Upload GPTJXForCausalLM

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]

config.json

@@ -0,0 +1,20 @@
+{
+  "_name_or_path": "/pretrainedmodel",
+  "architectures": [
+    "GPTJXForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "pretrained_config.GPTJXConfig",
+    "AutoModelForCausalLM": "pretrained_model.GPTJXForCausalLM"
+  },
+  "bias": false,
+  "block_size": 1024,
+  "dropout": 0.0,
+  "model_type": "nanogpt-j",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "vocab_size": 52050
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135619ec5be52e21223cd0c9dfec01af7f7f1b4600fd7af22d4d1db313a7a6ee
+size 553275408

pretrained_config.py

@@ -0,0 +1,30 @@
+from transformers import PretrainedConfig
+
+repo_name = "BeardedMonster/SabiYarn-125M"
+
+class GPTJXConfig(PretrainedConfig):
+    model_type="nanogpt-j"
+    
+    
+    def __init__(self,
+                block_size: int = 1024,
+                vocab_size: int = 52050, #50304 # GPT-2 vocab_size of 50257, padded up to nearest multiple of 64 for efficiency
+                n_layer: int = 12,
+                n_head: int = 12,
+                n_embd: int = 768,
+                dropout: float = 0.0,
+                bias: bool = False, # True: bias in Linears and LayerNorms, like GPT-2. False: a bit better and faster
+                **kwargs
+                ):
+        
+        self.block_size = block_size
+        self.vocab_size = vocab_size
+        self.n_layer = n_layer
+        self.n_head = n_head
+        self.n_embd = n_embd
+        self.dropout = dropout
+        self.bias = bias
+        
+        super().__init__(**kwargs)
+        
+        

pretrained_model.py

@@ -0,0 +1,188 @@
+from transformers import AutoConfig, PreTrainedModel, AutoModelForCausalLM
+from typing import List, Optional
+from torch import nn
+from model import LayerNorm, BlockJ
+from transformers.modeling_outputs import CausalLMOutputWithPast
+import torch
+import math
+from torch.nn import functional as F
+from transformers import AutoConfig, AutoModel
+from .pretrained_config import *
+
+   
+        
+class GPTJXForCausalLM(PreTrainedModel):
+    config_class = GPTJXConfig
+    base_model_prefix = "transformer"
+    is_parallelizable = True
+    supports_gradient_checkpointing = True
+    _no_split_modules = ["BlockJ"]
+    # _skip_keys_device_placement = "past_key_values"
+    _supports_flash_attn_2 = True
+    _tied_weights_keys = ["lm_head.weight"]
+    
+    
+    def __init__(self, config):
+        super().__init__(config)
+        assert config.vocab_size is not None
+        assert config.block_size is not None
+        self.config = config
+
+        self.transformer = nn.ModuleDict(dict(
+            wte = nn.Embedding(config.vocab_size, config.n_embd),
+            wpe = nn.Embedding(config.block_size, config.n_embd),
+            drop = nn.Dropout(config.dropout),
+            h = nn.ModuleList([BlockJ(config) for _ in range(config.n_layer)]),
+            ln_f = LayerNorm(config.n_embd, bias=config.bias),
+        ))
+        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
+        # with weight tying when using torch.compile() some warnings get generated:
+        # "UserWarning: functional_call was passed multiple values for tied weights.
+        # This behavior is deprecated and will be an error in future versions"
+        # not 100% sure what this is, so far seems to be harmless. TODO investigate
+        self.transformer.wte.weight = self.lm_head.weight # https://paperswithcode.com/method/weight-tying
+
+        # 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('c_proj.weight'):
+                torch.nn.init.normal_(p, mean=0.0, std=0.02/math.sqrt(2 * config.n_layer))
+
+        # report number of parameters
+        print("number of parameters: %.2fM" % (self.get_num_params()/1e6,))
+
+    def get_num_params(self, non_embedding=True):
+        """
+        Return the number of parameters in the model.
+        For non-embedding count (default), the position embeddings get subtracted.
+        The token embeddings would too, except due to the parameter sharing these
+        params are actually used as weights in the final layer, so we include them.
+        """
+        n_params = sum(p.numel() for p in self.parameters())
+        if non_embedding:
+            n_params -= self.transformer.wpe.weight.numel()
+        return n_params
+
+
+    def get_input_embeddings(self):
+        return self.wte
+
+    def set_input_embeddings(self, new_embeddings):
+        self.wte = new_embeddings
+
+    def forward(self, idx, targets=None, attn_mask= None,  output_hidden_states: Optional[bool] = None, **kwargs):
+        device = idx.device
+        b, t = idx.size()
+        
+        # attn_mask = _prepare_mask_(idx, b, eval)
+        # print("attention mask: ", attn_mask)
+        
+        assert t <= self.config.block_size, f"Cannot forward sequence of length {t}, block size is only {self.config.block_size}"
+        pos = torch.arange(0, t, dtype=torch.long, device=device) # shape (t)
+
+        # forward the GPT model itself
+        tok_emb = self.transformer.wte(idx) # token embeddings of shape (b, t, n_embd)
+        pos_emb = self.transformer.wpe(pos) # position embeddings of shape (t, n_embd)
+        x = self.transformer.drop(tok_emb + pos_emb)
+        for block in self.transformer.h:
+            x = block(x, attn_mask=attn_mask)
+        x = self.transformer.ln_f(x)
+
+        if targets is not None:
+            # if we are given some desired targets also calculate the loss
+            logits = self.lm_head(x)
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-100)
+        else:
+            # inference-time mini-optimization: only forward the lm_head on the very last position
+            logits = self.lm_head(x[:, [-1], :]) # note: using list [-1] to preserve the time dim
+            loss = None
+
+        # return {"logits": logits, "loss": loss}
+        return CausalLMOutputWithPast(
+            loss=loss,
+            logits=logits,
+            hidden_states=x if output_hidden_states else None,
+            attentions= None,
+        )
+
+    def prepare_inputs_for_generation(self, input_ids, attention_mask=None, **kwargs):
+        # Default model inputs
+        model_inputs = {"idx": input_ids}
+
+        # Add attention mask if provided
+        if attention_mask is not None:
+            model_inputs["attn_mask"] = attention_mask
+            
+        return model_inputs
+        
+
+    @torch.no_grad()
+    def stream(self, idx, max_new_tokens, temperature=1.0, top_k=None,gen_mode="greedy"):
+        """
+        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.
+        """
+        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.config.block_size else idx[:, -self.config.block_size:]
+            # forward the model to get the logits for the index in the sequence
+            logits, _ = self(idx_cond, eval=True)
+            # pluck the logits at the final step and scale by desired temperature
+            logits = logits[:, -1, :] / 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)
+            # sample from the distribution
+            if gen_mode == 'greedy':
+                idx_next = torch.argmax(probs, dim=-1).unsqueeze(0)
+                
+            else:
+                idx_next = torch.multinomial(probs, num_samples=1)
+            # print(idx_next.shape, idx.shape)
+            idx = torch.cat((idx, idx_next), dim=1)
+            # append sampled index to the running sequence and continue
+            yield idx_next
+            
+
+    def crop_block_size(self, block_size):
+        # model surgery to decrease the block size if necessary
+        # e.g. we may load the GPT2 pretrained model checkpoint (block size 1024)
+        # but want to use a smaller block size for some smaller, simpler model
+        assert block_size <= self.config.block_size
+        self.config.block_size = block_size
+        self.transformer.wpe.weight = nn.Parameter(self.transformer.wpe.weight[:block_size])
+        for block in self.transformer.h:
+            if hasattr(block.attn, 'bias'):
+                block.attn.bias = block.attn.bias[:,:,:block_size,:block_size]
+                
+
+AutoConfig.register("nanogpt-j", GPTJXConfig)
+AutoModel.register(GPTJXConfig,GPTJXForCausalLM)
+AutoModelForCausalLM.register(GPTJXConfig, GPTJXForCausalLM)               
+                
+        
+if __name__ == '__main__':
+    from transformers import AutoTokenizer
+
+    tokenizer = AutoTokenizer.from_pretrained("BeardedMonster/SabiYarn")
+    input_ids = tokenizer("ba wo ni?", return_tensors="pt")["input_ids"] 
+    targets = input_ids
+    
+    # config  = GPTJConfig()
+    # config.save_pretrained("gptj-config")
+    # new_config = GPTJ.from_pretrained("gptj-config")
+    # model = GPTJ(config)
+    # state_dict = torch.load('model.pt', map_location="cpu")
+    # model.load_state_dict(state_dict)
+    model = GPTJXForCausalLM.from_pretrained("/pretrainedmodel")
+    # model.save_pretrained("/pretrainedmodel")
+    outputs = model(input_ids, targets)
+    print(outputs)
+    output = model.generate(input_ids, max_new_tokens=100)
+    print(tokenizer.decode(output[0]))
+    # print(new_config)