not ready Current free model
LiquidAI: LFM2.5-1.2B-Instruct (free)
liquid/lfm-2.5-1.2b-instruct:free
Denne side er genereret fra Hermes LLM knowledge registry. Den viser status, research, test-evidens og næste testplan. Free-status er midlertidig metadata, ikke sidens formål.
Capabilities
frequency_penaltymax_tokensmin_ppresence_penaltyrepetition_penaltyseedstopstructured_outputstemperaturetop_ktop_p
Input modalities: text
Recommended use cases
- Structured extraction or validated JSON outputs, with parser validation
Skills and prompt patterns
No specific skills recorded yet.
Best practices
- Use external source evidence before final recommendation; keep local eval evidence authoritative for behavior.
- Start with low-temperature deterministic tests before creative tasks
- Log provider, returned model, latency, status, score, prompt/skill version, and redacted errors
- Persist every result immediately, including bad outcomes
- Do not test capabilities that catalog/provider metadata says are unsupported
- Validate structured outputs with an external parser; do not trust raw format claims
Test evidence
Status counts
{"200": 24, "404": 3}
Provider counts
{"Liquid": 24, "unknown": 3}
Bad signals
{"404_no_tool_endpoint": 3}
Recent records
| Lane | Scenario | Status | Provider | Score | Signal |
|---|
| optimal_tools_skills | optimal_policy_dry_run | 404 | | 0.0 | 404_no_tool_endpoint |
| optimal_tools_skills | optimal_research_synthesis | 404 | | 0.0 | 404_no_tool_endpoint |
| optimal_tools_skills | optimal_file_diagnosis | 404 | | 0.0 | 404_no_tool_endpoint |
| scenario_battery | t1_smoke_danish_exact | 200 | Liquid | 0.0 | |
| scenario_battery | t1_smoke_danish_exact | 200 | Liquid | 0.0 | |
| scenario_battery | t1_smoke_danish_exact | 200 | Liquid | 0.0 | |
| scenario_battery | t1_smoke_danish_exact | 200 | Liquid | 0.0 | |
| scenario_battery | t1_smoke_danish_exact | 200 | Liquid | 0.0 | |
Next test plan
researchsmokemodel_specific_optimalfinal_recommendation_pagestructured_output_validation
Skipped lanes:- tools_skills: catalog_supported_parameters_missing_tools
- tools_skills: catalog_supported_parameters_missing_tools
Research sources
External source enrichment present: yes
Recommendation status
not ready: Do not publish as a final recommended model yet. Keep the info page as evidence and run the listed follow-up tests.
Recommended roles
monitoring_only_until_retest
Risks and caveats
- policy: free_status_is_transient (1)