starble-dev commited on
Commit
3ea3df4
·
verified ·
1 Parent(s): dc9ff9e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -25,13 +25,13 @@ PPL = Perplexity, lower is better<br>
25
  Comparisons are done as Q?_? Llama-3-8B against FP16 Llama-3-8B, recommended as a guideline and not as fact.
26
  | Quant Type | Note | Size |
27
  | ---- | ---- | ---- |
28
- | [Q2_K](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q2_K.gguf) | +3.5199 ppl @ Llama-3-8B | ? GB |
29
- | [Q3_K_S](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q3_K_S.gguf) | +1.6321 ppl @ Llama-3-8B | ? GB |
30
- | [Q3_K_M](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q3_K_M.gguf) | +0.6569 ppl @ Llama-3-8B | ? GB |
31
- | [Q3_K_L](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q3_K_L.gguf) | +0.5562 ppl @ Llama-3-8B | ? GB |
32
- | [Q4_K_S](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q4_K_S.gguf) | +0.5562 ppl @ Llama-3-8B | ? GB |
33
- | [Q4_K_M](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q4_K_M.gguf) | +0.1754 ppl @ Llama-3-8B | ? GB |
34
- | [Q5_K_S](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q5_K_S.gguf) | +0.1049 ppl @ Llama-3-8B | ? GB |
35
- | [Q5_K_M](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q5_K_M.gguf) | +0.0569 ppl @ Llama-3-8B | ? GB |
36
- | [Q6_K](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q6_K.gguf) | +0.0217 ppl @ Llama-3-8B | ? GB |
37
- | [Q8_0](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q8_0.gguf) | +0.0026 ppl @ Llama-3-8B | ? GB |
 
25
  Comparisons are done as Q?_? Llama-3-8B against FP16 Llama-3-8B, recommended as a guideline and not as fact.
26
  | Quant Type | Note | Size |
27
  | ---- | ---- | ---- |
28
+ | [Q2_K](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q2_K.gguf) | +3.5199 ppl @ Llama-3-8B | 4.79 GB |
29
+ | [Q3_K_S](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q3_K_S.gguf) | +1.6321 ppl @ Llama-3-8B | 5.53 GB |
30
+ | [Q3_K_M](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q3_K_M.gguf) | +0.6569 ppl @ Llama-3-8B | 6.08 GB |
31
+ | [Q3_K_L](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q3_K_L.gguf) | +0.5562 ppl @ Llama-3-8B | 6.56 GB |
32
+ | [Q4_K_S](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q4_K_S.gguf) | +0.5562 ppl @ Llama-3-8B | 7.12 GB |
33
+ | [Q4_K_M](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q4_K_M.gguf) | +0.1754 ppl @ Llama-3-8B | 7.48 GB |
34
+ | [Q5_K_S](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q5_K_S.gguf) | +0.1049 ppl @ Llama-3-8B | 8.52 GB |
35
+ | [Q5_K_M](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q5_K_M.gguf) | +0.0569 ppl @ Llama-3-8B | 8.73 GB |
36
+ | [Q6_K](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q6_K.gguf) | +0.0217 ppl @ Llama-3-8B | 10.1 GB |
37
+ | [Q8_0](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/Mini-Magnum-12B-v1.1-Q8_0.gguf) | +0.0026 ppl @ Llama-3-8B | 13.00 GB |