Update README.md

edd1ee4 verified about 2 years ago

2.8 kB

---
license: mit
language:
- en
---
# On-chain llama.cpp - Internet Computer

You can run any *.gguf file in a llama_cpp_canister, but these are smaller models you can use for testing [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
Notes:
- Try them out at [ICGPT](https://icgpt.icpp.world/)
- To use on the Internet Computer, follow instructions of [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
- Run local with [ggerganov/llama.cpp](https://github.com/ggerganov/llama.cpp)
- The models were created with the training procedure outlined in [karpathy/llama2.c](https://github.com/karpathy/llama2.c) and then converted into *.gguf format as described below.


## Setup local git with lfs

See: [Getting Started: set-up](https://huggingface.co/docs/hub/repositories-getting-started#set-up)

```bash
# install git lfs
# Ubuntu
git lfs install
# Mac
brew install git-lfs
# install huggingface CLI tools in a python environment
pip install huggingface-hub
# Clone this repo
# https
git clone https://huggingface.co/onicai/llama_cpp_canister_models
# ssh
git clone git@hf.co:onicai/llama_cpp_canister_models
cd llama_cpp_canister_models
# configure lfs for local repo
huggingface-cli lfs-enable-largefiles .
# tell lfs what files to track (.gitattributes)
git lfs track "*.gguf"
# add, commit & push as usual with git
git add <file-name>
git commit -m "Adding <file-name>"
git push -u origin main
```

## Model creation

We used [convert-llama2c-to-ggml](https://github.com/ggerganov/llama.cpp/tree/32c8486e1f0297393cb22ac0a0d26a6b17ad4d54/examples/convert-llama2c-to-ggml) to convert the llama2.c model+tokenizer to llama.cpp gguf format.
- Good read: [lama : add support for llama2.c models](https://github.com/ggerganov/llama.cpp/issues/2379)

For example:
```bash
# From llama.cpp root folder
# Build everything
make -j
# Convert a llama2c model+tokenizer to gguf
convert-llama2c-to-ggml --llama2c-model stories260Ktok512.bin --copy-vocab-from-model tok512.bin --llama2c-output-model stories260Ktok512.gguf
convert-llama2c-to-ggml --llama2c-model stories15Mtok4096.bin --copy-vocab-from-model tok4096.bin --llama2c-output-model stories15Mtok4096.gguf
convert-llama2c-to-ggml --llama2c-model stories42Mtok4096.bin --copy-vocab-from-model tok4096.bin --llama2c-output-model stories42Mtok4096.gguf
convert-llama2c-to-ggml --llama2c-model stories110Mtok32000.bin --copy-vocab-from-model models/ggml-vocab-llama.gguf --llama2c-output-model stories110Mtok32000.gguf
convert-llama2c-to-ggml --llama2c-model stories42Mtok32000.bin --copy-vocab-from-model models/ggml-vocab-llama.gguf --llama2c-output-model stories42Mtok32000.gguf
# Run it local, like this
./llama-cli -m stories15Mtok4096.gguf -p "Joe loves writing stories" -n 600 -c 128
```

	---
	license: mit
	language:
	- en
	---

	# On-chain llama.cpp - Internet Computer

	You can run any *.gguf file in a llama_cpp_canister, but these are smaller models you can use for testing [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)

	Notes:
	- Try them out at [ICGPT](https://icgpt.icpp.world/)
	- To use on the Internet Computer, follow instructions of [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
	- Run local with [ggerganov/llama.cpp](https://github.com/ggerganov/llama.cpp)
	- The models were created with the training procedure outlined in [karpathy/llama2.c](https://github.com/karpathy/llama2.c) and then converted into *.gguf format as described below.


	## Setup local git with lfs

	See: [Getting Started: set-up](https://huggingface.co/docs/hub/repositories-getting-started#set-up)

	```bash
	# install git lfs
	# Ubuntu
	git lfs install
	# Mac
	brew install git-lfs

	# install huggingface CLI tools in a python environment
	pip install huggingface-hub

	# Clone this repo
	# https
	git clone https://huggingface.co/onicai/llama_cpp_canister_models
	# ssh
	git clone git@hf.co:onicai/llama_cpp_canister_models

	cd llama_cpp_canister_models

	# configure lfs for local repo
	huggingface-cli lfs-enable-largefiles .

	# tell lfs what files to track (.gitattributes)
	git lfs track "*.gguf"

	# add, commit & push as usual with git
	git add <file-name>
	git commit -m "Adding <file-name>"
	git push -u origin main
	```

	## Model creation

	We used [convert-llama2c-to-ggml](https://github.com/ggerganov/llama.cpp/tree/32c8486e1f0297393cb22ac0a0d26a6b17ad4d54/examples/convert-llama2c-to-ggml) to convert the llama2.c model+tokenizer to llama.cpp gguf format.
	- Good read: [lama : add support for llama2.c models](https://github.com/ggerganov/llama.cpp/issues/2379)

	For example:
	```bash
	# From llama.cpp root folder

	# Build everything
	make -j

	# Convert a llama2c model+tokenizer to gguf
	convert-llama2c-to-ggml --llama2c-model stories260Ktok512.bin --copy-vocab-from-model tok512.bin --llama2c-output-model stories260Ktok512.gguf
	convert-llama2c-to-ggml --llama2c-model stories15Mtok4096.bin --copy-vocab-from-model tok4096.bin --llama2c-output-model stories15Mtok4096.gguf
	convert-llama2c-to-ggml --llama2c-model stories42Mtok4096.bin --copy-vocab-from-model tok4096.bin --llama2c-output-model stories42Mtok4096.gguf
	convert-llama2c-to-ggml --llama2c-model stories110Mtok32000.bin --copy-vocab-from-model models/ggml-vocab-llama.gguf --llama2c-output-model stories110Mtok32000.gguf
	convert-llama2c-to-ggml --llama2c-model stories42Mtok32000.bin --copy-vocab-from-model models/ggml-vocab-llama.gguf --llama2c-output-model stories42Mtok32000.gguf

	# Run it local, like this
	./llama-cli -m stories15Mtok4096.gguf -p "Joe loves writing stories" -n 600 -c 128
	```