Llamacpp Quantizations of NeuralSirKrishna-7b
Using llama.cpp release b2440 for quantization.
Original model: https://huggingface.co/Kukedlc/NeuralSirKrishna-7b/
Download a file (not the whole branch) from below:
Filename | Quant type | File Size | Description |
---|---|---|---|
NeuralSirKrishna-7b-Q8_0.gguf | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
NeuralSirKrishna-7b-Q6_K.gguf | Q6_K | 5.94GB | Very high quality, near perfect, recommended. |
NeuralSirKrishna-7b-Q5_K_M.gguf | Q5_K_M | 5.13GB | High quality, very usable. |
NeuralSirKrishna-7b-Q5_K_S.gguf | Q5_K_S | 4.99GB | High quality, very usable. |
NeuralSirKrishna-7b-Q5_0.gguf | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
NeuralSirKrishna-7b-Q4_K_M.gguf | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
NeuralSirKrishna-7b-Q4_K_S.gguf | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
NeuralSirKrishna-7b-Q4_0.gguf | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
NeuralSirKrishna-7b-Q3_K_L.gguf | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
NeuralSirKrishna-7b-Q3_K_M.gguf | Q3_K_M | 3.51GB | Even lower quality. |
NeuralSirKrishna-7b-Q3_K_S.gguf | Q3_K_S | 3.16GB | Low quality, not recommended. |
NeuralSirKrishna-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
- Downloads last month
- 31
Model tree for bartowski/NeuralSirKrishna-7b-GGUF
Merge model
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard73.720
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard89.050
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.630
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard75.600
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard85.320
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard71.270