GGUF quantizations of a LoRA fine-tune of microsoft/FastContext-1.0-4B-RL (no longer available on the Hub), supervised fine-tuned on ermiaazarkhalili/claude-reasoning-distillation (private) (config sft).

Quantized from ermiaazarkhalili/FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth. See that repository for the full-precision weights.


Base model	`microsoft/FastContext-1.0-4B-RL` (no longer available on the Hub)
Training data	`ermiaazarkhalili/claude-reasoning-distillation` (private) (config `sft`)
Method	LoRA supervised fine-tuning via Unsloth + TRL

Available quantizations

File	Size
`fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q2_k.gguf`	1.67 GB
`fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q3_k_m.gguf`	2.08 GB
`fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q4_k_m.gguf`	2.50 GB
`fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q5_k_m.gguf`	2.89 GB
`fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q6_k.gguf`	3.31 GB
`fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q8_0.gguf`	4.28 GB

Usage

llama.cpp

bash

huggingface-cli download ermiaazarkhalili/FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth-GGUF fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q4_k_m.gguf --local-dir .
llama-cli -m fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256

Ollama

bash

echo 'FROM ./fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth.q4_k_m.gguf' > Modelfile
ollama create fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth-gguf -f Modelfile
ollama run fastcontext-4b-rl_base-sft-claude-opus-reasoning-unsloth-gguf

Training configuration

Setting	Value
LoRA rank (r)	16
LoRA alpha	16
Learning rate	0.0002
Epochs	1
Effective batch size	8 (2 x 4 grad accum)
Max sequence length	2048
Base precision	4-bit (QLoRA)
Target modules	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`

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.

SLURM job	Steps	First loss	Final loss
`53225525`	94,254	1.1631	0.8687
`45169149`	1,310	1.1535	0.8004

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.