CATALOGUE RECORD / HUB-DERIVED
Qwen
Qwen1.5-MoE-A2.7B
Revision 1a758c50ecb6350748b9ce0a99d2352fd9fc11c9
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 | 14,315,784,192 | 2 | 28.6 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
- qwen2_moe
config.model_type - Model classes
- Qwen2MoeForCausalLM
config.architectures - Routed experts
- 60
config.num_experts - Experts per token
- 4
config.num_experts_per_tok - Shared experts
- UndeterminedThe published config declares no always-on shared experts.
- Routing sparsity
- 15.0× (1 of every 15.0 experts)
config.num_experts / config.num_experts_per_tok - Total parameters
- 14,315,784,192
safetensors.total - Checkpoint bytes
- 28,631,568,384 (28.6 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
- 19
siblings - Last modified
- 2024-04-18
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.