Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Parable-SmolLM3-3B-Claude-Fable-5-GGUF-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Parable-SmolLM3-3B-Claude-Fable-5-GGUF-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86930a18b35020d0e90e945c1a44f6704972fc32943ed190c121ce18953d57e4
+size 6158339584

Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb88b166fe36aa59771db25bdae54e4b2fa756b165b4a32209f92c59825433b6
+size 1915305472

Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e863ea3b278932a1713a7b176c5d6215db2cc6f0b7fc50e5064a577e3a5c96
+size 2213756416

Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c97b0daf8ebbe335b54fa09160d74fc1b4b9b33a93b8f507daa17dc0109013
+size 2530860544

Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac4277c463ad245c880545480ef0983cd416ad24de78e9affe1a8e9e149e51d
+size 3275574784

README.md

@@ -0,0 +1,123 @@
+---
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM3-3B
+datasets:
+  - Glint-Research/Fable-5-traces
+  - Roman1111111/gpt5.5-terminal
+pipeline_tag: text-generation
+library_name: llama.cpp
+tags:
+  - gguf
+  - qlora
+  - agentic
+  - coding
+  - reasoning
+  - smollm3
+---
+
+# Parable-SmolLM3-3B-Claude-Fable-5-GGUF
+
+![SmolLM3-3B](banner.svg)
+
+Part of the **Parable** series: small local LLMs fine-tuned on genuine agent
+traces. This is HuggingFaceTB/SmolLM3-3B tuned on real Claude Fable 5 agent
+transcripts so its step-by-step reasoning voice carries into local use.
+
+Full-precision weights: [Parable-SmolLM3-3B-Claude-Fable-5](https://huggingface.co/AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5)
+
+## Files
+
+| File | Quant | Size | |
+|---|---|---|---|
+| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q4_K_M.gguf | Q4_K_M | 1.9 GB | **recommended default** |
+| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q5_K_M.gguf | Q5_K_M | 2.2 GB | |
+| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q6_K.gguf | Q6_K | 2.5 GB | |
+| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q8_0.gguf | Q8_0 | 3.3 GB | |
+| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-F16.gguf | F16 | 6.2 GB | for re-quantizing |
+
+## Usage
+
+```bash
+llama-cli -m Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q4_K_M.gguf \
+  -c 4096 -p "Write a python function that reverses a string." --temp 0.6
+```
+
+SmolLM3 is supported by current llama.cpp releases (brew, Ollama, LM Studio
+builds included); no special build is required.
+
+Output begins with a `<think>...</think>` reasoning block, then the answer.
+If you are building on top of this model, parse and strip the think block
+before showing text to end users. The chat template identifies the model as
+"Parable, a coding assistant that reasons before it answers."
+
+## Model details
+
+- **Base:** [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B) (3B, Apache-2.0, 64k context)
+- **Method:** MLX QLoRA on a 4-bit quantized base, 16 layers adapted,
+  6.7M trainable parameters (0.218%)
+- **Data:** 4,076 training rows from real Claude Fable 5 agent-session
+  traces plus gpt5.5-terminal transcripts, prepared at a 4,096-token window
+  (268 over-length rows dropped; 226/226 rows held out for validation/test)
+- **Schedule:** 1,200-iteration budget across a paused-and-resumed run;
+  best checkpoint selected on validation loss (iteration 200 of the final
+  segment, val 1.154)
+
+## Evaluation
+
+| | Held-out trace test loss |
+|---|---|
+| SmolLM3-3B base | 1.889 |
+| **This model** | **1.115** |
+
+The tuned model fits the Fable-5 reasoning distribution 41% better by
+held-out loss on a 226-row test split never seen in training. That is the
+honest headline for what this fine-tune does; we do not claim general
+benchmark gains.
+
+This lane trains on trace data without a replay mix, so impact on general
+coding benchmarks is unmeasured here. The series' technical report
+(DOI: [10.5281/zenodo.21676407](https://doi.org/10.5281/zenodo.21676407))
+documents why that matters and what replay does about it.
+
+## Limitations
+
+- Training ran on a 4-bit quantized base (16 GB M1 constraint); the F16
+  merge and higher quants cannot exceed 4-bit-base quality.
+- Modest scale: one seed, loss-based evaluation, no external benchmark run
+  for this model yet.
+- Not trained for: multi-file repo navigation, vision, non-English.
+- Inherits SmolLM3-3B's knowledge cutoff. Treat generated commands as
+  drafts to review.
+
+## Quantization
+
+Quantized with llama.cpp `llama-quantize` from the F16 merge.
+
+## Provenance & licensing
+
+Fine-tuned from HuggingFaceTB/SmolLM3-3B (Apache-2.0). Training data:
+[Glint-Research/Fable-5-traces](https://huggingface.co/datasets/Glint-Research/Fable-5-traces)
+(AGPL-3.0) and
+[Roman1111111/gpt5.5-terminal](https://huggingface.co/datasets/Roman1111111/gpt5.5-terminal)
+(MIT). Because those traces originate from third-party assistants, the
+providers' terms may apply to downstream training and distillation. If you
+plan to build on this model commercially, confirm your use aligns with those
+terms.
+
+## Citation
+
+```bibtex
+@misc{aglawe2026parable,
+  author = {Aglawe, Ankit},
+  title  = {Agent-Trace Fine-Tuning of Small Language Models under Constrained Compute},
+  year   = {2026},
+  doi    = {10.5281/zenodo.21676407},
+  url    = {https://doi.org/10.5281/zenodo.21676407}
+}
+```
+
+## Acknowledgements
+
+The SmolLM3 team at Hugging Face for the base model; Glint-Research and
+Roman1111111 for the trace datasets; empero-ai for the recipe this series
+iterates on.