btbtyler09
/

cogito-v1-preview-qwen-32B-gptq-8bit

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

btbtyler09 commited on Apr 12

Commit

9602cc6

·

verified ·

1 Parent(s): 31bee5b

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -4,13 +4,13 @@ library_name: transformers
 base_model: deepcogito/cogito-v1-preview-qwen-32B
 pipeline_tag: text-generation
 tags:
-- 4bit
 - gptq
 ---
 # Cogito v1 preview - 32B
-GPTQ quantization of Cogito v1 preview - 32B based on Qwen QwQ. This quantization is a
 [Blog Post](https://www.deepcogito.com/research/cogito-v1-preview)

 base_model: deepcogito/cogito-v1-preview-qwen-32B
 pipeline_tag: text-generation
 tags:
+- 8bit
 - gptq
 ---
 # Cogito v1 preview - 32B
+GPTQ quantization of Cogito v1 preview - 32B based on Qwen QwQ. This is an 8bit gptq quantization.
 [Blog Post](https://www.deepcogito.com/research/cogito-v1-preview)