diff --git a/README.md b/README.md index 3b202a336..48dcd6464 100644 --- a/README.md +++ b/README.md @@ -103,6 +103,7 @@ as the main playground for developing new features for the [ggml](https://github - [x] [Qwen models](https://huggingface.co/models?search=Qwen/Qwen) - [x] [Mixtral MoE](https://huggingface.co/models?search=mistral-ai/Mixtral) - [x] [PLaMo-13B](https://github.com/ggerganov/llama.cpp/pull/3557) +- [x] [GPT-2](https://huggingface.co/gpt2) **Multimodal models:** diff --git a/awq-py/README.md b/awq-py/README.md new file mode 100644 index 000000000..59354f4e3 --- /dev/null +++ b/awq-py/README.md @@ -0,0 +1,116 @@ +# AWQ: Activation-aware Weight Quantization for LLM - version apply to llamacpp +[[Paper](https://arxiv.org/abs/2306.00978)][[Original Repo](https://github.com/mit-han-lab/llm-awq)][[Easy-to-use Repo](https://github.com/casper-hansen/AutoAWQ)] + +**Supported models:** + +- [X] LLaMA +- [x] LLaMA 2 +- [X] MPT +- [X] Mistral AI v0.1 +- [ ] Bloom +- [ ] Mixtral MoE + +**TODO:** +- [x] Update version work with both MPT and MPT-AWQ model +- [ ] Add OPT model +- [ ] Add Bloom model +- [ ] Add Mixtral MoE +- [ ] Support w3, w2 + + +## Contents + +- [Install](##Install) +- [Convert](##Convert) +- [Quantize](##Quantize) +- [Test](##Test) +- [Benchmark](##Benchmark) +- [Results](##Results) + +## Install +Install requirements +```bash +pip install -r requirements.txt +``` +Get the pre-computed AWQ search results for multiple model families, including LLaMA, LLaMA2, MPT, OPT +```bash +git clone https://huggingface.co/datasets/mit-han-lab/awq-model-zoo awq_cache +``` + +## Convert +Example for llama model +```bash +# For llama7b and llama2 models +python convert.py models/llama-7b/ --awq-path awq_cache/llama-7b-w4-g128.pt --outfile models/llama_7b_fp16.gguf +# For mistral and mpt models +python convert-hf-to-gguf.py models/mpt-7b/ --awq-path awq_cache/llama-7b-w4-g128.pt --outfile models/mpt_7b_fp16.gguf +``` + +## Quantize +```bash +# We only benchmark and confirm the results on q4_0, q4_1, and q2_k types. +./quantize models/llama_7b_fp16.gguf models/llama_7b_q4_0.gguf q4_0 +``` + +## Test +```bash +# For all models. +./build/bin/main -m models/llama_7b_q4_0.gguf -n 128 --prompt "Once upon a time" +``` + +## Benchmark +The perplexity measurements in table above are done against the `wikitext2` test dataset (https://paperswithcode.com/dataset/wikitext-2), with context length of 512. +```bash +# For llama and llama2, and mistral models. +./perplexity -m models/llama_7b_q4_0.gguf -f datasets/wikitext-2-raw/wiki.test.raw +``` + +## Results +Results are run on OpenBLAS (CPU) and CuBLAS (GPU) for fair comparison +We use three types of llamacpp quantization methods to work with our version, including q4_0, q4_1, and q2_k + +### Llama 7B (Build with OpenBLAS) + +| Model | Measure | F16 | Q4_0 | Q4_1 | Q2_K | +|-----------:|--------------|-------:|-------:|-------:|-------:| +|Llama 7B | perplexity | 5.9066 | 6.1214 | 6.0643 | 6.5808 | +|Llama 7B | file size | 12.9G | 3.5G | 3.9G | 2.7G | +|Llama 7B | bits/weight | 16.0 | 4.5 | 5.0 | 2.6 | +|AWQ-LLama 7B| perplexity | 5.9175 | 6.0252 | 5.9987 | 6.3692 | +|AWQ-LLama 7B| file size | 12.9G | 3.5G | 3.9G | 2.7G | +|AWQ-LLama 7B| bits/weight | 16.0 | 4.5 | 5.0 | 2.6 | + + +### Llama2 7B (Build with CuBLAS) + +| Model | Measure | F16 | Q4_0 | Q4_1 | Q2_K | +|------------:|--------------|-------:|-------:|-------:|-------:| +|Llama2 7B | perplexity | 5.8664 | 6.0260 | 6.0656 | 6.4496 | +|Llama2 7B | file size | 12.9G | 3.5G | 3.9G | 2.7G | +|Llama2 7B | bits/weight | 16.0 | 4.5 | 5.0 | 2.6 | +|AWQ-LLama2 7B| perplexity | 5.8801 | 6.0054 | 5.9849 | 6.3650 | +|AWQ-LLama2 7B| file size | 12.9G | 3.5G | 3.9G | 2.7G | +|AWQ-LLama2 7B| bits/weight | 16.0 | 4.5 | 5.0 | 2.6 | + + +### Mistral 7B v0.1 (Build with CuBLAS) + +| Model | Measure | F16 | Q4_0 | Q4_1 | Q2_K | +|-------------:|--------------|-------:|-------:|-------:|-------:| +|Mistral 7B | perplexity | 5.6931 | 5.8202 | 5.8268 | 6.1645 | +|Mistral 7B | file size | 14.5G | 4.1G | 4.5G | 3.1G | +|Mistral 7B | bits/weight | 16.0 | 4.5 | 5.0 | 2.6 | +|AWQ-Mistral 7B| perplexity | 5.6934 | 5.8020 | 5.7691 | 6.0426 | +|AWQ-Mistral 7B| file size | 14.5G | 4.1G | 4.5G | 3.1G | +|AWQ-Mistral 7B| bits/weight | 16.0 | 4.5 | 5.0 | 2.6 | + +### MPT 7B (Build with OpenBLAS) + +| Model | Measure | F16 | Q4_0 | Q4_1 | Q2_K | +|---------:|--------------|-------:|-------:|-------:|--------:| +|MPT 7B | perplexity | 8.4369 | 8.7956 | 8.6265 | 11.4913 | +|MPT 7B | file size | 13.7G | 3.9G | 4.3G | 2.8G | +|MPT 7B | bits/weight | 16.0 | 4.5 | 5.0 | 2.6 | +|AWQ-MPT 7B| perplexity | 8.4944 | 8.7053 | 8.6750 | 10.2873| +|AWQ-MPT 7B| file size | 13.7G | 3.9G | 4.3G | 2.8G | +|AWQ-MPT 7B| bits/weight | 16.0 | 4.5 | 5.0 | 2.6 | diff --git a/awq-py/awq/apply_awq.py b/awq-py/awq/apply_awq.py new file mode 100644 index 000000000..11132c5d2 --- /dev/null +++ b/awq-py/awq/apply_awq.py @@ -0,0 +1,254 @@ +""" +Implements the AWQ for llama.cpp use cases. +Original paper: https://arxiv.org/abs/2306.00978 + +This code is based on versions of the AWQ implementation found in the following repositories: +* https://github.com/mit-han-lab/llm-awq +* https://github.com/casper-hansen/AutoAWQ +""" + +import os +import torch +import torch.nn as nn + +from transformers import AutoModelForCausalLM, AutoConfig +from transformers.models.bloom.modeling_bloom import BloomGelu +from transformers.models.llama.modeling_llama import LlamaRMSNorm +from transformers.activations import GELUActivation + + +class ScaledActivation(nn.Module): + """ + ScaledActivation module wraps an existing activation function and applies a + scale factor to its output. + + Args: + module (nn.Module): The activation function to be scaled. + scales (torch.Tensor): A tensor of size (num_features,) containing the initial + scale factors for each feature. + + Returns: + torch.Tensor: The scaled output of the activation function. + """ + + def __init__(self, module, scales): + super().__init__() + self.act = module + self.scales = nn.Parameter(scales.data) + + def forward(self, x): + return self.act(x) / self.scales.view(1, 1, -1).to(x.device) + + +def set_op_by_name(layer, name, new_module): + """ + Set the new module for given module's name. + + Args: + layer (nn.Module): The layer in which to replace the submodule. + name (str): The path to the submodule to be replaced, using dot notation + to access nested modules. + new_module (nn.Module): The new module to replace the existing one. + """ + levels = name.split(".") + if len(levels) > 1: + mod_ = layer + for l_idx in range(len(levels) - 1): + if levels[l_idx].isdigit(): + mod_ = mod_[int(levels[l_idx])] + else: + mod_ = getattr(mod_, levels[l_idx]) + setattr(mod_, levels[-1], new_module) + else: + setattr(layer, name, new_module) + + +def get_op_by_name(module, op_name): + """ + Retrieves a submodule within a given layer based on its name. + + Args: + module (nn.Module): The layer containing the submodule to find. + op_name (str): The name of the submodule. + + Returns: + nn.Module: The requested submodule found within the given layer. + + Raises: + ValueError: If the specified submodule cannot be found within the layer. + """ + for name, m in module.named_modules(): + if name == op_name: + return m + raise ValueError(f"Cannot find op {op_name} in module {module}") + + +@torch.no_grad() +def scale_ln_fcs(ln, fcs, scales): + """ + Scales the weights of a LayerNorm and a list of fully-connected layers proportionally. + + Args: + ln (nn.LayerNorm): The LayerNorm module to be scaled. + fcs (List[nn.Linear]): A list of fully-connected layers to be scaled. + scales (torch.Tensor): A 1D tensor of size (num_features,). + """ + + if not isinstance(fcs, list): + fcs = [fcs] + + scales = scales.to(ln.weight.device) + + ln.weight.div_(scales) + if hasattr(ln, "bias") and ln.bias is not None: + ln.bias.div_(scales) + + for fc in fcs: + fc.weight.mul_(scales.view(1, -1)) + + for p in ln.parameters(): + assert torch.isnan(p).sum() == 0 + for fc in fcs: + for p in fc.parameters(): + assert torch.isnan(p).sum() == 0 + + +@torch.no_grad() +def scale_fc_fc(fc1, fc2, scales): + """ + Scales the weights of two fully-connected layers in a specific pattern. + + Args: + fc1 (nn.Linear): The first fully-connected layer to be scaled. + fc2 (nn.Linear): The second fully-connected layer to be scaled. + scales (torch.Tensor): A 1D tensor of size (num_features,). + """ + assert isinstance(fc1, nn.Linear) + assert isinstance(fc2, nn.Linear) + + scales = scales.to(fc1.weight.device) + + fc1.weight[-scales.size(0):].div_(scales.view(-1, 1)) + if fc1.bias is not None: + fc1.bias.div_(scales.view(-1)) + + fc2.weight.mul_(scales.view(1, -1)) + + for p in fc1.parameters(): + assert torch.isnan(p).sum() == 0 + for p in fc2.parameters(): + assert torch.isnan(p).sum() == 0 + + +@torch.no_grad() +def scale_gelu_fc(gelu, fc, scales): + """ + Scales the weight of a GELU activation and a fully-connected layer proportionally. + + Args: + gelu (Union[nn.GELU, BloomGelu, GELUActivation]): The GELU activation module to be scaled. + fc (nn.Linear): The fully-connected layer to be scaled. + scales (torch.Tensor): A 1D tensor of size (num_features,). + + Raises: + TypeError: If the `gelu` module is not of type `nn.GELU`, `BloomGelu`, or `GELUActivation`. + TypeError: If the `fc` module is not of type `nn.Linear`. + """ + assert isinstance(gelu, (nn.GELU, BloomGelu, GELUActivation)) + assert isinstance(fc, nn.Linear) + + fc.weight.mul_(scales.view(1, -1).to(fc.weight.device)) + + for p in fc.parameters(): + assert torch.isnan(p).sum() == 0 + + +def apply_scale(module, scales_list, input_feat_dict=None): + """ + Applies different scaling strategies to layers based on their type and hierarchy within a given module. + + Args: + module (nn.Module): The module containing the layers to be scaled. + scales_list (List[Tuple[str, List[str], torch.Tensor]]): A list of tuples containing: + * prev_op_name (str): The name of the preceding operation or module, + relative to which the layers to be scaled are located. + * layer_names (List[str]): A list of names of the layers to be scaled, relative to the preceding operation. + * scales (torch.Tensor): A 1D tensor of size (num_features,) containing the scaling factors for each feature. + input_feat_dict (Optional[Dict[str, torch.Tensor]]): A dictionary mapping layer names to their corresponding + input features (optional). + """ + for prev_op_name, layer_names, scales in scales_list: + prev_op = get_op_by_name(module, prev_op_name) + layers = [get_op_by_name(module, name) for name in layer_names] + + prev_op.cuda() + for layer in layers: + layer.cuda() + scales.cuda() + + if isinstance(prev_op, nn.Linear): + assert len(layers) == 1 + scale_fc_fc(prev_op, layers[0], scales) + elif isinstance(prev_op, (nn.LayerNorm, LlamaRMSNorm)) or "rmsnorm" in str(prev_op.__class__).lower(): + scale_ln_fcs(prev_op, layers, scales) + elif isinstance(prev_op, (nn.GELU, BloomGelu, GELUActivation)): + new_module = ScaledActivation(prev_op, scales) + set_op_by_name(module, prev_op_name, new_module) + scale_gelu_fc(prev_op, layers[0], scales) + else: + raise NotImplementedError(f"prev_op {type(prev_op)} not supported yet!") + + # apply the scaling to input feat if given; prepare it for clipping + if input_feat_dict is not None: + for layer_name in layer_names: + inp = input_feat_dict[layer_name] + inp.div_(scales.view(1, -1).to(inp.device)) + + prev_op.cpu() + for layer in layers: + layer.cpu() + scales.cpu() + + +@torch.no_grad() +def apply_clip(module, clip_list): + """ + Applies element-wise clipping to the weight of a specific layer within a given module. + + Args: + module (nn.Module): The module containing the layer to be clipped. + clip_list (List[Tuple[str, torch.Tensor]]): A list of tuples containing: + * name (str): The name of the layer to be clipped, relative to the root of the module. + * max_val (torch.Tensor): A 1D or 2D tensor defining the upper bound for each element of the layer's weight. + """ + for name, max_val in clip_list: + layer = get_op_by_name(module, name) + layer.cuda() + max_val = max_val.to(layer.weight.device) + org_shape = layer.weight.shape + layer.weight.data = layer.weight.data.reshape(*max_val.shape[:2], -1) + layer.weight.data = torch.clamp(layer.weight.data, -max_val, max_val) + layer.weight.data = layer.weight.data.reshape(org_shape) + layer.cpu() + + +def add_scale_weights(model_path, scale_path, tmp_path): + """ + Adds pre-computed Activation Weight Quantization (AWQ) results to a model, + including scaling factors and clipping bounds. + + Args: + model_path (str): Path to the pre-trained model to be equipped with AWQ. + scale_path (str): Path to the AWQ scale factors (.pt file). + tmp_path (str): Path to the temporary directory where the equipped model will be saved. + """ + config = AutoConfig.from_pretrained(model_path, trust_remote_code=True) + model = AutoModelForCausalLM.from_pretrained( + model_path, config=config, trust_remote_code=True + ) + model.eval() + awq_results = torch.load(str(scale_path), map_location="cpu") + apply_scale(model, awq_results["scale"]) + apply_clip(model, awq_results["clip"]) + model.save_pretrained(str(tmp_path)) + os.system(f"cp {str(model_path)}/tokenizer* {str(tmp_path)}") diff --git a/awq-py/requirements.txt b/awq-py/requirements.txt new file mode 100644 index 000000000..5fe604329 --- /dev/null +++ b/awq-py/requirements.txt @@ -0,0 +1,2 @@ +torch>=2.0.0 +transformers>=4.32.0 diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py index 303d08170..3557a825e 100755 --- a/convert-hf-to-gguf.py +++ b/convert-hf-to-gguf.py @@ -46,7 +46,7 @@ class Model: self.part_names = self._get_part_names() self.hparams = Model.load_hparams(self.dir_model) self.model_arch = self._get_model_architecture() - self.gguf_writer = gguf.GGUFWriter(fname_out, gguf.MODEL_ARCH_NAMES[self.model_arch], endianess=self.endianess) + self.gguf_writer = gguf.GGUFWriter(fname_out, gguf.MODEL_ARCH_NAMES[self.model_arch], endianess=self.endianess, use_temp_file=False) def set_vocab(self): self._set_vocab_gpt2() @@ -59,7 +59,7 @@ class Model: from safetensors import safe_open ctx = cast(ContextManager[Any], safe_open(self.dir_model / part_name, framework="pt", device="cpu")) else: - ctx = contextlib.nullcontext(torch.load(str(self.dir_model / part_name), map_location="cpu", mmap=True, weights_only=True)) + ctx = contextlib.nullcontext(torch.load(str(self.dir_model / part_name), map_location="cpu", weights_only=True)) with ctx as model_part: for name in model_part.keys(): @@ -182,6 +182,8 @@ class Model: return QwenModel if model_architecture == "MixtralForCausalLM": return MixtralModel + if model_architecture == "GPT2LMHeadModel": + return GPT2Model if model_architecture == "PhiForCausalLM": return Phi2Model if model_architecture == "PlamoForCausalLM": @@ -225,6 +227,8 @@ class Model: return gguf.MODEL_ARCH.QWEN if arch == "MixtralForCausalLM": return gguf.MODEL_ARCH.LLAMA + if arch == "GPT2LMHeadModel": + return gguf.MODEL_ARCH.GPT2 if arch == "PhiForCausalLM": return gguf.MODEL_ARCH.PHI2 if arch == "PlamoForCausalLM": @@ -464,7 +468,11 @@ class MPTModel(Model): data = data_torch.squeeze().numpy() # map tensor names - new_name = tensor_map.get_name(name, try_suffixes=(".weight", ".bias")) + if "scales" in name: + new_name = tensor_map.get_name(name, try_suffixes=(".weight", ".bias", ".scales")) + new_name = new_name.replace("scales", "act.scales") + else: + new_name = tensor_map.get_name(name, try_suffixes=(".weight", ".bias")) if new_name is None: print(f"Can not map tensor {name!r}") sys.exit() @@ -989,6 +997,68 @@ class QwenModel(Model): self.gguf_writer.add_tensor(new_name, data) +class GPT2Model(Model): + def set_gguf_parameters(self): + self.gguf_writer.add_name(self.dir_model.name) + self.gguf_writer.add_block_count(self.hparams["n_layer"]) + self.gguf_writer.add_context_length(self.hparams["n_ctx"]) + self.gguf_writer.add_embedding_length(self.hparams["n_embd"]) + self.gguf_writer.add_feed_forward_length(4 * self.hparams["n_embd"]) + self.gguf_writer.add_head_count(self.hparams["n_head"]) + self.gguf_writer.add_layer_norm_eps(self.hparams["layer_norm_epsilon"]) + self.gguf_writer.add_file_type(self.ftype) + + def write_tensors(self): + block_count = self.hparams.get("n_layers", self.hparams.get("num_hidden_layers", self.hparams.get("n_layer"))) + tensor_map = gguf.get_tensor_name_map(self.model_arch, block_count) + + for name, data_torch in self.get_tensors(): + # we don't need these + if name.endswith((".attention.masked_bias", ".attention.bias", ".attention.rotary_emb.inv_freq", ".attn.bias")): + continue + + if name.endswith((".c_attn.weight", ".c_proj.weight", ".c_fc.weight", ".c_proj.weight")): + data_torch = data_torch.transpose(1, 0) + + old_dtype = data_torch.dtype + + # convert any unsupported data types to float32 + if data_torch.dtype not in (torch.float16, torch.float32): + data_torch = data_torch.to(torch.float32) + + data = data_torch.squeeze().numpy() + + # map tensor names + new_name = tensor_map.get_name(name, try_suffixes=(".weight", ".bias")) + if new_name is None: + print(f"Can not map tensor {name!r}") + sys.exit() + + n_dims = len(data.shape) + data_dtype = data.dtype + + # if f32 desired, convert any float16 to float32 + if self.ftype == 0 and data_dtype == np.float16: + data = data.astype(np.float32) + + # TODO: Why cant we use these float16 as-is? There should be not reason to store float16 as float32 + if self.ftype == 1 and data_dtype == np.float16 and n_dims == 1: + data = data.astype(np.float32) + + # if f16 desired, convert any float32 2-dim weight tensors to float16 + if self.ftype == 1 and data_dtype == np.float32 and name.endswith(".weight") and n_dims == 2: + data = data.astype(np.float16) + + print(f"{new_name}, n_dims = {n_dims}, {old_dtype} --> {data.dtype}") + + self.gguf_writer.add_tensor(new_name, data) + + # note: GPT2 output is tied to (same as) wte in original model + if new_name == "token_embd.weight": + print(f"output.weight, n_dims = {n_dims}, {old_dtype} --> {data.dtype}") + self.gguf_writer.add_tensor("output.weight", data) + + class Phi2Model(Model): def set_gguf_parameters(self): block_count = self.hparams["n_layer"] @@ -1095,6 +1165,9 @@ def parse_args() -> argparse.Namespace: "--vocab-only", action="store_true", help="extract only the vocab", ) + parser.add_argument( + "--awq-path", type=Path, default=None, + help="Path to scale awq cache file") parser.add_argument( "--outfile", type=Path, help="path to write to; default: based on input", @@ -1115,6 +1188,20 @@ def parse_args() -> argparse.Namespace: args = parse_args() dir_model = args.model + +if args.awq_path: + sys.path.insert(1, str(Path(__file__).parent / 'awq-py')) + from awq.apply_awq import add_scale_weights + tmp_model_path = args.model / "weighted_model" + dir_model = tmp_model_path + if tmp_model_path.is_dir(): + print(f"{tmp_model_path} exists as a weighted model.") + else: + tmp_model_path.mkdir(parents=True, exist_ok=True) + print("Saving new weighted model ...") + add_scale_weights(str(args.model), str(args.awq_path), str(tmp_model_path)) + print(f"Saved weighted model at {tmp_model_path}.") + if not dir_model.is_dir(): print(f'Error: {args.model} is not a directory', file=sys.stderr) sys.exit(1) diff --git a/convert.py b/convert.py index 1f0c4f2f4..c3f3fc0a1 100755 --- a/convert.py +++ b/convert.py @@ -1187,6 +1187,7 @@ def main(args_in: list[str] | None = None) -> None: # We currently only support Q8_0 output on little endian systems. output_choices.append("q8_0") parser = argparse.ArgumentParser(description="Convert a LLaMa model to a GGML compatible file") + parser.add_argument("--awq-path", type=Path, help="Path to scale awq cache file", default=None) parser.add_argument("--dump", action="store_true", help="don't convert, just show what's in the model") parser.add_argument("--dump-single", action="store_true", help="don't convert, just show what's in a single model file") parser.add_argument("--vocab-only", action="store_true", help="extract only the vocab") @@ -1200,6 +1201,19 @@ def main(args_in: list[str] | None = None) -> None: parser.add_argument("--padvocab", action="store_true", help="add pad tokens when model vocab expects more than tokenizer metadata provides") args = parser.parse_args(args_in) + if args.awq_path: + sys.path.insert(1, str(Path(__file__).parent / 'awq-py')) + from awq.apply_awq import add_scale_weights + tmp_model_path = args.model / "weighted_model" + if tmp_model_path.is_dir(): + print(f"{tmp_model_path} exists as a weighted model.") + else: + tmp_model_path.mkdir(parents=True, exist_ok=True) + print("Saving new weighted model ...") + add_scale_weights(str(args.model), str(args.awq_path), str(tmp_model_path)) + print(f"Saved weighted model at {tmp_model_path}.") + args.model = tmp_model_path + if args.dump_single: model_plus = lazy_load_file(args.model) do_dump_model(model_plus) diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 4cd87cdda..ae62cc575 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -120,6 +120,7 @@ class MODEL_TENSOR(IntEnum): FFN_GATE = auto() FFN_DOWN = auto() FFN_UP = auto() + FFN_ACT = auto() FFN_GATE_EXP = auto() FFN_DOWN_EXP = auto() FFN_UP_EXP = auto() @@ -169,6 +170,7 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = { MODEL_TENSOR.FFN_GATE: "blk.{bid}.ffn_gate", MODEL_TENSOR.FFN_DOWN: "blk.{bid}.ffn_down", MODEL_TENSOR.FFN_UP: "blk.{bid}.ffn_up", + MODEL_TENSOR.FFN_ACT: "blk.{bid}.ffn", MODEL_TENSOR.FFN_GATE_EXP: "blk.{bid}.ffn_gate.{xid}", MODEL_TENSOR.FFN_DOWN_EXP: "blk.{bid}.ffn_down.{xid}", MODEL_TENSOR.FFN_UP_EXP: "blk.{bid}.ffn_up.{xid}", @@ -269,6 +271,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.FFN_NORM, MODEL_TENSOR.FFN_DOWN, MODEL_TENSOR.FFN_UP, + MODEL_TENSOR.FFN_ACT, ], MODEL_ARCH.GPTJ: [ MODEL_TENSOR.TOKEN_EMBD, @@ -367,7 +370,16 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.FFN_UP, ], MODEL_ARCH.GPT2: [ - # TODO + MODEL_TENSOR.TOKEN_EMBD, + MODEL_TENSOR.POS_EMBD, + MODEL_TENSOR.OUTPUT_NORM, + MODEL_TENSOR.OUTPUT, + MODEL_TENSOR.ATTN_NORM, + MODEL_TENSOR.ATTN_QKV, + MODEL_TENSOR.ATTN_OUT, + MODEL_TENSOR.FFN_NORM, + MODEL_TENSOR.FFN_DOWN, + MODEL_TENSOR.FFN_UP, ], MODEL_ARCH.PHI2: [ MODEL_TENSOR.TOKEN_EMBD, diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 446c6b688..80c1d5449 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -17,6 +17,7 @@ class TensorNameMap: "tok_embeddings", # llama-pth "embeddings.word_embeddings", # bert "language_model.embedding.word_embeddings", # persimmon + "wte", # gpt2 "transformer.embd.wte", # phi2 ), @@ -34,6 +35,7 @@ class TensorNameMap: MODEL_TENSOR.POS_EMBD: ( "transformer.wpe", # gpt2 "embeddings.position_embeddings", # bert + "wpe", # gpt2 ), # Output @@ -53,7 +55,7 @@ class TensorNameMap: "norm", # llama-pth "embeddings.LayerNorm", # bert "transformer.norm_f", # mpt - "ln_f", # refact bloom qwen + "ln_f", # refact bloom qwen gpt2 "language_model.encoder.final_layernorm", # persimmon "lm_head.ln", # phi2 ), @@ -78,6 +80,7 @@ class TensorNameMap: "encoder.layer.{bid}.attention.output.LayerNorm", # bert "language_model.encoder.layers.{bid}.input_layernorm", # persimmon "model.layers.{bid}.ln1", # yi + "h.{bid}.ln_1", # gpt2 "transformer.h.{bid}.ln", # phi2 "model.layers.layers.{bid}.norm", # plamo ), @@ -95,6 +98,7 @@ class TensorNameMap: "transformer.h.{bid}.self_attention.query_key_value", # falcon "h.{bid}.self_attention.query_key_value", # bloom "language_model.encoder.layers.{bid}.self_attention.query_key_value", # persimmon + "h.{bid}.attn.c_attn", # gpt2 "transformer.h.{bid}.mixer.Wqkv", # phi2 ), @@ -137,6 +141,7 @@ class TensorNameMap: "encoder.layer.{bid}.attention.output.dense", # bert "transformer.h.{bid}.attn.out_proj", # gpt-j "language_model.encoder.layers.{bid}.self_attention.dense", # persimmon + "h.{bid}.attn.c_proj", # gpt2 "transformer.h.{bid}.mixer.out_proj", # phi2 "model.layers.layers.{bid}.self_attn.o_proj", # plamo ), @@ -159,6 +164,7 @@ class TensorNameMap: "encoder.layer.{bid}.output.LayerNorm", # bert "language_model.encoder.layers.{bid}.post_attention_layernorm", # persimmon "model.layers.{bid}.ln2", # yi + "h.{bid}.ln_2", # gpt2 ), MODEL_TENSOR.FFN_GATE_INP: ( @@ -179,6 +185,7 @@ class TensorNameMap: "transformer.h.{bid}.mlp.fc_in", # gpt-j "language_model.encoder.layers.{bid}.mlp.dense_h_to_4h", # persimmon "transformer.h.{bid}.mlp.w1", # qwen + "h.{bid}.mlp.c_fc", # gpt2 "transformer.h.{bid}.mlp.fc1", # phi2 "model.layers.layers.{bid}.mlp.up_proj", # plamo ), @@ -188,6 +195,11 @@ class TensorNameMap: "model.layers.{bid}.block_sparse_moe.experts.{xid}.w3", # mixtral ), + # AWQ-activation gate + MODEL_TENSOR.FFN_ACT: ( + "transformer.blocks.{bid}.ffn.act", # mpt + ), + # Feed-forward gate MODEL_TENSOR.FFN_GATE: ( "model.layers.{bid}.mlp.gate_proj", # llama-hf refact @@ -213,6 +225,7 @@ class TensorNameMap: "encoder.layer.{bid}.output.dense", # bert "transformer.h.{bid}.mlp.fc_out", # gpt-j "language_model.encoder.layers.{bid}.mlp.dense_4h_to_h", # persimmon + "h.{bid}.mlp.c_proj", # gpt2 "transformer.h.{bid}.mlp.fc2", # phi2 "model.layers.layers.{bid}.mlp.down_proj", # plamo ), diff --git a/llama.cpp b/llama.cpp index 4aa59c4c0..68c7cced6 100644 --- a/llama.cpp +++ b/llama.cpp @@ -354,6 +354,7 @@ enum llm_tensor { LLM_TENSOR_FFN_GATE, LLM_TENSOR_FFN_DOWN, LLM_TENSOR_FFN_UP, + LLM_TENSOR_FFN_ACT, LLM_TENSOR_FFN_DOWN_EXP, LLM_TENSOR_FFN_GATE_EXP, LLM_TENSOR_FFN_UP_EXP, @@ -422,6 +423,15 @@ static std::map> LLM_TENSOR_NAMES = LLM_ARCH_GPT2, { { LLM_TENSOR_TOKEN_EMBD, "token_embd" }, + { LLM_TENSOR_POS_EMBD, "position_embd" }, + { LLM_TENSOR_OUTPUT_NORM, "output_norm" }, + { LLM_TENSOR_OUTPUT, "output" }, + { LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" }, + { LLM_TENSOR_ATTN_QKV, "blk.%d.attn_qkv" }, + { LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" }, + { LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" }, + { LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" }, + { LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" }, }, }, { @@ -473,6 +483,7 @@ static std::map> LLM_TENSOR_NAMES = { LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" }, { LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" }, { LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" }, + { LLM_TENSOR_FFN_ACT, "blk.%d.ffn.act" }, }, }, { @@ -1254,6 +1265,10 @@ enum e_model { MODEL_40B, MODEL_65B, MODEL_70B, + MODEL_SMALL, + MODEL_MEDIUM, + MODEL_LARGE, + MODEL_XL, }; static const size_t kiB = 1024; @@ -1285,6 +1300,7 @@ struct llama_hparams { float f_clamp_kqv; float f_max_alibi_bias; + bool operator!=(const llama_hparams & other) const { if (this->vocab_only != other.vocab_only) return true; if (this->n_vocab != other.n_vocab) return true; @@ -1388,6 +1404,7 @@ struct llama_layer { // ff bias struct ggml_tensor * ffn_down_b; // b2 struct ggml_tensor * ffn_up_b; // b3 + struct ggml_tensor * ffn_act; }; struct llama_kv_cell { @@ -2548,18 +2565,22 @@ static std::string llama_model_ftype_name(llama_ftype ftype) { static const char * llama_model_type_name(e_model type) { switch (type) { - case MODEL_1B: return "1B"; - case MODEL_3B: return "3B"; - case MODEL_7B: return "7B"; - case MODEL_8B: return "8B"; - case MODEL_13B: return "13B"; - case MODEL_15B: return "15B"; - case MODEL_30B: return "30B"; - case MODEL_34B: return "34B"; - case MODEL_40B: return "40B"; - case MODEL_65B: return "65B"; - case MODEL_70B: return "70B"; - default: return "?B"; + case MODEL_1B: return "1B"; + case MODEL_3B: return "3B"; + case MODEL_7B: return "7B"; + case MODEL_8B: return "8B"; + case MODEL_13B: return "13B"; + case MODEL_15B: return "15B"; + case MODEL_30B: return "30B"; + case MODEL_34B: return "34B"; + case MODEL_40B: return "40B"; + case MODEL_65B: return "65B"; + case MODEL_70B: return "70B"; + case MODEL_SMALL: return "0.1B"; + case MODEL_MEDIUM: return "0.4B"; + case MODEL_LARGE: return "0.8B"; + case MODEL_XL: return "1.5B"; + default: return "?B"; } } @@ -2778,6 +2799,17 @@ static void llm_load_hparams( default: model.type = e_model::MODEL_UNKNOWN; } } break; + case LLM_ARCH_GPT2: + { + ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); + switch (hparams.n_layer) { + case 12: model.type = e_model::MODEL_SMALL; break; + case 24: model.type = e_model::MODEL_MEDIUM; break; + case 36: model.type = e_model::MODEL_LARGE; break; + case 48: model.type = e_model::MODEL_XL; break; + default: model.type = e_model::MODEL_UNKNOWN; + } + } break; default: (void)0; } @@ -3471,7 +3503,6 @@ static bool llm_load_tensors( case LLM_ARCH_MPT: { model.tok_embd = ml.create_tensor(ctx, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, GGML_BACKEND_CPU); - // output { ggml_backend_type backend_norm; @@ -3509,6 +3540,9 @@ static bool llm_load_tensors( layer.ffn_down = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}, backend_split); layer.ffn_up = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, backend_split); + + // AWQ ScaleActivation layer + layer.ffn_act = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, backend, false); } } break; case LLM_ARCH_STABLELM: @@ -3704,6 +3738,60 @@ static bool llm_load_tensors( layer.ffn_up = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, backend_split); } } break; + case LLM_ARCH_GPT2: + { + model.tok_embd = ml.create_tensor(ctx, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, GGML_BACKEND_CPU); + model.pos_embd = ml.create_tensor(ctx, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}, GGML_BACKEND_CPU); + + // output + { + ggml_backend_type backend_norm; + ggml_backend_type backend_output; + + if (n_gpu_layers > int(n_layer)) { + backend_norm = llama_backend_offload; + backend_output = llama_backend_offload_split; + } else { + backend_norm = GGML_BACKEND_CPU; + backend_output = GGML_BACKEND_CPU; + } + + model.output_norm = ml.create_tensor(ctx, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, backend_norm); + model.output_norm_b = ml.create_tensor(ctx, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}, backend_norm); + model.output = ml.create_tensor(ctx, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, backend_output); + } + + const uint32_t n_ff = hparams.n_ff; + + const int i_gpu_start = n_layer - n_gpu_layers; + + model.layers.resize(n_layer); + + for (uint32_t i = 0; i < n_layer; ++i) { + const ggml_backend_type backend = int(i) < i_gpu_start ? GGML_BACKEND_CPU : llama_backend_offload; // NOLINT + const ggml_backend_type backend_split = int(i) < i_gpu_start ? GGML_BACKEND_CPU : llama_backend_offload_split; // NOLINT + + auto & layer = model.layers[i]; + + layer.attn_norm = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, backend); + layer.attn_norm_b = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}, backend); + + layer.wqkv = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, backend_split); + layer.bqkv = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}, backend); + + layer.wo = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, backend_split); + layer.bo = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, backend); + + layer.ffn_norm = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, backend); + layer.ffn_norm_b = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}, backend); + + layer.ffn_down = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, backend_split); + layer.ffn_down_b = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, backend); + + layer.ffn_up = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, backend_split); + layer.ffn_up_b = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}, backend); + } + } break; default: throw std::runtime_error("unknown architecture"); } @@ -4039,6 +4127,7 @@ static struct ggml_tensor * llm_build_ffn( struct ggml_tensor * gate_b, struct ggml_tensor * down, struct ggml_tensor * down_b, + struct ggml_tensor * act_scales, llm_ffn_op_type type_op, llm_ffn_gate_type type_gate, const llm_build_cb & cb, @@ -4083,6 +4172,10 @@ static struct ggml_tensor * llm_build_ffn( { cur = ggml_gelu(ctx, cur); cb(cur, "ffn_gelu", il); + if (act_scales != NULL) { + cur = ggml_div(ctx, cur, act_scales); + cb(cur, "ffn_act", il); + } } break; case LLM_FFN_RELU: { @@ -4401,6 +4494,7 @@ struct llm_build_context { model.layers[il].ffn_up, NULL, model.layers[il].ffn_gate, NULL, model.layers[il].ffn_down, NULL, + NULL, LLM_FFN_SILU, LLM_FFN_PAR, cb, il); cb(cur, "ffn_out", il); } else { @@ -4580,6 +4674,7 @@ struct llm_build_context { model.layers[il].ffn_up, NULL, model.layers[il].ffn_gate, NULL, model.layers[il].ffn_down, NULL, + NULL, LLM_FFN_SILU, LLM_FFN_PAR, cb, il); cb(cur, "ffn_out", il); } @@ -4694,6 +4789,7 @@ struct llm_build_context { model.layers[il].ffn_up, NULL, NULL, NULL, model.layers[il].ffn_down, NULL, + NULL, LLM_FFN_GELU, LLM_FFN_SEQ, cb, il); cb(cur, "ffn_out", il); } @@ -4798,6 +4894,7 @@ struct llm_build_context { model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL, NULL, model.layers[il].ffn_down, model.layers[il].ffn_down_b, + NULL, LLM_FFN_GELU, LLM_FFN_SEQ, cb, il); cb(cur, "ffn_out", il); } @@ -5002,6 +5099,7 @@ struct llm_build_context { model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL, NULL, model.layers[il].ffn_down, model.layers[il].ffn_down_b, + NULL, LLM_FFN_RELU_SQR, LLM_FFN_SEQ, cb, il); cb(cur, "ffn_out", il); } @@ -5088,6 +5186,7 @@ struct llm_build_context { model.layers[il].ffn_up, NULL, model.layers[il].ffn_gate, NULL, model.layers[il].ffn_down, NULL, + NULL, LLM_FFN_SILU, LLM_FFN_PAR, cb, il); cb(cur, "ffn_out", il); } @@ -5183,6 +5282,7 @@ struct llm_build_context { model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL, NULL, model.layers[il].ffn_down, model.layers[il].ffn_down_b, + NULL, LLM_FFN_GELU, LLM_FFN_SEQ, cb, il); cb(cur, "ffn_out", il); } @@ -5268,11 +5368,11 @@ struct llm_build_context { NULL, LLM_NORM, cb, il); cb(cur, "ffn_norm", il); - cur = llm_build_ffn(ctx0, cur, model.layers[il].ffn_up, NULL, NULL, NULL, model.layers[il].ffn_down, NULL, + model.layers[il].ffn_act, LLM_FFN_GELU, LLM_FFN_SEQ, cb, il); cb(cur, "ffn_out", il); } @@ -5381,6 +5481,7 @@ struct llm_build_context { model.layers[il].ffn_up, NULL, model.layers[il].ffn_gate, NULL, model.layers[il].ffn_down, NULL, + NULL, LLM_FFN_SILU, LLM_FFN_PAR, cb, il); cb(cur, "ffn_out", il); } @@ -5493,6 +5594,7 @@ struct llm_build_context { model.layers[il].ffn_up, NULL, model.layers[il].ffn_gate, NULL, model.layers[il].ffn_down, NULL, + NULL, LLM_FFN_SILU, LLM_FFN_PAR, cb, il); cb(cur, "ffn_out", il); } @@ -5600,6 +5702,7 @@ struct llm_build_context { model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL, NULL, model.layers[il].ffn_down, model.layers[il].ffn_down_b, + NULL, LLM_FFN_GELU, LLM_FFN_SEQ, cb, il); cb(ffn_output, "ffn_out", il); } @@ -5703,6 +5806,7 @@ struct llm_build_context { model.layers[il].ffn_up, NULL, model.layers[il].ffn_gate, NULL, model.layers[il].ffn_down, NULL, + NULL, LLM_FFN_SILU, LLM_FFN_PAR, cb, il); cb(cur, "ffn_out", il); } @@ -5732,6 +5836,102 @@ struct llm_build_context { return gf; } + + struct ggml_cgraph * build_gpt2() { + struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, LLAMA_MAX_NODES, false); + + struct ggml_tensor * cur; + struct ggml_tensor * pos; + struct ggml_tensor * inpL; + + inpL = llm_build_inp_embd(ctx0, hparams, batch, model.tok_embd, cb); + cb(inpL, "inp_embd", -1); + + // inp_pos - contains the positions + struct ggml_tensor * inp_pos = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens); + cb(inp_pos, "inp_pos", -1); + + // KQ_mask (mask for 1 head, it will be broadcasted to all heads) + struct ggml_tensor * KQ_mask = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_kv, n_tokens, 1); + cb(KQ_mask, "KQ_mask", -1); + + pos = ggml_get_rows(ctx0, model.pos_embd, inp_pos); + cb(pos, "pos_embd", -1); + + inpL = ggml_add(ctx0, inpL, pos); + cb(inpL, "inpL", -1); + + for (int il = 0; il < n_layer; ++il) { + cur = llm_build_norm(ctx0, inpL, hparams, + model.layers[il].attn_norm, + model.layers[il].attn_norm_b, + LLM_NORM, cb, il); + cb(cur, "attn_norm", il); + + // self-attention + { + cur = ggml_mul_mat(ctx0, model.layers[il].wqkv, cur); + cb(cur, "wqkv", il); + + cur = ggml_add(ctx0, cur, model.layers[il].bqkv); + cb(cur, "bqkv", il); + + struct ggml_tensor * Qcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd, n_tokens, cur->nb[1], 0*sizeof(float)*(n_embd))); + struct ggml_tensor * Kcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd))); + struct ggml_tensor * Vcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd + n_embd_gqa))); + + cb(Qcur, "Qcur", il); + cb(Kcur, "Kcur", il); + cb(Vcur, "Vcur", il); + + Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens); + + llm_build_kv_store(ctx0, hparams, kv_self, gf, Kcur, Vcur, n_ctx, n_tokens, kv_head, cb, il); + + cur = llm_build_kqv(ctx0, model, hparams, kv_self, + model.layers[il].wo, model.layers[il].bo, + Qcur, KQ_mask, n_ctx, n_tokens, n_kv, -1.0f, 1.0f/sqrtf(float(n_embd_head)), cb, il); + cb(cur, "kqv_out", il); + } + + // add the input + struct ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpL); + cb(ffn_inp, "ffn_inp", il); + + // FF + { + cur = llm_build_norm(ctx0, ffn_inp, hparams, + model.layers[il].ffn_norm, + model.layers[il].ffn_norm_b, + LLM_NORM, cb, il); + cb(cur, "ffn_norm", il); + + cur = llm_build_ffn(ctx0, cur, + model.layers[il].ffn_up, model.layers[il].ffn_up_b, + NULL, NULL, + model.layers[il].ffn_down, model.layers[il].ffn_down_b, + NULL, + LLM_FFN_GELU, LLM_FFN_SEQ, cb, il); + cb(cur, "ffn_out", il); + } + + inpL = ggml_add(ctx0, cur, ffn_inp); + cb(inpL, "l_out", il); + } + + cur = llm_build_norm(ctx0, inpL, hparams, + model.output_norm, + model.output_norm_b, + LLM_NORM, cb, -1); + cb(cur, "result_norm", -1); + + cur = ggml_mul_mat(ctx0, model.output, cur); + cb(cur, "result_output", -1); + + ggml_build_forward_expand(gf, cur); + + return gf; + } }; // @@ -5887,6 +6087,7 @@ static const std::unordered_map k_offload_map { "ffn_gate", OFFLOAD_FUNC }, { "ffn_gate_b", OFFLOAD_FUNC }, { "ffn_gate_par", OFFLOAD_FUNC }, + { "ffn_act", OFFLOAD_FUNC }, { "ffn_down", OFFLOAD_FUNC }, { "ffn_down_b", OFFLOAD_FUNC }, { "ffn_out", OFFLOAD_FUNC }, @@ -6246,6 +6447,10 @@ static struct ggml_cgraph * llama_build_graph( { result = llm.build_plamo(); } break; + case LLM_ARCH_GPT2: + { + result = llm.build_gpt2(); + } break; default: GGML_ASSERT(false); } diff --git a/models/ggml-vocab-gpt2.gguf b/models/ggml-vocab-gpt2.gguf new file mode 100644 index 000000000..1fbc72c1e Binary files /dev/null and b/models/ggml-vocab-gpt2.gguf differ diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index e42237c7a..9b5e69d13 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -41,6 +41,7 @@ llama_test_executable (test-tokenizer-1-stablelm-3b-4e1t test-tokenizer-1-bpe.cp llama_test_executable (test-tokenizer-1-gpt-neox test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-neox.gguf) llama_test_executable (test-tokenizer-1-refact test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf) llama_test_executable (test-tokenizer-1-starcoder test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf) +llama_test_executable (test-tokenizer-1-gpt2 test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt2.gguf) # llama_test_executable (test-tokenizer-1-bloom test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bloom.gguf) # BIG llama_build_and_test_executable(test-grammar-parser.cpp)