Update README.md

README.md

@@ -12,13 +12,54 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# RuBit-Llama-56M2
+# RuBit-Llama-63M
 
-This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the darulm dataset.
+This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the darulm dataset. 
+From darulm aphorisms, dramaturgy, history, humor, literature domains were sampled
+
+Training on 2_125_871_104 tokens.
+
+Inspired by [abideen/Bitnet-Llama-70M](https://huggingface.co/abideen/Bitnet-Llama-70M)
 
 ## Model description
 
-More information needed
+# Sample inference code
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load a pretrained BitNet model
+model = "igorktech/RuBit-LLama-63M"
+tokenizer = AutoTokenizer.from_pretrained(model)
+model = AutoModelForCausalLM.from_pretrained(model)
+
+def convert_to_bitnet(model, copy_weights):
+    for name, module in model.named_modules():
+        # Replace linear layers with BitNet
+        if isinstance(module, LlamaSdpaAttention) or isinstance(module, LlamaMLP):
+            for child_name, child_module in module.named_children():
+                if isinstance(child_module, nn.Linear):
+                    bitlinear = BitLinear(child_module.in_features, child_module.out_features, child_module.bias is not None).to(device="cuda:0")
+                    if copy_weights:
+                        bitlinear.weight = child_module.weight
+                        if child_module.bias is not None:
+                            bitlinear.bias = child_module.bias
+                    setattr(module, child_name, bitlinear)
+        # Remove redundant input_layernorms
+        elif isinstance(module, LlamaDecoderLayer):
+            for child_name, child_module in module.named_children():
+                if isinstance(child_module, LlamaRMSNorm) and child_name == "input_layernorm":
+                    setattr(module, child_name, nn.Identity().to(device="cuda:0"))
+              
+
+convert_to_bitnet(model, copy_weights=True)
+model.to(device="cuda:0")
+
+prompt = "Привет"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+generate_ids = model.generate(inputs.input_ids, max_length=100)
+tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+```
 
 ## Intended uses & limitations