cross-distill-cart is an open-weight model from Sehyun Park. Its published files total 15.3 GB.
Parameters—
Context—
Weights14.4 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- sehyun734/cross-distill-cart
- Publisher
- Sehyun Park
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- f46777e6d761ef58d769d7705ffb9e8b6e50de64
- First published
- 2026-10-03
- Last updated
- 2026-10-07
Files and Weights
57 files, 15.3 GB in total. The weights are 12 files totalling 14.4 GB in safetensors.
Weights12 files · 14.4 GB
Configuration44 files · 885.8 MB
Repository1 file · 3.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/cartridge.safetensors | Weights | 134.3 MB | 916672ef46e9 |
| cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-1B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/cartridge.safetensors | Weights | 134.3 MB | aa60ce325ae6 |
| cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/cartridge.safetensors | Weights | 134.3 MB | 241dbbbcbfc6 |
| cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.2/cartridge_len=2048,learning_rate=0.02,seed=0/cartridge.safetensors | Weights | 469.9 MB | 9a426137f650 |
| cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/cartridge.safetensors | Weights | 469.9 MB | 218019607d43 |
| cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=32768,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/cartridge.safetensors | Weights | 469.9 MB | 73657b8a7804 |
| cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/cartridge.safetensors | Weights | 469.9 MB | 77e20c903c2f |
| synthesis/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.2/logprobs.safetensors | Weights | 1.8 GB | 4b0e60dad86f |
| synthesis/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/logprobs.safetensors | Weights | 2.1 GB | 254e7f135b7b |
| synthesis/teacher=Llama-3.1-8B-Instruct,num_samples=32768,cot_ratio=0.75/logprobs.safetensors | Weights | 4.1 GB | f49abb2de231 |
| synthesis/teacher=Llama-3.2-1B-Instruct,num_samples=16384,cot_ratio=0.75/logprobs.safetensors | Weights | 2.2 GB | 346885bdf251 |
| synthesis/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/logprobs.safetensors | Weights | 2.0 GB | a2aa64a29000 |
| kl/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/num_samples=1024.json | Configuration | 74 B | — |
| kl/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-1B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/num_samples=1024.json | Configuration | 74 B | — |
| kl/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/num_samples=1024.json | Configuration | 73 B | — |
| kl/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.2/cartridge_len=2048,learning_rate=0.02,seed=0/num_samples=1024.json | Configuration | 74 B | — |
| kl/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/num_samples=1024.json | Configuration | 74 B | — |
| kl/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=32768,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/num_samples=1024.json | Configuration | 74 B | — |
| kl/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/num_samples=1024.json | Configuration | 74 B | — |
| longhealth/base/Llama-3.2-1B-Instruct/logprob.json | Configuration | 2.2 KB | — |
| longhealth/base/Llama-3.2-1B-Instruct/seed=0.json | Configuration | 215.1 KB | — |
| longhealth/base/Llama-3.2-1B-Instruct/seed=1.json | Configuration | 214.9 KB | — |
| longhealth/base/Llama-3.2-1B-Instruct/seed=2.json | Configuration | 211.5 KB | — |
| longhealth/base/Llama-3.2-3B-Instruct/logprob.json | Configuration | 2.2 KB | — |
| longhealth/base/Llama-3.2-3B-Instruct/seed=1.json | Configuration | 218.6 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/logprob.json | Configuration | 2.2 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=0.json | Configuration | 173.9 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=1.json | Configuration | 157.0 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=2.json | Configuration | 159.6 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-1B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/logprob.json | Configuration | 2.2 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-1B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=0.json | Configuration | 210.5 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-1B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=1.json | Configuration | 218.3 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-1B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=2.json | Configuration | 210.9 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/logprob.json | Configuration | 2.2 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=0.json | Configuration | 202.1 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=1.json | Configuration | 201.9 KB | — |
| longhealth/cartridge/Llama-3.2-1B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=2.json | Configuration | 204.8 KB | — |
| longhealth/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.2/cartridge_len=2048,learning_rate=0.02,seed=0/logprob.json | Configuration | 2.2 KB | — |
| longhealth/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.2/cartridge_len=2048,learning_rate=0.02,seed=0/seed=1.json | Configuration | 236.9 KB | — |
| longhealth/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/logprob.json | Configuration | 2.2 KB | — |
| longhealth/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=1.json | Configuration | 346.6 KB | — |
| longhealth/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=32768,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/logprob.json | Configuration | 2.2 KB | — |
| longhealth/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.1-8B-Instruct,num_samples=32768,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=1.json | Configuration | 361.0 KB | — |
| longhealth/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/logprob.json | Configuration | 2.2 KB | — |
| longhealth/cartridge/Llama-3.2-3B-Instruct/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/cartridge_len=2048,learning_rate=0.02,seed=0/seed=1.json | Configuration | 213.4 KB | — |
| longhealth/icl/Llama-3.2-1B-Instruct/logprob.json | Configuration | 2.2 KB | — |
| longhealth/icl/Llama-3.2-1B-Instruct/seed=0.json | Configuration | 148.9 KB | — |
| longhealth/icl/Llama-3.2-1B-Instruct/seed=1.json | Configuration | 145.5 KB | — |
| longhealth/icl/Llama-3.2-1B-Instruct/seed=2.json | Configuration | 130.8 KB | — |
| longhealth/icl/Llama-3.2-3B-Instruct/logprob.json | Configuration | 2.1 KB | — |
| longhealth/icl/Llama-3.2-3B-Instruct/seed=1.json | Configuration | 165.8 KB | — |
| synthesis/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.2/rows.json | Configuration | 142.6 MB | 72c18e9ad6f7 |
| synthesis/teacher=Llama-3.1-8B-Instruct,num_samples=16384,cot_ratio=0.75/rows.json | Configuration | 147.9 MB | e17b05217a67 |
| synthesis/teacher=Llama-3.1-8B-Instruct,num_samples=32768,cot_ratio=0.75/rows.json | Configuration | 293.9 MB | e989a648f521 |
| synthesis/teacher=Llama-3.2-1B-Instruct,num_samples=16384,cot_ratio=0.75/rows.json | Configuration | 150.7 MB | e81b4377faaf |
| synthesis/teacher=Llama-3.2-3B-Instruct,num_samples=16384,cot_ratio=0.75/rows.json | Configuration | 146.3 MB | 292bebdf3d93 |
| .gitattributes | Repository | 3.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 14.4 GB
Download from Sehyun Park
Released by Sehyun Park through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 14.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.