Hugging Face's logo

bhenrym14
/
airoboros-13b-gpt4-1.4.1-PI-8192-GPTQ

Text Generation
Transformers
llama
Inference Endpoints
Model card Files Community
bhenrym14 commited on
Commit
300be9f
·
1 Parent(s): a6ffb6f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -34,9 +34,14 @@ Recent advancements in extending context by RoPE scaling ([kaiokendev](https://k
34
  ## Relative Performance (perplexity)
35
  | Model | Context (tokens) | Perplexity |
36
  | ---------------------------------------------------- | ----------- | ---------- |
 
 
 
 
37
  | TheBloke/airoboros-13B-gpt4-1-4-SuperHOT-8K-GPTQ | 2048 | 5.98 |
38
  | TheBloke/airoboros-13B-gpt4-1-4-SuperHOT-8K-GPTQ | 4096 | 5.80 |
39
- | **bhenrym14/airoboros-13b-gpt4-1.4.1-PI-8192-GPTQ** | **2048** | **5.28** |
 
40
  | **bhenrym14/airoboros-13b-gpt4-1.4.1-PI-8192-GPTQ** | **4096** | **5.15** |
41
 
42
 
 
34
  ## Relative Performance (perplexity)
35
  | Model | Context (tokens) | Perplexity |
36
  | ---------------------------------------------------- | ----------- | ---------- |
37
+ | TheBloke/airoboros-13B-gpt4-1-4-SuperHOT-8K-GPTQ | 512 | **7.42** |
38
+ | TheBloke/airoboros-13B-gpt4-1-4-SuperHOT-8K-GPTQ | 2048 | **5.01** |
39
+ | TheBloke/airoboros-13B-gpt4-1-4-SuperHOT-8K-GPTQ | 4096 | 9848.0 |
40
+ | TheBloke/airoboros-13B-gpt4-1-4-SuperHOT-8K-GPTQ | 512 | 8.86 |
41
  | TheBloke/airoboros-13B-gpt4-1-4-SuperHOT-8K-GPTQ | 2048 | 5.98 |
42
  | TheBloke/airoboros-13B-gpt4-1-4-SuperHOT-8K-GPTQ | 4096 | 5.80 |
43
+ | **bhenrym14/airoboros-13b-gpt4-1.4.1-PI-8192-GPTQ** | **512** | 7.94 |
44
+ | **bhenrym14/airoboros-13b-gpt4-1.4.1-PI-8192-GPTQ** | **2048** | 5.28 |
45
  | **bhenrym14/airoboros-13b-gpt4-1.4.1-PI-8192-GPTQ** | **4096** | **5.15** |
46
 
47