Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
wtfsayo
/
devstral-finetuned-lora
like
0
Text Generation
PEFT
Safetensors
Transformers
custom
English
lora
sft
trl
unsloth
code
devstral
mistral
conversational
Eval Results (legacy)
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
devstral-finetuned-lora
757 MB
1 contributor
History:
3 commits
wtfsayo
Add HumanEval benchmark results (pass@1: 3.0%)
96dc054
verified
15 days ago
.gitattributes
1.57 kB
Upload Devstral Small 2507 fine-tuned LoRA adapters (QLoRA r32, trained on 2100 AI coding conversations)
15 days ago
README.md
4.56 kB
Add HumanEval benchmark results (pass@1: 3.0%)
15 days ago
adapter_config.json
1.22 kB
Upload Devstral Small 2507 fine-tuned LoRA adapters (QLoRA r32, trained on 2100 AI coding conversations)
15 days ago
adapter_model.safetensors
739 MB
xet
Upload Devstral Small 2507 fine-tuned LoRA adapters (QLoRA r32, trained on 2100 AI coding conversations)
15 days ago
chat_template.jinja
9.84 kB
Upload Devstral Small 2507 fine-tuned LoRA adapters (QLoRA r32, trained on 2100 AI coding conversations)
15 days ago
special_tokens_map.json
21.4 kB
Upload Devstral Small 2507 fine-tuned LoRA adapters (QLoRA r32, trained on 2100 AI coding conversations)
15 days ago
tokenizer.json
17.1 MB
xet
Upload Devstral Small 2507 fine-tuned LoRA adapters (QLoRA r32, trained on 2100 AI coding conversations)
15 days ago
tokenizer_config.json
198 kB
Upload Devstral Small 2507 fine-tuned LoRA adapters (QLoRA r32, trained on 2100 AI coding conversations)
15 days ago
