Upload README (2).md

README (2).md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+---
+CURRENTLY IN TRAINING :)
+
+Currently, only the LLM section of this model is fully ready.
+```py
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+import torch
+
+# Load model and tokenizer
+model_name = "Abhaykoul/hai3.1-pretrainedv3"
+
+# Set device to CUDA if available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype="auto")
+model.to(device)
+print(model)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+# Message role format for chat
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": """hlo"""},
+]
+
+# Apply chat template to format prompt
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+# Tokenize input and move to device
+inputs = tokenizer(prompt, return_tensors="pt")
+inputs = {k: v.to(device) for k, v in inputs.items()}
+
+# Set up text streamer for live output
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+# Generate text with streaming
+model.generate(
+    **inputs,
+    max_new_tokens=4089,
+    temperature=0.7,
+    top_p=0.9,
+    do_sample=True,
+    streamer=streamer
+)
+```
+Classfication section undertraining
+```py
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+ckpt = "Abhaykoul/hai3.1-pretrainedv3"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+model = AutoModelForCausalLM.from_pretrained(ckpt, trust_remote_code=True).to(device).eval()
+tok = AutoTokenizer.from_pretrained(ckpt, trust_remote_code=True)
+if tok.pad_token is None:
+    tok.pad_token = tok.eos_token
+
+text = "I am thrilled about my new job!"
+enc = tok([text], padding=True, truncation=True, max_length=2048, return_tensors="pt")
+enc = {k: v.to(device) for k, v in enc.items()}
+
+with torch.no_grad():
+    out = model(input_ids=enc["input_ids"], attention_mask=enc.get("attention_mask"), output_hidden_states=True, return_dict=True, use_cache=False)
+    last = out.hidden_states[-1]
+    idx = (enc["attention_mask"].sum(dim=1) - 1).clamp(min=0)
+    pooled = last[torch.arange(last.size(0)), idx]
+    logits = model.structured_lm_head(pooled)
+    pred_id = logits.argmax(dim=-1).item()
+
+print("Predicted class id:", pred_id)
+# Map id -> label using your dataset’s label list, e.g.:
+id2label = ["sadness","joy","love","anger","fear","surprise"]  # dair-ai/emotion
+print("Predicted label:", id2label[pred_id] if pred_id < len(id2label) else "unknown")
+```
+
+TTS layers in training
+
+NOTE: we have used qwen2 tokenizer in it
+
+This model contains layers from our diffrent models
+To aline layers we have done post training after merging layers