GB |
|
|
| [VLLM-new.Q6_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q6_K.gguf) | Q6_K | 6.14GB |
|
|
| [VLLM-new.Q8_0.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q8_0.gguf) | Q8_0 | 7.95GB |
|
|
|
|
|
|
|
|
|
|
Original model description:
|
|
---
|
|
base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
|
|
tags:
|
|
- text-generation-inference
|
|
- transformers
|
|
- unsloth
|
|
- llama
|
|
- trl
|
|
- sft
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# Uploaded model
|
|
|
|
- **Developed by:** Diksha2001
|
|
- **License:** apache-2.0
|
|
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-bnb-4bit
|
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
|