mirror of
https://github.com/zenlm/zen5-engine.git
synced 2026-11-02 03:03:29 +00:00
Frank Denisandantirez
4344ab40f1
Broaden the DS4 imatrix prompt dataset with provider-neutral agent/tool traffic, multi-language programming prompts, algorithm recall, Bash scripting, and multilingual translation tasks. Remove duplicate rendered prompts and avoid provider-specific client references in the generated calibration corpus. This improves calibration coverage without claiming to fix a distributed GGUF bug.
36 lines
816 B
JSON
36 lines
816 B
JSON
{
|
|
"version": 3,
|
|
"purpose": "DeepSeek V4 Flash imatrix calibration prompts",
|
|
"record_count": 3310,
|
|
"rendered_utf8_bytes": 10167295,
|
|
"rough_token_estimate_bytes_div_4": 2541823,
|
|
"categories": {
|
|
"agent": 1106,
|
|
"algorithms": 32,
|
|
"general": 40,
|
|
"long_context": 12,
|
|
"programming": 48,
|
|
"source": 1892,
|
|
"translation": 180
|
|
},
|
|
"modes": {
|
|
"nothink": 1655,
|
|
"think": 1655
|
|
},
|
|
"bytes_by_category": {
|
|
"agent": 4432105,
|
|
"algorithms": 9388,
|
|
"general": 11902,
|
|
"long_context": 248628,
|
|
"programming": 14320,
|
|
"source": 5394802,
|
|
"translation": 56150
|
|
},
|
|
"files": {
|
|
"jsonl": "prompts.jsonl",
|
|
"all_rendered": "rendered_prompts.txt",
|
|
"nothink_rendered": "rendered_prompts_nothink.txt",
|
|
"think_rendered": "rendered_prompts_think.txt"
|
|
}
|
|
}
|