Downloads · 30 days
0
glm-4.7-flash-spd-sidecar
meshllm/glm-4.7-flash-spd-sidecar
glm-4.7-flash-spd-sidecar is a text generation model from meshllm. Use it when you need the model to write or continue text. It is set up for skippy.
This repository contains a trained Speculative Pipeline Decoding (SPD) sidecar head for zai-org/GLM-4.7-Flash, produced for mesh-llm/Skippy PR 866.
Access
Public
Updated Jun 19, 2026
Repo size
964 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt643 MB · 67%
At a glance
- Task
- Text Generation
- Library
- skippy
- Access
- Public
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026
- SHA
- 9aad3508
Try a prompt
Base models
Model card
From the Hugging Face model README
GLM 4.7 Flash SPD Sidecar
This repository contains a trained Speculative Pipeline Decoding (SPD) sidecar head for zai-org/GLM-4.7-Flash, produced for mesh-llm/Skippy PR #866.
The head was trained against a frozen GLM 4.7 Flash checkpoint using the reference SPD trainer from yuyijiong/speculative_pipeline_decoding, with mesh-llm patches for GLM 4.7 topology, reduced-vocab KL training, and usable-row filtering.
Intended Use
This is a research/validation sidecar for verified speculative decoding. The target GLM model remains authoritative and verifies every proposed token. Current Skippy/Rust code can validate the manifest and serving checkpoint shape; live Rust-side SPD execution is still the integration target.
Training Configuration
| Field | Value |
|---|---|
| Base model | zai-org/GLM-4.7-Flash |
| Dataset | HuggingFaceH4/ultrachat_200k, split train_sft |
| Raw train rows | 8192 |
| Usable train rows after shifted-label filtering | 7377 |
| Stages | 3 |
| Stage layer boundaries | 15,31,47 |
| Spec layers | 1 |
| Draft vocab size | 16000 GLM-tokenizer ids |
| Max train length | 512 |
| Epochs | 1 |
| Optimizer steps | 923 |
| Batch / grad accumulation | 1 / 8 |
| Learning rate | 2e-5, 50 warmup steps |
| Device | Apple MPS |
Verified Acceptance Eval
Evaluation used the donor verifier with target verification enabled, greedy decode (temperature=0.0), draft_top_k=1, and 4 prompts each from MT-Bench, HumanEval, and GSM8K.
| Scope | Acceptance | Equivalent accept length | Theoretical gain | Accepted flags | New tokens | Decode steps |
|---|---|---|---|---|---|---|
| Overall | 0.3699 | 1.1098 | 11.09% | 109/768 | 768 | 2076 |
| MT-Bench | 0.3596 | 1.0787 | 7.88% | 26/256 | 256 | 712 |
| HumanEval | 0.3689 | 1.1066 | 10.76% | 35/256 | 256 | 694 |
| GSM8K | 0.3821 | 1.1463 | 14.64% | 48/256 | 256 | 670 |
Files
train/speculation_head_final.pt: original PyTorch reference checkpoint.train/spd-head.safetensors: Rust-readable serving checkpoint exported as F16.train/skippy-spd-head.json: Skippy SPD manifest with topology, draft vocabulary ids, and checksums.train/trainer_state.json: final trainer state and logged loss/accuracy curve.eval/summary/*.json: verifier acceptance summary.eval/raw/*.jsonl: per-sample verifier trace.data/draft_vocab_top_16000.json: generated GLM-tokenizer draft vocabulary.repro/train.sh: training/eval command used for this artifact.repro/export.sh: safetensors export command.checksums.json: SHA-256 and byte size for uploaded files.
Manifest Validation
The exported manifest was validated with:
SKIPPY_SPD_MANIFEST=/tmp/glm-4.7-flash-spd-sidecar-hub/train/skippy-spd-head.json cargo test -p skippy-runtime --lib validates_external_manifest_when_skippy_spd_manifest_is_set
- Task
- Text Generation
- Library
- skippy
- Languages
- en
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026