CATALOGUE RECORD / HUB-DERIVED
Qwen
Qwen-72B
Revision b8e18ac61df64d35308695769ff46b976b6a00f4
TENSOR ACCOUNTING
Where the bytes are.
Summed from the safetensors index, one row per dtype. A parameter count alone cannot produce this figure, because a checkpoint may mix widths.
| Dtype | Parameters | Bytes each | Bytes | Share |
|---|---|---|---|---|
BF16 | 72,287,920,128 | 2 | 144.6 GB | 100.0% |
EVERY FIELD, WITH ITS ORIGIN
Sourced or undetermined. Never assumed.
Each value below names the exact API field it was computed from. Where the Hub does not establish a value, the reason is shown instead of a plausible default.
- Architecture
- qwen
config.model_type - Model classes
- QWenLMHeadModel
config.architectures - Routed experts
- UndeterminedThe published config exposes no routed-expert count. The Hub's config summary omits fields some architectures place only in the full config.json.
- Experts per token
- UndeterminedThe published config exposes no per-token expert count.
- Shared experts
- UndeterminedThe published config declares no always-on shared experts.
- Routing sparsity
- UndeterminedRouting sparsity requires both a routed-expert and a per-token expert count.
- Total parameters
- 72,287,920,128
safetensors.total - Checkpoint bytes
- 144,575,840,256 (144.6 GB)
safetensors.parameters - Ships below 16-bit
- No
safetensors.parameters - Quantisation method
- UndeterminedThe repository declares no quantization method, which normally means unquantized weights.
- Trained context
- UndeterminedThe config summary omits max_position_embeddings. Trained context is a model-card claim, not a derivable fact.
- Declared licence
- other
cardData.license - Base model
- UndeterminedThe repository declares no base model.
- Library
- transformers
library_name - Files in repository
- 103
siblings - Last modified
- 2024-10-09
lastModified
LICENCE POSTURE
Vendor terms
The repository ships bespoke vendor terms rather than a standard open licence. Acceptable-use clauses, attribution duties and user-count thresholds are common; read the terms in full.
This is a reading of a metadata field, not legal advice, and it does not account for the licences of upstream models or training data.
WEIGHT RESIDENCY FLOOR
The count below which it cannot fit.
Ceiling of checkpoint bytes over advertised accelerator memory. This is a lower bound on accelerator count for weights alone — KV cache, activations and runtime overhead all sit on top, so a real deployment needs more.