DavidAU
/

Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B-128k-ctx

Model card Files Files and versions

DavidAU commited on Jul 21

Commit

fdb2435

·

verified ·

1 Parent(s): a7bd31a

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -32,7 +32,7 @@ tags:
 library_name: transformers
 ---
-<h2>Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B</h2>
 This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
 The source code can also be used directly.
@@ -59,7 +59,7 @@ NOTE: All experts help with coding, regardless of how many you have activated.
 SETTINGS:
 - Temp .5 to .7 (or lower)
-- Max Context is 32k
 - topk: 20, topp: .8, minp: .05
 - rep pen: 1.05-1.1 (can be lower)
 - Jinja Template (embedded) or CHATML template.

 library_name: transformers
 ---
+<h2>Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B-128k-ctx</h2>
 This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
 The source code can also be used directly.
 SETTINGS:
 - Temp .5 to .7 (or lower)
+- Max Context is 128k
 - topk: 20, topp: .8, minp: .05
 - rep pen: 1.05-1.1 (can be lower)
 - Jinja Template (embedded) or CHATML template.