Update README.md

README.md

@@ -126,7 +126,11 @@ This is an illustration, not an evaluation. In deployment:
 Install a recent Transformers release:
 
 ```bash
-pip install -U "transformers>=5.2.0,<6" torch
+%pip install -q --upgrade \
+    "transformers==5.15.0" \
+    "accelerate>=1.10,<2" \
+    "safetensors>=0.6" \
+    "huggingface_hub>=0.34"
 ```
 
 Then apply the checkpoint's native chat template:
@@ -135,24 +139,41 @@ Then apply the checkpoint's native chat template:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "AyoubChLin/lfm2.5-2.6b-fable5-coding-agent"
+MODEL_ID = "AyoubChLin/lfm2.5-2.6b-fable5-coding-agent"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    dtype=torch.bfloat16,
-    device_map="auto",
+    MODEL_ID,
+    dtype=torch.float16,          # Important: T4 uses FP16, not BF16
+    device_map={"": 0},           # Keep the complete model on GPU 0
+    low_cpu_mem_usage=True,
+    attn_implementation="sdpa",   # No external flash-attn installation
 )
+
 model.eval()
 
+parameter = next(model.parameters())
+print("Model device:", parameter.device)
+print("Model dtype:", parameter.dtype)
+
+assert parameter.device.type == "cuda"
+assert parameter.dtype == torch.float16
+
 messages = [
     {
         "role": "system",
-        "content": "You are a careful coding assistant. Make focused changes and verify the result.",
+        "content": (
+            "You are a careful coding assistant. Return complete, executable "
+            "code and briefly explain how it was verified."
+        ),
     },
     {
         "role": "user",
-        "content": "Write a tested Python function that merges overlapping integer intervals.",
+        "content": (
+            "Write a Python function that merges overlapping integer intervals. "
+            "Include pytest tests."
+        ),
     },
 ]
 
@@ -162,22 +183,34 @@ inputs = tokenizer.apply_chat_template(
     add_generation_prompt=True,
     return_tensors="pt",
     return_dict=True,
-).to(model.device)
+    truncation=True,
+    max_length=8192,              # Safe starting point for a T4
+).to("cuda:0")
+
+prompt_length = inputs["input_ids"].shape[1]
 
 with torch.inference_mode():
     output = model.generate(
         **inputs,
         max_new_tokens=768,
         do_sample=True,
-        temperature=0.2,
+        temperature=0.1,
         top_k=50,
         repetition_penalty=1.1,
+        use_cache=True,
         pad_token_id=tokenizer.pad_token_id,
         eos_token_id=tokenizer.eos_token_id,
     )
 
-new_tokens = output[0, inputs["input_ids"].shape[1]:]
-print(tokenizer.decode(new_tokens, skip_special_tokens=False))
+generated_tokens = output[0, prompt_length:]
+
+print(
+    tokenizer.decode(
+        generated_tokens,
+        skip_special_tokens=False,
+    )
+)
+
 ```
 
 `skip_special_tokens=False` preserves native reasoning and tool-call delimiters for inspection by a compatible parser. Do not send raw reasoning or unvalidated tool syntax directly to end users or executors.