初始化项目，由ModelHub XC社区提供模型
Model: ZelligeAI/tessera-compressor Source: Original Platform
This commit is contained in:
ModelHub XC
95
README.md
Normal file
95
README.md
Normal file
@@ -0,0 +1,95 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
|
||||
language:
|
||||
- en
|
||||
- zh
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- reasoning-compression
|
||||
- cjk
|
||||
- chain-of-thought
|
||||
- distillation
|
||||
- qwen2.5
|
||||
---
|
||||
|
||||
|
||||
|
||||
# tessera-compressor
|
||||
|
||||
A 1.5B model that compresses English reasoning text into a telegraphic CJK/symbol register under deterministic fidelity gates. It minted the training data for [Tessera-Preview-9B](https://huggingface.co/ZelligeAI/tessera-preview-9b) and replaces the frontier-model teacher that originally produced the register: English reasoning text becomes compressed-register training data at local-inference cost, with no API key and no external dependency. Validation covered code-centric reasoning (103 held-out mixed blocks); behavior on distant domains is unmeasured.
|
||||
|
||||
**Paper:** [Tessera-Preview-9B: Compressed Reasoning at 18x Fewer Tokens, and What It Costs](https://zellige.ai/research/compressed-cjk-reasoning) — section 3.1 covers this compressor's design and acceptance record.
|
||||
|
||||
Example (real training pair, 85 to 49 tokens):
|
||||
|
||||
```text
|
||||
EN : So the classes are: - Integer (line 32) - Boolean (line 262) - BitString (line 341)
|
||||
- OctetString (line 693) ... Let me look at the base class to see if it defines __mul__:
|
||||
|
||||
CJK: Integer(line32),Boolean(line262),BitString(line341),OctetString(line693). 查基类是否定义__mul__:
|
||||
```
|
||||
|
||||
## How it works
|
||||
|
||||
The compressor operates on passages, not whole blocks. A reasoning block is segmented (code fences stay atomic), sentences are grouped into step-sized passages, each passage is classified as fact-dense or narrative, and the model compresses it against the tail of the chain built so far. Every model output then passes a deterministic gate: the passage's novel numbers and identifiers must survive as substrings, the output must not blow up in length, and it must not exceed a rules-only compression of the same passage in token count. A passage that fails any check falls back to the rules-only version, so a bad generation costs savings rather than gated content. The gate is lexical, not semantic: it prevents the loss of numbers and identifiers, and a judged semantic-equivalence check backed it at acceptance (below), but it does not by itself guarantee semantic preservation on arbitrary input.
|
||||
|
||||
## Acceptance record
|
||||
|
||||
Measured on 103 held-out reasoning blocks the model never trained on, under criteria fixed before evaluation:
|
||||
|
||||
| Criterion | Result |
|
||||
| --- | --- |
|
||||
| Per-passage fidelity gate (numbers and identifiers survive) | 99.0% |
|
||||
| Median per-passage compression ratio (output/input tokens) | 0.716 |
|
||||
| CJK adoption | 98.9% of compressed passages |
|
||||
| Judged semantic equivalence | 103/103 blocks (teacher references on the same blocks: 97.1%) |
|
||||
| Degenerate outputs | 0 |
|
||||
| Net corpus savings (after 24% rules-only fallback) | 30.4% |
|
||||
|
||||
On whole thinks in downstream production use (45,202 pairs), the compressed rendering costs a median 0.58x the tokens of its English source.
|
||||
|
||||
## Files
|
||||
|
||||
- Root: merged model, standard Hugging Face format (bf16). Base: Qwen2.5-Coder-1.5B-Instruct, LoRA r=16 merged in.
|
||||
- `gguf/compressor-v31-q8_0.gguf`: llama.cpp quantization, validated behaviorally (scores 4/4 on the same acceptance suite). q4_k_m showed visible drift and is not published.
|
||||
- `scripts/`: the complete usage harness. No tokens or keys required anywhere.
|
||||
|
||||
## Usage
|
||||
|
||||
Serve the model behind any OpenAI-compatible endpoint:
|
||||
|
||||
```bash
|
||||
vllm serve ZelligeAI/tessera-compressor --port 8001
|
||||
# or, CPU-friendly:
|
||||
llama-server -m gguf/compressor-v31-q8_0.gguf --port 8001
|
||||
```
|
||||
|
||||
Then run the harness:
|
||||
|
||||
```bash
|
||||
cd scripts && pip install -r requirements.txt
|
||||
|
||||
# compress one reasoning block from a text file
|
||||
python compress.py --in think.txt --endpoint http://localhost:8001/v1
|
||||
|
||||
# compress a corpus: {"id": ..., "text": ...} per JSONL line
|
||||
python compress.py --in blocks.jsonl --out compressed.jsonl \
|
||||
--endpoint http://localhost:8001/v1
|
||||
```
|
||||
|
||||
Output records carry the compressed text, source and output token counts, and per-block harness stats (model-accepted vs rules-fallback passage counts).
|
||||
|
||||
`scripts/` contents:
|
||||
|
||||
- `compress.py`: the driver. Segment, classify, compress per passage with chain context, gate, fall back on failure.
|
||||
- `segmenting.py`: segmentation, passage grouping, fact extraction, classification, and the fidelity gate. Pure text processing.
|
||||
- `tokenmax.py`: deterministic token-saving substitutions, used as the rules-only fallback and as a post-processor.
|
||||
|
||||
One note on token counting: the gate compares token counts under a tokenizer you choose (`--tokenizer`, default this repo). To reproduce the acceptance harness exactly, point it at the tokenizer of the model you are minting data for (the acceptance run used the Qwen3.5 target tokenizer).
|
||||
|
||||
Throughput on the acceptance hardware was 19.6K blocks/hour on one GPU, which makes minting compressed data cheap at any corpus size.
|
||||
|
||||
## License
|
||||
|
||||
Apache-2.0, same as the base model.
|
||||
Reference in New Issue
Block a user