初始化项目，由ModelHub XC社区提供模型

Model: flammenai/FlameDesigner-Qwen2.5-3B-v1-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,39 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+FlameDesigner-Qwen2.5-3B-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FlameDesigner-Qwen2.5-3B-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FlameDesigner-Qwen2.5-3B-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+FlameDesigner-Qwen2.5-3B-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text

FlameDesigner-Qwen2.5-3B-v1.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ae7c9ba6031cbbf0fa8f8b8f563c9215c2444c52a8bad289276f1abcc58e54
+size 1929903104

FlameDesigner-Qwen2.5-3B-v1.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44703edb7421fdae97bcba603bdbba077fd51acc28354ffc8d29c74f9b7e5327
+size 2224815104

FlameDesigner-Qwen2.5-3B-v1.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b957b50f00c4e9dff19681a0653a09a664411ced93645642cbec6b38d19ff4e0
+size 3285476352

FlameDesigner-Qwen2.5-3B-v1.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb81cd4cd1ab31ebbae4e6118d4eb300e4b8f5c17d1ef172968678b56f857c7b
+size 6178317312

README.md

@@ -0,0 +1,107 @@
+---
+license: mit
+base_model: flammenai/FlameDesigner-Qwen2.5-3B-v1
+base_model_relation: quantized
+library_name: gguf
+tags:
+- character-design
+- json
+- structured-output
+- flammen.ai
+- gguf
+quantized_by: flammenai
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# FlameDesigner-Qwen2.5-3B-v1-GGUF
+
+GGUF quantizations of [`flammenai/FlameDesigner-Qwen2.5-3B-v1`](https://huggingface.co/flammenai/FlameDesigner-Qwen2.5-3B-v1) — a Qwen2.5-3B-Instruct LoRA finetune that turns a free-text seed (e.g. `"samurai"`, `"Mongolian falconer"`) into a strict-schema JSON character design for [flammen.ai](https://huggingface.co/flammenai)'s Create-a-Flame pipeline.
+
+Trained on [`flammenai/flame-kindling-v1`](https://huggingface.co/datasets/flammenai/flame-kindling-v1) (400 SFT rows distilled from Claude Sonnet 4.5).
+
+## Files
+
+| Quant | Size | Notes |
+|---|---|---|
+| `FlameDesigner-Qwen2.5-3B-v1.f16.gguf` | 5.8 GB | Source for further quantization |
+| `FlameDesigner-Qwen2.5-3B-v1.Q8_0.gguf`  | 3.1 GB | **Recommended.** Best strict-schema compliance in our eval; near-F16 quality at half the size. |
+| `FlameDesigner-Qwen2.5-3B-v1.Q5_K_M.gguf` | 2.1 GB | Compromise between Q8 and Q4. |
+| `FlameDesigner-Qwen2.5-3B-v1.Q4_K_M.gguf` | 1.8 GB | Smallest practical CPU quant. Strict-schema pass rate drops noticeably (see eval); use the auto-repair shim. |
+
+## Inference
+
+### llama.cpp / llama-server
+
+```bash
+llama-server -m FlameDesigner-Qwen2.5-3B-v1.Q4_K_M.gguf \
+  --host 127.0.0.1 --port 8081 -c 8192 --jinja
+```
+
+Then `POST /v1/chat/completions` with the [`flame_dataset.GOLD_SYSTEM`](https://huggingface.co/datasets/flammenai/flame-kindling-v1) system prompt and the seed as the user message. Output is a single JSON object matching the `DesignedFlame` schema (or close — see "Auto-repair shim" below).
+
+### Example
+
+```python
+import requests, json
+SYSTEM = open("GOLD_SYSTEM.txt").read()  # from the dataset card / FlameKindling repo
+r = requests.post("http://127.0.0.1:8081/v1/chat/completions", json={
+    "messages": [
+        {"role": "system", "content": SYSTEM},
+        {"role": "user", "content": "Mongolian falconer"},
+    ],
+    "max_tokens": 2048,
+    "temperature": 0.7,
+})
+text = r.json()["choices"][0]["message"]["content"]
+print(json.loads(text))
+```
+
+## Eval
+
+20 held-out seeds (no overlap with training data, mix of one-word + sentence + paragraph). Inference at `temperature=0.7`, GPU offload (`-ngl 999`) on an A6000. Per-output coherence judged by Qwen3.5-27B (1-5 scale, lenient at the high end).
+
+| Quant | Avg latency | Strict pass | Soft pass (after auto-repair) |
+|---|---|---|---|
+| **Q8_0** | 3.1 s | **15/20 (75%)** | 19/20 (95%) |
+| F16 | 5.1 s | 13/20 (65%) | 20/20 (100%) |
+| Q4_K_M | 2.2 s | 7/20 (35%) | 19/20 (95%) |
+
+Quantization noticeably affects strict-schema compliance — Q4 loses ~half the strict pass rate vs Q8. The soft-pass numbers (after the auto-repair shim below) are within rounding distance for all three. **Recommendation: Q8_0 in production, with the shim regardless.**
+
+Coherence on valid outputs is consistently 4.5-5.0 across all quants — when the model produces a parseable design, the design is good. The strict failures are **1-off constraint violations**, not quality problems:
+- `writing_style` arrays with 5 entries instead of max 4 (trim to 4)
+- `languages` containing codes outside the [SUPPORTED_LANGUAGES](https://huggingface.co/datasets/flammenai/flame-kindling-v1) allow-list (e.g. `mn`, `cy`, `mi`, `sq` — Qwen2.5-3B knows these from base training; the LoRA didn't fully suppress them)
+- `system_prompt_extra` over 512 chars (truncate)
+- Rare: output truncated by max_tokens (use `max_tokens >= 2048`)
+
+## Auto-repair shim
+
+Production integration in FlameGen wraps the model with this shim before validating against `DesignedFlame`:
+
+```python
+def autorepair(obj: dict) -> dict:
+    if isinstance(obj.get("writing_style"), list):
+        obj["writing_style"] = obj["writing_style"][:4]
+    if isinstance(obj.get("languages"), list):
+        obj["languages"] = [c for c in obj["languages"] if c in SUPPORTED_LANGUAGES]
+        if not obj["languages"]:
+            obj["languages"] = ["en"]
+    if isinstance(obj.get("system_prompt_extra"), str):
+        obj["system_prompt_extra"] = obj["system_prompt_extra"][:512].rstrip()
+    return obj
+```
+
+Recovers ~60% of strict-failures, lifts effective pass rate from 35% to 95% with zero quality cost (the trimmed entries are themselves on-character — model just over-produced).
+
+## Limitations
+
+- **Small training set (400 rows).** Schema constraint violations above are likely from the small dataset + rank-128 LoRA over-capacity ratio. A v2 with more data should improve hard-pass.
+- **Schema drift on language allow-list.** Base Qwen knows codes outside `SUPPORTED_LANGUAGES`; the LoRA inherits this. The auto-repair shim handles it.
+- **Verbose `system_prompt_extra`.** Sometimes overshoots the 512-char cap — relax to 600 or apply the shim.
+- **No NSFW.** Training data was Sonnet-distilled; Sonnet declines explicit traits. NSFW Create-a-Flame is deferred in flammen.ai anyway.
+
+## License
+
+MIT