cstr
/

llama3-8b-spaetzle-v13

Text Generation

Azure99/blossom-v5-llama3-8b

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

cstr commited on May 7

Commit

06e68b1

•

1 Parent(s): c29116a

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -21,9 +21,9 @@ No change in llama3 prompt format template.
 It should work not too bad for German or English, e.g. it achieves 64.14(.10) on EQ Bench v2_de with 170(171)/171 per [q4km GGUF](https://huggingface.co/cstr/llama3-8b-spaetzle-v13-GGUF) (bpe fixed).
 And for English EQ-Bench Score (v2): 75.59, Parseable: 171.
-| Model                        | Average    | ARC    | HellaSwag | MMLU   | TruthfulQA | Winogrande | GSM8K  |
-|------------------------------|------------|--------|-----------|--------|------------|------------|--------|
-|  cstr/llama3-8b-spaetzle-v13 | 71.26      | 68.69  | 85.05     | 68.06  | 59.43      | 79.24      | 67.1   |
 ## Sample output

 It should work not too bad for German or English, e.g. it achieves 64.14(.10) on EQ Bench v2_de with 170(171)/171 per [q4km GGUF](https://huggingface.co/cstr/llama3-8b-spaetzle-v13-GGUF) (bpe fixed).
 And for English EQ-Bench Score (v2): 75.59, Parseable: 171.
+| Average    | ARC    | HellaSwag | MMLU   | TruthfulQA | Winogrande | GSM8K  |
+|------------|--------|-----------|--------|------------|------------|--------|
+| 71.26      | 68.69  | 85.05     | 68.06  | 59.43      | 79.24      | 67.1   |
 ## Sample output