---
license: apache-2.0
datasets:
- karpathy/fineweb-edu-100b-shuffle
language:
- en
model-index:
- name: chat-d10
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
    metrics:
    - type: acc
      value: 9.7
      name: accuracy
    source:
      url: https://github.com/karpathy/nanochat
      name: nanochat
---

# NanoChat SFT

This is the RL trained checkpoint from [Andrej Karpathy's](https://huggingface.co/karpathy) fullstack llm project to build an LLM, [nanochat](https://github.com/karpathy/nanochat).

## Usage

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


model_name = "nanochat-students/rl-d20"
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True).to(device)
model.eval()

conversation = [
    {"role": "user", "content": "Hello, who are you?"},
]
rendered = tokenizer.apply_chat_template(
    conversation,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([rendered], return_tensors="pt").to(model.device)

generated = model.generate(**model_inputs, max_new_tokens=256)
output_ids = generated[0, model_inputs.input_ids.shape[1]:]
print(tokenizer.decode(output_ids, skip_special_tokens=True))
```


## Chat RL Training Metrics

timestamp: 2025-10-15 12:59:52

- run: burtenshaw-20251015111354
- source: sft
- dtype: bfloat16
- device_batch_size: 8
- examples_per_step: 16
- num_samples: 16
- max_new_tokens: 256
- temperature: 1.0000
- top_k: 50
- unembedding_lr: 0.0040
- embedding_lr: 0.2000
- matrix_lr: 0.0200
- weight_decay: 0.0000
- init_lr_frac: 0.0500
- num_epochs: 1
- save_every: 60
- eval_every: 60
- eval_examples: 400

## Chat evaluation RL

timestamp: 2025-10-15 13:04:39

- source: rl
- task_name: GSM8K
- dtype: bfloat16
- temperature: 0.0000
- max_new_tokens: 512
- num_samples: 1
- top_k: 50
- batch_size: 8
- model_tag: None
- step: None
- max_problems: None
- GSM8K: 0.0970

Logs from training can be found here: https://huggingface.co/spaces/nanochat-students/trackio