bartowski's picture
Llamacpp quants
333663a verified
---
language:
- en
license: mit
base_model:
- mistralai/Mistral-7B-v0.1
datasets:
- HuggingFaceH4/ultrafeedback_binarized
pipeline_tag: text-generation
model-index:
- name: Mistral-ORPO-⍺
results:
- task:
type: text-generation
dataset:
name: AlpacaEval 1
type: AlpacaEval
metrics:
- type: AlpacaEval 1.0
value: 87.92%
name: Win Rate
source:
url: https://github.com/tatsu-lab/alpaca_eval
name: self-reported
- task:
type: text-generation
dataset:
name: AlpacaEval 2
type: AlpacaEval
metrics:
- type: AlpacaEval 2.0
value: 11.33%
name: Win Rate
source:
url: https://github.com/tatsu-lab/alpaca_eval
name: self-reported
- task:
type: text-generation
dataset:
name: MT-Bench
type: MT-Bench
metrics:
- type: MT-Bench
value: 7.23
name: Score
source:
url: https://github.com/lm-sys/FastChat/blob/main/fastchat/llm_judge/
name: self-reported
quantized_by: bartowski
---
## Llamacpp Quantizations of mistral-orpo-alpha
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.
Original model: https://huggingface.co/kaist-ai/mistral-orpo-alpha
Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [mistral-orpo-alpha-Q8_0.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
| [mistral-orpo-alpha-Q6_K.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
| [mistral-orpo-alpha-Q5_K_M.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
| [mistral-orpo-alpha-Q5_K_S.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
| [mistral-orpo-alpha-Q5_0.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
| [mistral-orpo-alpha-Q4_K_M.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
| [mistral-orpo-alpha-Q4_K_S.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
| [mistral-orpo-alpha-Q4_0.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
| [mistral-orpo-alpha-Q3_K_L.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
| [mistral-orpo-alpha-Q3_K_M.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
| [mistral-orpo-alpha-Q3_K_S.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
| [mistral-orpo-alpha-Q2_K.gguf](https://huggingface.co/bartowski/mistral-orpo-alpha-GGUF/blob/main/mistral-orpo-alpha-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski