Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
mrcmilo
/
phi3-text2sql-lora
like
0
Safetensors
GGUF
b-mc2/sql-create-context
English
mistral
llama.cpp
unsloth
conversational
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
phi3-text2sql-lora
5.16 GB
1 contributor
History:
17 commits
mrcmilo
Update README: correct Modelfile template and add ollama example
c82b290
verified
9 days ago
.gitattributes
1.66 kB
Add 5-bit GGUF for improved SQL generation accuracy
10 days ago
Modelfile
331 Bytes
Add 5-bit GGUF for improved SQL generation accuracy - Ollama Modelfile
10 days ago
README.md
2.28 kB
Update README: correct Modelfile template and add ollama example
9 days ago
adapter_config.json
1.21 kB
Initial fine-tuned TEXT2SQL adapter for Phi3 (Trained with Unsloth)
11 days ago
adapter_model.safetensors
120 MB
xet
Initial fine-tuned TEXT2SQL adapter for Phi3 (Trained with Unsloth)
11 days ago
added_tokens.json
293 Bytes
Upload model trained with Unsloth
11 days ago
chat_template.jinja
371 Bytes
Upload model trained with Unsloth
11 days ago
config.json
753 Bytes
Add 4-bit GGUF for local use - config
11 days ago
phi-3-mini-4k-instruct.Q4_K_M.gguf
2.32 GB
xet
Add 4-bit GGUF for local use
11 days ago
phi-3-mini-4k-instruct.Q5_K.gguf
2.72 GB
xet
Add 5-bit GGUF for improved SQL generation accuracy
10 days ago
special_tokens_map.json
572 Bytes
Upload model trained with Unsloth
11 days ago
tokenizer.json
3.62 MB
Upload model trained with Unsloth
11 days ago
tokenizer.model
500 kB
xet
Upload model trained with Unsloth
11 days ago
tokenizer_config.json
2.94 kB
Upload model trained with Unsloth
11 days ago