|
--- |
|
license: other |
|
license_name: yi-license |
|
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE |
|
base_model: 01-ai/yi-34b-200k |
|
datasets: |
|
- jondurbin/airoboros-3.2 |
|
- bluemoon-fandom-1-1-rp-cleaned |
|
- boolq |
|
- jondurbin/gutenberg-dpo-v0.1 |
|
- LDJnr/Capybara |
|
- jondurbin/cinematika-v0.1 |
|
- glaiveai/glaive-function-calling-v2 |
|
- grimulkan/LimaRP-augmented |
|
- piqa |
|
- Vezora/Tested-22k-Python-Alpaca |
|
- mattpscott/airoboros-summarization |
|
- unalignment/toxic-dpo-v0.2 |
|
quantized_by: bartowski |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
## Llamacpp Quantizations of airoboros-34b-3.2 |
|
|
|
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2334">b2334</a> for quantization. |
|
|
|
Original model: https://huggingface.co/jondurbin/airoboros-34b-3.2 |
|
|
|
Download a file (not the whole branch) from below: |
|
|
|
| Filename | Quant type | File Size | Description | |
|
| -------- | ---------- | --------- | ----------- | |
|
| [airoboros-34b-3.2-Q8_0.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q8_0.gguf) | Q8_0 | 36.54GB | Extremely high quality, generally unneeded but max available quant. | |
|
| [airoboros-34b-3.2-Q6_K.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q6_K.gguf) | Q6_K | 28.21GB | Very high quality, near perfect, *recommended*. | |
|
| [airoboros-34b-3.2-Q5_K_M.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q5_K_M.gguf) | Q5_K_M | 24.32GB | High quality, very usable. | |
|
| [airoboros-34b-3.2-Q5_K_S.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q5_K_S.gguf) | Q5_K_S | 23.70GB | High quality, very usable. | |
|
| [airoboros-34b-3.2-Q5_0.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q5_0.gguf) | Q5_0 | 23.70GB | High quality, older format, generally not recommended. | |
|
| [airoboros-34b-3.2-Q4_K_M.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q4_K_M.gguf) | Q4_K_M | 20.65GB | Good quality, similar to 4.25 bpw. | |
|
| [airoboros-34b-3.2-Q4_K_S.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q4_K_S.gguf) | Q4_K_S | 19.59GB | Slightly lower quality with small space savings. | |
|
| [airoboros-34b-3.2-Q4_0.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q4_0.gguf) | Q4_0 | 19.46GB | Decent quality, older format, generally not recommended. | |
|
| [airoboros-34b-3.2-Q3_K_L.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q3_K_L.gguf) | Q3_K_L | 18.13GB | Lower quality but usable, good for low RAM availability. | |
|
| [airoboros-34b-3.2-Q3_K_M.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q3_K_M.gguf) | Q3_K_M | 16.65GB | Even lower quality. | |
|
| [airoboros-34b-3.2-Q3_K_S.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q3_K_S.gguf) | Q3_K_S | 14.96GB | Low quality, not recommended. | |
|
| [airoboros-34b-3.2-Q2_K.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q2_K.gguf) | Q2_K | 12.82GB | Extremely low quality, *not* recommended. |
|
|
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski |
|
|