Upload Transformer

LMConfig.py

@@ -0,0 +1,33 @@
+from transformers import PretrainedConfig
+from typing import List
+
+
+class LMConfig(PretrainedConfig):
+    model_type = "babylm"
+
+    def __init__(
+            self,
+            dim: int = 512,
+            n_layers: int = 8,
+            n_heads: int = 8,
+            n_kv_heads: int = None,
+            vocab_size: int = 64000,
+            hidden_dim: int = None,
+            multiple_of: int = 64,
+            norm_eps: float = 1e-5,
+            max_seq_len: int = 512,
+            dropout: float = 0.0,
+            **kwargs,
+    ):
+
+        self.dim = dim
+        self.n_layers = n_layers
+        self.n_heads = n_heads
+        self.n_kv_heads = n_kv_heads
+        self.vocab_size = vocab_size
+        self.hidden_dim = hidden_dim
+        self.multiple_of = multiple_of
+        self.norm_eps = norm_eps
+        self.max_seq_len = max_seq_len
+        self.dropout = dropout
+        super().__init__(**kwargs)

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "babylm",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w2",
+    "wo",
+    "w1",
+    "wq",
+    "output",
+    "w3",
+    "wk",
+    "wv"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c754e66921267847a12d761fa2e408d9ec205459c6c2a30a54f97ba872ba3c
+size 4601272

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.41.1"
+}

model.py

@@ -0,0 +1,416 @@
+import math
+import struct
+import inspect
+from .LMConfig import LMConfig
+from typing import Any, Optional, Tuple
+import numpy as np
+import torch
+import torch.nn.functional as F
+from torch import nn
+from transformers import PreTrainedModel
+
+
+class RMSNorm(torch.nn.Module):
+    def __init__(self, dim: int, eps: float):
+        super().__init__()
+        self.eps = eps
+        self.weight = nn.Parameter(torch.ones(dim))
+
+    def _norm(self, x):
+        return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
+
+    def forward(self, x):
+        output = self._norm(x.float()).type_as(x)
+        return output * self.weight
+
+
+def precompute_freqs_cis(dim: int, end: int, theta: float = 10000.0):
+    freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim))
+    t = torch.arange(end, device=freqs.device)  # type: ignore
+    freqs = torch.outer(t, freqs).float()  # type: ignore
+    freqs_cos = torch.cos(freqs)  # real part
+    freqs_sin = torch.sin(freqs)  # imaginary part
+    return freqs_cos, freqs_sin
+
+
+def reshape_for_broadcast(freqs_cis: torch.Tensor, x: torch.Tensor):
+    ndim = x.ndim
+    assert 0 <= 1 < ndim
+    assert freqs_cis.shape == (x.shape[1], x.shape[-1])
+    shape = [d if i == 1 or i == ndim - 1 else 1 for i, d in enumerate(x.shape)]
+    return freqs_cis.view(shape)
+
+
+def apply_rotary_emb(
+        xq: torch.Tensor,
+        xk: torch.Tensor,
+        freqs_cos: torch.Tensor,
+        freqs_sin: torch.Tensor
+) -> Tuple[torch.Tensor, torch.Tensor]:
+    # reshape xq and xk to match the complex representation
+    xq_r, xq_i = xq.float().reshape(xq.shape[:-1] + (-1, 2)).unbind(-1)
+    xk_r, xk_i = xk.float().reshape(xk.shape[:-1] + (-1, 2)).unbind(-1)
+
+    # reshape freqs_cos and freqs_sin for broadcasting
+    freqs_cos = reshape_for_broadcast(freqs_cos, xq_r)
+    freqs_sin = reshape_for_broadcast(freqs_sin, xq_r)
+
+    # apply rotation using real numbers
+    xq_out_r = xq_r * freqs_cos - xq_i * freqs_sin
+    xq_out_i = xq_r * freqs_sin + xq_i * freqs_cos
+    xk_out_r = xk_r * freqs_cos - xk_i * freqs_sin
+    xk_out_i = xk_r * freqs_sin + xk_i * freqs_cos
+
+    # flatten last two dimensions
+    xq_out = torch.stack([xq_out_r, xq_out_i], dim=-1).flatten(3)
+    xk_out = torch.stack([xk_out_r, xk_out_i], dim=-1).flatten(3)
+
+    return xq_out.type_as(xq), xk_out.type_as(xk)
+
+
+def repeat_kv(x: torch.Tensor, n_rep: int) -> torch.Tensor:
+    """torch.repeat_interleave(x, dim=2, repeats=n_rep)"""
+    bs, slen, n_kv_heads, head_dim = x.shape
+    if n_rep == 1:
+        return x
+    return (
+        x[:, :, :, None, :]
+        .expand(bs, slen, n_kv_heads, n_rep, head_dim)
+        .reshape(bs, slen, n_kv_heads * n_rep, head_dim)
+    )
+
+
+class Attention(nn.Module):
+    def __init__(self, args: LMConfig):
+        super().__init__()
+        self.n_kv_heads = args.n_heads if args.n_kv_heads is None else args.n_kv_heads
+        assert args.n_heads % self.n_kv_heads == 0
+        model_parallel_size = 1
+        self.n_local_heads = args.n_heads // model_parallel_size
+        self.n_local_kv_heads = self.n_kv_heads // model_parallel_size
+        self.n_rep = self.n_local_heads // self.n_local_kv_heads
+        self.head_dim = args.dim // args.n_heads
+        self.wq = nn.Linear(args.dim, args.n_heads * self.head_dim, bias=False)
+        self.wk = nn.Linear(args.dim, self.n_kv_heads * self.head_dim, bias=False)
+        self.wv = nn.Linear(args.dim, self.n_kv_heads * self.head_dim, bias=False)
+        self.wo = nn.Linear(args.n_heads * self.head_dim, args.dim, bias=False)
+        self.attn_dropout = nn.Dropout(args.dropout)
+        self.resid_dropout = nn.Dropout(args.dropout)
+        self.dropout = args.dropout
+
+        # use flash attention or a manual implementation?
+        self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention')
+        if not self.flash:
+            print("WARNING: using slow attention. Flash Attention requires PyTorch >= 2.0")
+            mask = torch.full((1, 1, args.max_seq_len, args.max_seq_len), float("-inf"))
+            mask = torch.triu(mask, diagonal=1)
+            self.register_buffer("mask", mask)
+
+    def forward(
+            self,
+            x: torch.Tensor,
+            freqs_cos: torch.Tensor,
+            freqs_sin: torch.Tensor,
+    ):
+        bsz, seqlen, _ = x.shape
+
+        # QKV
+        xq, xk, xv = self.wq(x), self.wk(x), self.wv(x)
+        xq = xq.view(bsz, seqlen, self.n_local_heads, self.head_dim)
+        xk = xk.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
+        xv = xv.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
+
+        # RoPE relative positional embeddings
+        xq, xk = apply_rotary_emb(xq, xk, freqs_cos, freqs_sin)
+
+        # grouped multiquery attention: expand out keys and values
+        xk = repeat_kv(xk, self.n_rep)  # (bs, seqlen, n_local_heads, head_dim)
+        xv = repeat_kv(xv, self.n_rep)  # (bs, seqlen, n_local_heads, head_dim)
+
+        # make heads into a batch dimension
+        xq = xq.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
+        xk = xk.transpose(1, 2)
+        xv = xv.transpose(1, 2)
+
+        # flash implementation
+        if self.flash:
+            output = torch.nn.functional.scaled_dot_product_attention(xq, xk, xv, attn_mask=None,
+                                                                      dropout_p=self.dropout if self.training else 0.0,
+                                                                      is_causal=True)
+        else:
+            # manual implementation
+            scores = torch.matmul(xq, xk.transpose(2, 3)) / math.sqrt(self.head_dim)
+            assert hasattr(self, 'mask')
+            scores = scores + self.mask[:, :, :seqlen, :seqlen]  # (bs, n_local_heads, seqlen, cache_len + seqlen)
+            scores = F.softmax(scores.float(), dim=-1).type_as(xq)
+            scores = self.attn_dropout(scores)
+            output = torch.matmul(scores, xv)  # (bs, n_local_heads, seqlen, head_dim)
+
+        # restore time as batch dimension and concat heads
+        output = output.transpose(1, 2).contiguous().view(bsz, seqlen, -1)
+
+        # final projection into the residual stream
+        output = self.wo(output)
+        output = self.resid_dropout(output)
+        return output
+
+
+class FeedForward(nn.Module):
+    def __init__(self, dim: int, hidden_dim: int, multiple_of: int, dropout: float):
+        super().__init__()
+        if hidden_dim is None:
+            hidden_dim = 4 * dim
+            hidden_dim = int(2 * hidden_dim / 3)
+            hidden_dim = multiple_of * ((hidden_dim + multiple_of - 1) // multiple_of)
+        self.w1 = nn.Linear(dim, hidden_dim, bias=False)
+        self.w2 = nn.Linear(hidden_dim, dim, bias=False)
+        self.w3 = nn.Linear(dim, hidden_dim, bias=False)
+        self.dropout = nn.Dropout(dropout)
+
+    def forward(self, x):
+        return self.dropout(self.w2(F.silu(self.w1(x)) * self.w3(x)))
+
+
+class TransformerBlock(nn.Module):
+    def __init__(self, layer_id: int, args: LMConfig):
+        super().__init__()
+        self.n_heads = args.n_heads
+        self.dim = args.dim
+        self.head_dim = args.dim // args.n_heads
+        self.attention = Attention(args)
+        self.feed_forward = FeedForward(
+            dim=args.dim,
+            hidden_dim=args.hidden_dim,
+            multiple_of=args.multiple_of,
+            dropout=args.dropout,
+        )
+        self.layer_id = layer_id
+        self.attention_norm = RMSNorm(args.dim, eps=args.norm_eps)
+        self.ffn_norm = RMSNorm(args.dim, eps=args.norm_eps)
+
+    def forward(self, x, freqs_cos, freqs_sin):
+        h = x + self.attention.forward(self.attention_norm(x), freqs_cos, freqs_sin)
+        out = h + self.feed_forward.forward(self.ffn_norm(h))
+        return out
+
+
+class Transformer(PreTrainedModel):
+    config_class = LMConfig
+
+    last_loss: Optional[torch.Tensor]
+
+    def __init__(self, params: LMConfig = None):
+        super().__init__(params)
+        if not params:
+            params = LMConfig()
+        self.params = params
+        self.vocab_size = params.vocab_size
+        self.n_layers = params.n_layers
+
+        self.tok_embeddings = nn.Embedding(params.vocab_size, params.dim)
+        self.dropout = nn.Dropout(params.dropout)
+        self.layers = torch.nn.ModuleList()
+        for layer_id in range(params.n_layers):
+            self.layers.append(TransformerBlock(layer_id, params))
+        self.norm = RMSNorm(params.dim, eps=params.norm_eps)
+        self.output = nn.Linear(params.dim, params.vocab_size, bias=False)
+
+        # share the unembedding parameters with the embedding parameters
+        self.tok_embeddings.weight = self.output.weight  # https://paperswithcode.com/method/weight-tying
+
+        # some useful precompute for the RoPE relative positional embeddings
+        freqs_cos, freqs_sin = precompute_freqs_cis(self.params.dim // self.params.n_heads, self.params.max_seq_len)
+        self.register_buffer("freqs_cos", freqs_cos, persistent=False)
+        self.register_buffer("freqs_sin", freqs_sin, persistent=False)
+
+        # init all weights
+        self.apply(self._init_weights)
+        # apply special scaled init to the residual projections, per GPT-2 paper
+        for pn, p in self.named_parameters():
+            if pn.endswith('w3.weight') or pn.endswith('wo.weight'):
+                torch.nn.init.normal_(p, mean=0.0, std=0.02 / math.sqrt(2 * params.n_layers))
+
+        # Initialize attribute for the loss of the last forward call. This will be set if the forward is called with a targets tensor.
+        self.last_loss = None
+
+    def _init_weights(self, module):
+        if isinstance(module, nn.Linear):
+            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
+            if module.bias is not None:
+                torch.nn.init.zeros_(module.bias)
+        elif isinstance(module, nn.Embedding):
+            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
+
+    def forward(self, tokens: Optional[torch.Tensor] = None,
+                targets: Optional[torch.Tensor] = None, **keyargs) -> torch.Tensor:
+        if 'input_ids' in keyargs:
+            tokens = keyargs['input_ids']
+        if 'attention_mask' in keyargs:
+            targets = keyargs['attention_mask']
+
+        _bsz, seqlen = tokens.shape
+        h = self.tok_embeddings(tokens)
+        h = self.dropout(h)
+        freqs_cos = self.freqs_cos[:seqlen]
+        freqs_sin = self.freqs_sin[:seqlen]
+
+        for layer in self.layers:
+            h = layer(h, freqs_cos, freqs_sin)
+        h = self.norm(h)
+
+        if targets is not None:
+            # if we are given some desired targets also calculate the loss
+            logits = self.output(h)
+            self.last_loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1)
+        else:
+            # inference-time mini-optimization: only forward the output on the very last position
+            logits = self.output(h[:, [-1], :])  # note: using list [-1] to preserve the time dim
+            self.last_loss = None
+
+        return logits
+
+    def configure_optimizers(self, weight_decay, learning_rate, device_type):
+        # start with all of the candidate parameters
+        param_dict = {pn: p for pn, p in self.named_parameters()}
+        # filter out those that do not require grad
+        param_dict = {pn: p for pn, p in param_dict.items() if p.requires_grad}
+        # create optim groups. Any parameters that is 2D will be weight decayed, otherwise no.
+        # i.e. all weight tensors in matmuls + embeddings decay, all biases and layernorms don't.
+        decay_params = [p for n, p in param_dict.items() if p.dim() >= 2]
+        nodecay_params = [p for n, p in param_dict.items() if p.dim() < 2]
+        optim_groups = [
+            {'params': decay_params, 'weight_decay': weight_decay},
+            {'params': nodecay_params, 'weight_decay': 0.0}
+        ]
+        num_decay_params = sum(p.numel() for p in decay_params)
+        num_nodecay_params = sum(p.numel() for p in nodecay_params)
+        print(f"num decayed parameter tensors: {len(decay_params)}, with {num_decay_params:,} parameters")
+        print(f"num non-decayed parameter tensors: {len(nodecay_params)}, with {num_nodecay_params:,} parameters")
+        # Create AdamW optimizer and use the fused version if it is available
+        fused_available = 'fused' in inspect.signature(torch.optim.AdamW).parameters
+        use_fused = fused_available and device_type == 'cuda'
+        extra_args = dict(fused=True) if use_fused else dict()
+        optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=(0.9, 0.999), **extra_args)
+        print(f"using fused AdamW: {use_fused}")
+        return optimizer
+
+    @torch.inference_mode()
+    def generate(self, idx, max_new_tokens=512, temperature=1.0, top_k=None):
+        """
+        Take a conditioning sequence of indices idx (LongTensor of shape (b,t)) and complete
+        the sequence max_new_tokens times, feeding the predictions back into the model each time.
+        Most likely you'll want to make sure to be in model.eval() mode of operation for this.
+        Also note this is a super inefficient version of sampling with no key/value cache.
+        """
+        for _ in range(max_new_tokens):
+            # if the sequence context is growing too long we must crop it at block_size
+            idx_cond = idx if idx.size(1) <= self.params.max_seq_len else idx[:, -self.params.max_seq_len:]
+            # forward the model to get the logits for the index in the sequence
+            logits = self(idx_cond)
+            logits = logits[:, -1, :]  # crop to just the final time step
+            if temperature == 0.0:
+                # "sample" the single most likely index
+                _, idx_next = torch.topk(logits, k=1, dim=-1)
+            else:
+                # pluck the logits at the final step and scale by desired temperature
+                logits = logits / temperature
+                # optionally crop the logits to only the top k options
+                if top_k is not None:
+                    v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
+                    logits[logits < v[:, [-1]]] = -float('Inf')
+                # apply softmax to convert logits to (normalized) probabilities
+                probs = F.softmax(logits, dim=-1)
+                idx_next = torch.multinomial(probs, num_samples=1)
+            # append sampled index to the running sequence and continue
+            idx = torch.cat((idx, idx_next), dim=1)
+
+        return idx
+
+    # @torch.inference_mode()
+    @torch.no_grad()
+    def stream_generate(self, idx, eos, max_new_tokens, temperature=1.0, top_k=None):
+        """
+        Take a conditioning sequence of indices idx (LongTensor of shape (b,t)) and complete
+        the sequence max_new_tokens times, feeding the predictions back into the model each time.
+        Most likely you'll want to make sure to be in model.eval() mode of operation for this.
+        Also note this is a super inefficient version of sampling with no key/value cache.
+        """
+        idx_ = idx.shape[1]
+        for __ in range(max_new_tokens):
+            # if the sequence context is growing too long we must crop it at block_size
+            idx_cond = idx if idx.size(1) <= self.params.max_seq_len else idx[:, -self.params.max_seq_len:]
+            # forward the model to get the logits for the index in the sequence
+            logits = self(idx_cond)
+            logits = logits[:, -1, :]  # crop to just the final time step
+            if temperature == 0.0:
+                # "sample" the single most likely index
+                _, idx_next = torch.topk(logits, k=1, dim=-1)
+            else:
+                # pluck the logits at the final step and scale by desired temperature
+                logits = logits / temperature
+                # optionally crop the logits to only the top k options
+                if top_k is not None:
+                    v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
+                    logits[logits < v[:, [-1]]] = -float('Inf')
+
+                # apply softmax to convert logits to (normalized) probabilities
+                probs = F.softmax(logits, dim=-1)
+                idx_next = torch.multinomial(probs, num_samples=1, generator=None)
+            # append sampled index to the running sequence and continue
+            idx = torch.cat((idx, idx_next), dim=1)
+            yield idx[:, idx_:]
+
+            if idx_next == eos:
+                break
+
+    def export(self, filepath='model.bin'):
+        """export the model weights in fp32 into .bin file to be read from C"""
+        f = open(filepath, 'wb')
+
+        def serialize(t):
+            d = t.detach().cpu().view(-1).numpy().astype(np.float32)
+            b = struct.pack(f'{len(d)}f', *d)
+            f.write(b)
+
+        # first write out the header
+        hidden_dim = self.layers[0].feed_forward.w1.weight.shape[0]
+        p = self.params
+        n_kv_heads = p.n_heads if p.n_kv_heads is None else p.n_kv_heads
+        header = struct.pack('iiiiiii', p.dim, hidden_dim, p.n_layers, p.n_heads,
+                             n_kv_heads, p.vocab_size, p.max_seq_len)
+        f.write(header)
+
+        # next write out the embedding weights
+        serialize(self.tok_embeddings.weight)
+
+        # now all the layers
+        # attention weights
+        for layer in self.layers:
+            serialize(layer.attention_norm.weight)
+        for layer in self.layers:
+            serialize(layer.attention.wq.weight)
+        for layer in self.layers:
+            serialize(layer.attention.wk.weight)
+        for layer in self.layers:
+            serialize(layer.attention.wv.weight)
+        for layer in self.layers:
+            serialize(layer.attention.wo.weight)
+        # ffn weights
+        for layer in self.layers:
+            serialize(layer.ffn_norm.weight)
+        for layer in self.layers:
+            serialize(layer.feed_forward.w1.weight)
+        for layer in self.layers:
+            serialize(layer.feed_forward.w2.weight)
+        for layer in self.layers:
+            serialize(layer.feed_forward.w3.weight)
+        # final rmsnorm
+        serialize(self.norm.weight)
+        # note: no need to write final classifier weights due to weight sharing
+        # freqs_cis
+        serialize(self.freqs_cos[:p.max_seq_len])
+        serialize(self.freqs_sin[:p.max_seq_len])
+
+        # write to binary file
+        f.close()
+        print(f"wrote {filepath}")