tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-06-15 18:49:10 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Allow local install and model loading

Browse Source
This commit is contained in:
askerlee 2026-01-13 22:20:22 +08:00
parent 4610a838a1
commit d6829284c4
3 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -12,3 +12,4 @@ eval_bundle/
.claude
CLAUDE.md
wandb/
*.egg-info/

3
pyproject.toml
View File

@ -71,3 +71,6 @@ conflicts = [
{ extra = "gpu" },
],
]
[tool.setuptools]
packages = ["nanochat"]

7
scripts/base_eval.py
View File

@ -134,13 +134,16 @@ def load_hf_model(hf_path: str, device):
print0(f"Loading model from: {hf_path}")
# Load the model
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(hf_path)
model = AutoModelForCausalLM.from_pretrained(hf_path, trust_remote_code=True)
model.to(device)
model.eval()
max_seq_len = 1024 if "openai-community/gpt2" in hf_path else None
model = ModelWrapper(model, max_seq_len=max_seq_len)
# Load the tokenizer
tokenizer = HuggingFaceTokenizer.from_pretrained(hf_path)
if os.path.exists(hf_path):
tokenizer = HuggingFaceTokenizer.from_directory(hf_path)
else:
tokenizer = HuggingFaceTokenizer.from_pretrained(hf_path)
return model, tokenizer
# -----------------------------------------------------------------------------