Add a new model architecture to `llama.cpp`

Adding a model requires few steps:

Convert the model to GGUF
Define the model architecture in llama.cpp
Build the GGML graph implementation

After following these steps, you can open PR.

Also, it is important to check that the examples and main ggml backends (CUDA, METAL, CPU) are working with the new architecture, especially:

main
imatrix
quantize
server

1. Convert the model to GGUF

This step is done in python with a convert script using the gguf library. Depending on the model architecture, you can use either convert_hf_to_gguf.py or examples/convert_legacy_llama.py (for llama/llama2 models in .pth format).

The convert script reads the model configuration, tokenizer, tensor names+data and converts them to GGUF metadata and tensors.

The required steps to implement for an HF model are:

Define the model Model.register annotation in a new Model subclass, example:

@Model.register("MyModelForCausalLM")
class MyModel(Model):
    model_arch = gguf.MODEL_ARCH.MYMODEL

Define the layout of the GGUF tensors in constants.py

Add an enum entry in MODEL_ARCH, the model human friendly name in MODEL_ARCH_NAMES and the GGUF tensor names in MODEL_TENSORS.

Example for falcon model:

    MODEL_ARCH.FALCON: [
        MODEL_TENSOR.TOKEN_EMBD,
        MODEL_TENSOR.OUTPUT_NORM,
        MODEL_TENSOR.OUTPUT,
        MODEL_TENSOR.ATTN_NORM,
        MODEL_TENSOR.ATTN_NORM_2,
        MODEL_TENSOR.ATTN_QKV,
        MODEL_TENSOR.ATTN_OUT,
        MODEL_TENSOR.FFN_DOWN,
        MODEL_TENSOR.FFN_UP,
    ]

Map the original tensor names to the standardize equivalent in GGUF

As a general rule, before adding a new tensor name to GGUF, be sure the equivalent naming does not already exist.

Once you have found the GGUF tensor name equivalent, add it to the tensor_mapping.py file.

If the tensor name is part of a repetitive layer/block, the key word bid substitutes it.

Example for the normalization tensor in attention layers:

block_mappings_cfg: dict[MODEL_TENSOR, tuple[str, ...]] = {
        # Attention norm
        MODEL_TENSOR.ATTN_NORM: (
            "gpt_neox.layers.{bid}.input_layernorm",                # gptneox
            "transformer.h.{bid}.ln_1",                             # gpt2 gpt-j refact qwen
            "transformer.blocks.{bid}.norm_1",                      # mpt
            ...
        )
}

transformer.blocks.{bid}.norm_1 will be mapped to blk.{bid}.attn_norm in GGUF.

Depending on the model configuration, tokenizer, code and tensors layout, you will have to override:

Model#set_gguf_parameters
Model#set_vocab
Model#write_tensors

NOTE: Tensor names must end with .weight or .bias suffixes, that is the convention and several tools like quantize expect this to proceed the weights.

2. Define the model architecture in `llama.cpp`

The model params and tensors layout must be defined in llama.cpp source files:

Define a new llm_arch enum value in src/llama-arch.h.
In src/llama-arch.cpp:
- Add the architecture name to the LLM_ARCH_NAMES map.
- Add the tensor mappings to the LLM_TENSOR_NAMES map.
Add any non-standard metadata loading in the llama_model_loader constructor in src/llama-model-loader.cpp.
If the model has a RoPE operation, add a case for the architecture in llama_model_rope_type function in src/llama-model.cpp.

NOTE: The dimensions in ggml are typically in the reverse order of the pytorch dimensions.

3. Build the GGML graph implementation

This is the funniest part, you have to provide the inference graph implementation of the new model architecture in src/llama-model.cpp. Create a new struct that inherits from llm_graph_context and implement the graph-building logic in its constructor. Have a look at existing implementations like llm_build_llama, llm_build_dbrx or llm_build_bert. Then, in the llama_model::build_graph method, add a case for your architecture to instantiate your new graph-building struct.

Some ggml backends do not support all operations. Backend implementations can be added in a separate PR.

Note: to debug the inference graph: you can use llama-eval-callback.

GGUF specification

https://github.com/ggml-org/ggml/blob/master/docs/gguf.md

Resources

YaRN RoPE scaling #2268
support Baichuan serial models #3009
support attention bias #4283
Mixtral support #4406
BERT embeddings #5423
Grok-1 support #6204
Command R Plus support #6491
support arch DBRX #6515
How to convert HuggingFace model to GGUF format #2948

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!