Skip to content

[llama examples] Update README.md to refer directly consolidated.00.p… #11298

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 2, 2025
Merged

[llama examples] Update README.md to refer directly consolidated.00.p… #11298

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions examples/models/llama/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,7 +164,7 @@ Llama 3 8B performance was measured on the Samsung Galaxy S22, S24, and OnePlus
```
# No quantization
# Set these paths to point to the downloaded files
LLAMA_CHECKPOINT=path/to/checkpoint.pth
LLAMA_CHECKPOINT=path/to/consolidated.00.pth
LLAMA_PARAMS=path/to/params.json

python -m examples.models.llama.export_llama \
Expand All @@ -186,7 +186,7 @@ For convenience, an [exported ExecuTorch bf16 model](https://huggingface.co/exec
```
# SpinQuant
# Set these paths to point to the exported files
LLAMA_QUANTIZED_CHECKPOINT=path/to/spinquant/checkpoint.pth
LLAMA_QUANTIZED_CHECKPOINT=path/to/spinquant/consolidated.00.pth.pth
LLAMA_PARAMS=path/to/spinquant/params.json

python -m examples.models.llama.export_llama \
Expand Down Expand Up @@ -215,7 +215,7 @@ For convenience, an [exported ExecuTorch SpinQuant model](https://huggingface.co
```
# QAT+LoRA
# Set these paths to point to the exported files
LLAMA_QUANTIZED_CHECKPOINT=path/to/qlora/checkpoint.pth
LLAMA_QUANTIZED_CHECKPOINT=path/to/qlora/consolidated.00.pth.pth
LLAMA_PARAMS=path/to/qlora/params.json

python -m examples.models.llama.export_llama \
Expand Down Expand Up @@ -248,7 +248,7 @@ You can export and run the original Llama 3 8B instruct model.
2. Export model and generate `.pte` file
```
python -m examples.models.llama.export_llama \
--checkpoint <consolidated.00.pth> \
--checkpoint <consolidated.00.pth.pth> \
-p <params.json> \
-kv \
--use_sdpa_with_kv_cache \
Expand Down Expand Up @@ -396,7 +396,7 @@ First export your model for lowbit quantization (step 2 above):

```
# Set these paths to point to the downloaded files
LLAMA_CHECKPOINT=path/to/checkpoint.pth
LLAMA_CHECKPOINT=path/to/consolidated.00.pth.pth
LLAMA_PARAMS=path/to/params.json

# Set low-bit quantization parameters
Expand Down Expand Up @@ -476,7 +476,7 @@ We use [LM Eval](https://github.com/EleutherAI/lm-evaluation-harness) to evaluat
For base models, use the following example command to calculate its perplexity based on WikiText.
```
python -m examples.models.llama.eval_llama \
-c <checkpoint.pth> \
-c <consolidated.00.pth.pth> \
-p <params.json> \
-t <tokenizer.model/bin> \
-kv \
Expand All @@ -489,7 +489,7 @@ python -m examples.models.llama.eval_llama \
For instruct models, use the following example command to calculate its MMLU score.
```
python -m examples.models.llama.eval_llama \
-c <checkpoint.pth> \
-c <consolidated.00.pth.pth> \
-p <params.json> \
-t <tokenizer.model/bin> \
-kv \
Expand Down
Loading