Update README.md

README.md

@@ -35,10 +35,10 @@ Fine-tuning started from the **instruct checkpoint** rather than base. Testing c
 - **Base model:** `LiquidAI/LFM2.5-350M` (instruct)
 - **Method:** Full fine-tune (96GB VRAM, no LoRA needed)
 - **Datasets:**
-  - Python Code: `iamtarun/python_code_instructions_18k_alpaca` (Python-focused, replacing the multi-language 120k set)
-  - Math: `openai/gsm8k` (main split)
-  - General Chat: `yahma/alpaca-cleaned` (30k sample subset)
-  - Custom Fix-It: Hand-crafted examples for negative constraints ("no dairy", "no eggs") and complete runnable Pygame scripts (duplicated 50× for weight)
+  - Python Code: [`iamtarun/python_code_instructions_18k_alpaca`](https://huggingface.co/datasets/iamtarun/python_code_instructions_18k_alpaca) (Python-focused, replacing the multi-language 120k set)
+  - Math: [`openai/gsm8k`](https://huggingface.co/datasets/openai/gsm8k) (main split)
+  - General Chat: [`yahma/alpaca-cleaned`](https://huggingface.co/datasets/yahma/alpaca-cleaned) (30k sample subset)
+  - Custom Fix-It: Hand-crafted examples for negative constraints ("no dairy", "no eggs") and complete runnable Pygame scripts (duplicated 50x for weight)
 - **Checkpoint selection:** Best by eval_loss
 - **Sequence length:** 2048 tokens (increased from 1024 to accommodate full scripts)
 - **Max response chars:** 3500 (prevents code truncation)
@@ -48,21 +48,22 @@ Fine-tuning started from the **instruct checkpoint** rather than base. Testing c
 
 ## What it's good at
 
-- **Python Code:** Complete, runnable scripts including Pygame game loops, file I/O, classes, list comprehensions, and algorithmic implementations (e.g., two-pointer palindrome check). No more placeholder `pass` statements or truncated functions.
-- **Math:** GSM8K-style word problems with step-by-step reasoning annotations (`<<...>>`). Reliable on algebra, percentages, geometry, and multi-step arithmetic.
-- **General Chat:** Retains coherent conversational ability. Correctly handles negative constraints (e.g., "breakfast without eggs" returns egg-free options). Knows the difference between baking cookies and browser cookies.
-- **Speed:** At 350M parameters, achieves ~157 t/s generation on laptop CPU (i5-12450H) with Q5_K_S quantization via llama.cpp.
+- **Python Code**: Complete, runnable scripts including Pygame game loops, file I/O, classes, list comprehensions, and algorithmic implementations (e.g., two-pointer palindrome check). No more placeholder `pass` statements or truncated functions.
+- **Math**: GSM8K-style word problems with step-by-step reasoning annotations (`<<...>>`). Reliable on algebra, percentages, geometry, and multi-step arithmetic.
+- **General Chat**: Retains coherent conversational ability. Correctly handles negative constraints (e.g., "breakfast without eggs" returns egg-free options). Knows the difference between baking cookies and browser cookies.
+- **Speed**: At 350M parameters, achieves ~157 t/s generation on laptop CPU (i5-12450H) with Q5_K_S quantization via llama.cpp.
 
 ## Known limitations
 
-- **Python only:** Trained exclusively on Python code instructions. Other languages were not included in this fine-tune.
-- **Sentence counting:** May not strictly adhere to "exactly N sentences" constraints.
-- **Identity:** May occasionally claim to be developed by Google (artifact from Alpaca-Cleaned training data).
-- **Still 350M parameters:** Do not expect deep multi-step reasoning or long-form creative writing at the level of larger models.
+- **Python only**: Trained exclusively on Python code instructions. Other languages were not included in this fine-tune.
+- **Sentence counting**: May not strictly adhere to "exactly N sentences" constraints.
+- **Identity**: May occasionally claim to be developed by Google (artifact from Alpaca-Cleaned training data).
+- **Still 350M parameters**: Do not expect deep multi-step reasoning or long-form creative writing at the level of larger models.
 - Not evaluated on safety-critical, medical, or legal use cases.
 
 ## Usage
 
+```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_id = "hauser458original/lfm2.5-350m-python-math"
@@ -76,8 +77,9 @@ inputs = tokenizer.apply_chat_template(
 
 output = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.5, top_p=0.9)
 print(tokenizer.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+```
 
-GGUF quantized versions (Q4_K_M, Q5_K_S, Q5_K_M, Q8_0, F16) for llama.cpp/Ollama/LM Studio are available at: hauser458original/lfm2.5-350m-python-math-GGUF
+GGUF quantized versions (Q4_K_M, Q5_K_S, Q5_K_M, Q8_0, F16) for llama.cpp/Ollama/LM Studio are available at: [`hauser458original/lfm2.5-350m-python-math-GGUF`](https://huggingface.co/hauser458original/lfm2.5-350m-python-math-GGUF)
 
 ## License