lthn
/

LEK-GPT-OSS-20B

Text Generation

Mixture of Experts

4-bit precision

Model card Files Files and versions

LEK-GPT-OSS-20B

11.2 GB

1 contributor

History: 7 commits

lthn's picture

Update model card with v2 training details (600 iter, 2.3K examples, val loss 1.057)

06e8a0b verified 1 day ago

.gitattributes
1.57 kB

LEM-GPT-OSS-20B: LoRA fine-tuned with LEK-1 (iter 100 checkpoint, val_loss 1.052) 2 days ago
README.md
5.44 kB

Update model card with v2 training details (600 iter, 2.3K examples, val loss 1.057) 1 day ago
chat_template.jinja
16.7 kB

LEM-GPT-OSS-20B: LoRA fine-tuned with LEK-1 (iter 100 checkpoint, val_loss 1.052) 2 days ago
config.json
34 kB

LEK-GPT-OSS-20B v2: 600 iter LoRA on 2,299 examples (up from 160) 1 day ago
generation_config.json
177 Bytes

LEM-GPT-OSS-20B: LoRA fine-tuned with LEK-1 (iter 100 checkpoint, val_loss 1.052) 2 days ago
model-00001-of-00003.safetensors
5.31 GB
xet

LEK-GPT-OSS-20B v2: 600 iter LoRA on 2,299 examples (up from 160) 1 day ago
model-00002-of-00003.safetensors
5.26 GB
xet

LEK-GPT-OSS-20B v2: 600 iter LoRA on 2,299 examples (up from 160) 1 day ago
model-00003-of-00003.safetensors
608 MB
xet

LEK-GPT-OSS-20B v2: 600 iter LoRA on 2,299 examples (up from 160) 1 day ago
model.safetensors.index.json
67 kB

LEM-GPT-OSS-20B: LoRA fine-tuned with LEK-1 (iter 100 checkpoint, val_loss 1.052) 2 days ago
special_tokens_map.json
440 Bytes

LEM-GPT-OSS-20B: LoRA fine-tuned with LEK-1 (iter 100 checkpoint, val_loss 1.052) 2 days ago
tokenizer.json
27.9 MB
xet

LEM-GPT-OSS-20B: LoRA fine-tuned with LEK-1 (iter 100 checkpoint, val_loss 1.052) 2 days ago
tokenizer_config.json
351 Bytes

LEK-GPT-OSS-20B v2: 600 iter LoRA on 2,299 examples (up from 160) 1 day ago