| --- |
| license: apache-2.0 |
| base_model: ibm-granite/granite-4.0-h-micro |
| tags: |
| - microtensor |
| - ctx_compress |
| extra_gated_heading: Request access to this model |
| extra_gated_prompt: >- |
| This model was ranked in the Agent session compaction arena on Microtensor. Its files open once |
| Microtensor approves your request. Tell us who you are and what you will use it for. |
| extra_gated_fields: |
| Name: text |
| Organisation: text |
| Intended use: text |
| I will use this model only under its licence: checkbox |
| extra_gated_button_content: Request access |
| --- |
| |
| # Agent session compaction, epoch 0 |
|
|
| This model ranked in the top 3 of a pool in the Agent session compaction arena (`ctx_compress`) on Microtensor (testnet), epoch 0. The weights, tokenizer and config here are byte for byte the files that were scored. |
|
|
| | Placement | Score | |
| |---|---| |
| | 2nd in the Model pool | 0.868 | |
|
|
| ## Results |
|
|
| | Pool | Score | Lower bound | Items | Eligible | |
| |---|---|---|---|---| |
| | Model | 0.868 | 0.867 | 25 | yes | |
| | Harness | 0.000 | 0.000 | 25 | no | |
| | Escalation | 0.000 | 0.000 | 25 | no | |
| | System | 0.000 | 0.000 | 25 | no | |
|
|
| ## Spot check |
|
|
| The coordinator reran 40 sampled model calls on the profile card and 40 matched token for token. First token p95 5,648 ms, per token p95 8.5 ms, within the speed limits: yes, within the memory limit: yes. |
|
|
| ## Use it |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| tokenizer = AutoTokenizer.from_pretrained("microtensor-io/ctx_compress-b0bd36e4") |
| model = AutoModelForCausalLM.from_pretrained("microtensor-io/ctx_compress-b0bd36e4") |
| ``` |
|
|
| ## What is in this repo |
|
|
| | Path | Contents | |
| |---|---| |
| | root | the scored model files, unchanged | |
| | `README.miner.md` | the miner's own README, unchanged | |
| | `system/` | the rest of the scored system: manifest, harness and escalation code | |
| | `training/` | the miner's training record, when the miner published one | |
| | `certificates/` | one signed certificate per epoch this artifact placed in | |
| | `evidence/` | the arena definition and links to the public records | |
|
|
| ## Verify it |
|
|
| 1. Take the SHA-256 of each weight file (`.safetensors` or `.gguf`), write one line per file as the file name, a space and the hash, sort the lines by file name, join them with newlines and take the SHA-256 of that text. It must equal `b0bd36e4ffcbf6e55762df1ed07d662c8eca53591e172bf845001bdcd133ed03`. |
| 2. Open `certificates/e0.json`, remove the `coordinator_sig` field, write the rest as JSON with sorted keys and no spaces, and take its SHA-256 as hex. The signature is over the text `microtensor-certificate:` followed by that hash, made with the sr25519 key of the coordinator hotkey `5D4cKxE8nX4jqJ7aMrrEhkXf7r6chouZbbn4ivQa9emk84m1`. |
| 3. Compare the scores with the public records listed in `evidence/links.json`. |
|
|
| Certificate hash: `06bb4e682ed4aa6b7b6d05f5d7c93a0e47070bb96f0568085f40edd12fc43918` |
|
|
| The certificate covers the measured results in this arena and epoch only. |
|
|
| Source model: `Daniel01410/mt_slm_ctx_compress@f72666d65646044970aaa3d11c80e3275c7ac994` by Daniel01410. |
|
|
