docs: note 128K context and thinking on for frank-default-small
This commit is contained in:
@@ -131,9 +131,12 @@ Downloaded with the HF token to
|
|||||||
|
|
||||||
### Launch profile (from the model card)
|
### Launch profile (from the model card)
|
||||||
|
|
||||||
- 64K context, one slot, f16 KV, context checkpoints (32), prompt cache
|
- 128K context (user request 2026-08-18; model card default is 64K), one
|
||||||
|
slot, f16 KV (8 GiB at 128K, ~51.5 GiB total used of 64 GiB), context
|
||||||
|
checkpoints (32), prompt cache
|
||||||
- Native MTP draft, depth 4, device ROCm0
|
- Native MTP draft, depth 4, device ROCm0
|
||||||
- `--temp 0.7 --top-p 0.95`, reasoning off
|
- `--temp 0.7 --top-p 0.95`, reasoning on (`--reasoning-format deepseek`
|
||||||
|
puts `<think>` reasoning in `message.reasoning_content`)
|
||||||
- PromptForge env: `PROMPTFORGE_MODE=m2048_fused_tail1476`,
|
- PromptForge env: `PROMPTFORGE_MODE=m2048_fused_tail1476`,
|
||||||
`GGML_CUDA_GRAPH_OPT=0`, `LLAMA_MTP_CPU_ARGMAX_FASTPATH=1`
|
`GGML_CUDA_GRAPH_OPT=0`, `LLAMA_MTP_CPU_ARGMAX_FASTPATH=1`
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user