|
--- |
|
license: other |
|
tags: |
|
- axolotl |
|
- generated_from_trainer |
|
- Mistral |
|
- instruct |
|
- finetune |
|
- chatml |
|
- gpt4 |
|
- synthetic data |
|
- science |
|
- physics |
|
- chemistry |
|
- biology |
|
- math |
|
base_model: alpindale/Mistral-7B-v0.2-hf |
|
datasets: |
|
- allenai/ai2_arc |
|
- camel-ai/physics |
|
- camel-ai/chemistry |
|
- camel-ai/biology |
|
- camel-ai/math |
|
- metaeval/reclor |
|
- openbookqa |
|
- mandyyyyii/scibench |
|
- derek-thomas/ScienceQA |
|
- TIGER-Lab/ScienceEval |
|
- jondurbin/airoboros-3.2 |
|
- LDJnr/Capybara |
|
- Cot-Alpaca-GPT4-From-OpenHermes-2.5 |
|
- STEM-AI-mtl/Electrical-engineering |
|
- knowrohit07/saraswati-stem |
|
- sablo/oasst2_curated |
|
- lmsys/lmsys-chat-1m |
|
- TIGER-Lab/MathInstruct |
|
- bigbio/med_qa |
|
- meta-math/MetaMathQA-40K |
|
- openbookqa |
|
- piqa |
|
- metaeval/reclor |
|
- derek-thomas/ScienceQA |
|
- scibench |
|
- sciq |
|
- Open-Orca/SlimOrca |
|
- migtissera/Synthia-v1.3 |
|
- TIGER-Lab/ScienceEval |
|
- allenai/WildChat |
|
- microsoft/orca-math-word-problems-200k |
|
- openchat/openchat_sharegpt4_dataset |
|
- teknium/GPTeacher-General-Instruct |
|
- m-a-p/CodeFeedback-Filtered-Instruction |
|
quantized_by: bartowski |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
## Llamacpp Quantizations of Einstein-v5-v0.2-7B |
|
|
|
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2536">b2536</a> for quantization. |
|
|
|
Original model: https://huggingface.co/Weyaxi/Einstein-v5-v0.2-7B |
|
|
|
Download a file (not the whole branch) from below: |
|
|
|
| Filename | Quant type | File Size | Description | |
|
| -------- | ---------- | --------- | ----------- | |
|
| [Einstein-v5-v0.2-7B-Q8_0.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. | |
|
| [Einstein-v5-v0.2-7B-Q6_K.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. | |
|
| [Einstein-v5-v0.2-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. | |
|
| [Einstein-v5-v0.2-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. | |
|
| [Einstein-v5-v0.2-7B-Q5_0.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. | |
|
| [Einstein-v5-v0.2-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, uses about 4.83 bits per weight. | |
|
| [Einstein-v5-v0.2-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. | |
|
| [Einstein-v5-v0.2-7B-IQ4_NL.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-IQ4_NL.gguf) | IQ4_NL | 4.15GB | Decent quality, similar to Q4_K_S, new method of quanting, | |
|
| [Einstein-v5-v0.2-7B-IQ4_XS.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-IQ4_XS.gguf) | IQ4_XS | 3.94GB | Decent quality, new method with similar performance to Q4. | |
|
| [Einstein-v5-v0.2-7B-Q4_0.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. | |
|
| [Einstein-v5-v0.2-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. | |
|
| [Einstein-v5-v0.2-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. | |
|
| [Einstein-v5-v0.2-7B-IQ3_M.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-IQ3_M.gguf) | IQ3_M | 3.28GB | Medium-low quality, new method with decent performance. | |
|
| [Einstein-v5-v0.2-7B-IQ3_S.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-IQ3_S.gguf) | IQ3_S | 3.18GB | Lower quality, new method with decent performance, recommended over Q3 quants. | |
|
| [Einstein-v5-v0.2-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. | |
|
| [Einstein-v5-v0.2-7B-Q2_K.gguf](https://huggingface.co/bartowski/Einstein-v5-v0.2-7B-GGUF/blob/main/Einstein-v5-v0.2-7B-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 |
|
|
