diff --git a/ask b/ask index 0cc2eb20c894cce6f341df86ac36669a52415d1e..14b4eb4cd70722f357b93fb652fdbe38fad259c9 100755 --- a/ask +++ b/ask @@ -23,7 +23,7 @@ get_model() { } # Default values -MODEL="inception/mercury-coder" +MODEL="inception/mercury-coder:nitro" SYSTEM_PROMPT="" PROMPT="" STREAMING=false @@ -163,13 +163,13 @@ if [ "$STREAMING" = true ]; then if [[ "$line" == data:* ]]; then json="${line#data: }" [ "$json" = "" ] || [ "$json" = "[DONE]" ] && continue - + content=$(echo "$json" | jq -r '.choices[0].delta.content // ""' 2>/dev/null) [ -n "$content" ] && printf '%s' "$content" fi done echo - + # Show metadata ELAPSED=$(printf "%.2f" $(echo "$(date +%s.%N) - $START_TIME" | bc)) echo @@ -195,7 +195,7 @@ else TOKENS=$(echo "$response" | jq -r '.usage.completion_tokens // 0') PROVIDER=$(echo "$response" | jq -r '.provider // "Unknown"') TPS=$(echo "scale=1; $TOKENS / $ELAPSED" | bc 2>/dev/null || echo "0.0") - + echo echo "[$MODEL via $PROVIDER - ${ELAPSED}s - ${TPS} tok/s]" >&2 fi