|
|
--- |
|
|
tags: |
|
|
- code |
|
|
- starcoder2 |
|
|
library_name: transformers |
|
|
pipeline_tag: text-generation |
|
|
license: bigcode-openrail-m |
|
|
quantized_by: bartowski |
|
|
--- |
|
|
|
|
|
## Llamacpp Quantizations of starcoder2-15b-instruct |
|
|
|
|
|
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2354">b2354</a> for quantization. |
|
|
|
|
|
Original model: https://huggingface.co/TechxGenus/starcoder2-15b-instruct |
|
|
|
|
|
Download a file (not the whole branch) from below: |
|
|
|
|
|
| Filename | Quant type | File Size | Description | |
|
|
| -------- | ---------- | --------- | ----------- | |
|
|
| [starcoder2-15b-instruct-Q8_0.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q8_0.gguf) | Q8_0 | 16.96GB | Extremely high quality, generally unneeded but max available quant. | |
|
|
| [starcoder2-15b-instruct-Q6_K.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q6_K.gguf) | Q6_K | 13.10GB | Very high quality, near perfect, *recommended*. | |
|
|
| [starcoder2-15b-instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q5_K_M.gguf) | Q5_K_M | 11.43GB | High quality, very usable. | |
|
|
| [starcoder2-15b-instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q5_K_S.gguf) | Q5_K_S | 11.02GB | High quality, very usable. | |
|
|
| [starcoder2-15b-instruct-Q5_0.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q5_0.gguf) | Q5_0 | 11.02GB | High quality, older format, generally not recommended. | |
|
|
| [starcoder2-15b-instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q4_K_M.gguf) | Q4_K_M | 9.86GB | Good quality, similar to 4.25 bpw. | |
|
|
| [starcoder2-15b-instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q4_K_S.gguf) | Q4_K_S | 9.25GB | Slightly lower quality with small space savings. | |
|
|
| [starcoder2-15b-instruct-Q4_0.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q4_0.gguf) | Q4_0 | 9.06GB | Decent quality, older format, generally not recommended. | |
|
|
| [starcoder2-15b-instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q3_K_L.gguf) | Q3_K_L | 8.96GB | Lower quality but usable, good for low RAM availability. | |
|
|
| [starcoder2-15b-instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q3_K_M.gguf) | Q3_K_M | 8.10GB | Even lower quality. | |
|
|
| [starcoder2-15b-instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q3_K_S.gguf) | Q3_K_S | 6.98GB | Low quality, not recommended. | |
|
|
| [starcoder2-15b-instruct-Q2_K.gguf](https://huggingface.co/bartowski/starcoder2-15b-instruct-GGUF/blob/main/starcoder2-15b-instruct-Q2_K.gguf) | Q2_K | 6.19GB | Extremely low quality, *not* recommended. |
|
|
|
|
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski |
|
|
|
