Upload README.md with huggingface_hub

README.md

@@ -11,9 +11,8 @@ tags:
 # Mini-LLM Assistant 150M
 
 A ~150M parameter conversational assistant with a full training pipeline implemented
-end-to-end in PyTorch — BPE tokenizer, pretraining and supervised fine-tuning, no
-pretrained backbone. Code, training pipeline and documentation:
-[github.com/Mini-llm-lab/Mini-LLM](https://github.com/Mini-llm-lab/Mini-LLM).
+end-to-end in PyTorch: BPE tokenizer, pretraining and supervised fine-tuning, no
+pretrained backbone.
 
 This repository hosts both the SFT assistant (repository root) and the base model it
 was fine-tuned from ([`base/`](base)).
@@ -26,14 +25,14 @@ was fine-tuned from ([`base/`](base)).
 | Architecture   | Transformer decoder: RMSNorm, RoPE, causal attention, SwiGLU                                                                    |
 | Context length | 512 tokens                                                                                                                      |
 | Vocabulary     | 32,768 (BPE)                                                                                                                    |
-| Pretraining    | ~4.50B tokens (FineWeb-Edu + Wikipedia), 34,332 steps — base val loss 2.941 (32k vocabulary)                                    |
-| Fine-tuning    | 2 epochs of SFT on Dolly-15k, No Robots, OpenAssistant oasst2, alpaca-cleaned and identity/small-talk examples — val loss 2.780 |
+| Pretraining    | ~4.50B tokens (FineWeb-Edu + Wikipedia), 34,332 steps, base val loss 2.941 (32k vocabulary)                                    |
+| Fine-tuning    | 2 epochs of SFT on Dolly-15k, No Robots, OpenAssistant oasst2, alpaca-cleaned and identity/small-talk examples, val loss 2.780 |
 
 ## Base model
 
 The [`base/`](base) subfolder contains the pretrained checkpoint
 (`mini-llm-base-150M-34332steps.pt`) before SFT: 152,596,224 parameters, 32,768-token
-BPE vocabulary, ~4.50B tokens (FineWeb-Edu + Wikipedia), 34,332 steps — base val loss
+BPE vocabulary, ~4.50B tokens (FineWeb-Edu + Wikipedia), 34,332 steps, base val loss
 2.941. It is a raw completion model, not an assistant: `base/` ships without a chat
 template and without the assistant's sampling defaults.
 
@@ -64,7 +63,7 @@ out = model.generate(inputs, max_new_tokens=128)
 print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
 ```
 
-`trust_remote_code=True` is required — the architecture ships with the repository
+`trust_remote_code=True` is required, the architecture ships with the repository
 (`modeling_mini_llm.py`, `configuration_mini_llm.py`). Sampling defaults
 (temperature 0.5, top_k 40, repetition penalty 1.15) live in `generation_config.json`.
 
@@ -76,7 +75,7 @@ User: <question>
 Assistant: <answer>
 ```
 
-Each question is processed independently — no conversation history is attached.
+Each question is processed independently, no conversation history is attached.
 
 ## Limitations
 
@@ -88,4 +87,4 @@ Generation quality is tracked by the
 ## Links
 
 - Base model weights: https://huggingface.co/GautierP/MiniLLM-150M/tree/main/base
-- Code, training pipeline and full documentation: https://github.com/Mini-llm-lab/Mini-LLM
+- Code, training pipeline and full documentation: https://github.com/Mini-llm-lab/