jtatman/python-github-code-instruct-filtered-5k
Viewer • Updated • 4.5k • 83 • 7
How to use jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("jtatman/tinymistral-v2-pycoder-instruct-248m")
model = PeftModel.from_pretrained(base_model, "jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora")How to use jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora",
max_seq_length=2048,
)irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora to start chatting# No setup required# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora to start chattingpip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora",
max_seq_length=2048,
)Experiment in reasoning using philosophy instead of direct CoT or other prompted thoughts.
An experimental model only.
Locutusque/TinyMistral-248M-v2-Instruct
Experimental model in code and reasoning using a philosophical base. Needs massive tuning and training.
None yet.
Install Unsloth Studio (macOS, Linux, WSL)
# Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for jtatman/tinymistral-v2-pycoder-philosophy-instruct-248m-lora to start chatting