FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth

FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth

A LoRA fine-tune of microsoft/FastContext-1.0-4B-RL, supervised fine-tuned on ermiaazarkhalili/claude-reasoning-distillation (private) (config sft).

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ermiaazarkhalili/FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype='auto', device_map='auto')

messages = [{"role": "user", "content": "Explain gradient checkpointing in two sentences."}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors='pt'
).to(model.device)

outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training configuration

Observed training loss

Measured from our SLURM logs for this configuration. These are training-loss observations only — no downstream benchmark evaluation has been run on this model, so they should not be read as a quality claim.

Limitations

• No benchmark evaluation has been run on this checkpoint. The only reported numbers are training-loss observations.
• Inherits the biases, knowledge cutoff and failure modes of the base model.
• Fine-tuned on a single instruction-following dataset; behaviour outside that distribution is untested.
• LoRA adapters were merged into the base weights, so the merged model cannot be detached from this fine-tune.

Reproducing

Trained by notebooks/sft_distillation_fastcontext-4b-rl_unsloth.ipynb, executed non-interactively with papermill on a SLURM H100 partition (Unsloth + TRL, LoRA).

---

Card generated from the training run's own configuration and logs by scripts/generate_hub_model_card.py.