Instructions to use lordx64/Qwable-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lordx64/Qwable-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="lordx64/Qwable-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lordx64/Qwable-v1")
model = AutoModelForMultimodalLM.from_pretrained("lordx64/Qwable-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lordx64/Qwable-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lordx64/Qwable-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lordx64/Qwable-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lordx64/Qwable-v1

SGLang

How to use lordx64/Qwable-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "lordx64/Qwable-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lordx64/Qwable-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "lordx64/Qwable-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lordx64/Qwable-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lordx64/Qwable-v1 with Docker Model Runner:
```
docker model run hf.co/lordx64/Qwable-v1
```

lordx64 commited on 17 days ago

Commit

ea97e8f

verified ·

1 Parent(s): 44aabe8

Card: full benchmark table with status column (all 🚧 in progress) + methodology notes

Browse files

Files changed (1) hide show

README.md +23 -13

README.md CHANGED Viewed

@@ -135,19 +135,29 @@ Content domain: web/game development, Three.js scenes, multiplayer FPS prototype
 ## Evaluation
-> **Pending the first eval batch.** Numbers will appear here when the lm-eval-harness + agent-coding eval suites complete.
-Planned benchmarks:
-| Benchmark | Why | Expected signal |
-|---|---|---|
-| GSM8K-CoT | Verify reasoning prior preserved through second SFT | Should match or beat the Opus 4.7 distill (~84% flexible) |
-| MMLU-Pro | General knowledge reasoning | Same as above (~75%) |
-| HumanEval / MBPP | Pure code completion (non-agentic) | Baseline check |
-| SWE-bench Lite (or BCB-Hard) | Agentic coding ability | This is where Fable-5 SFT should show gains over the Opus 4.7 base |
-| `qwen3-6-distill-eval` Space | Side-by-side qualitative comparison vs base + Claude/Kimi distills | Live at [`lordx64/qwen3-6-distill-eval`](https://huggingface.co/spaces/lordx64/qwen3-6-distill-eval) |
-Following our project convention: numbers stay blank until verified. If a benchmark hits a known extraction bug (e.g. AIME strict-match returning 0 because the model outputs `**Answer: N**` instead of `\boxed{N}`), we omit it rather than publish a misleading score.
 ## Usage

 ## Evaluation
+> 🚧 **Evals are in progress.** This table will fill in as each suite completes; nothing here is published until verified.
+| Benchmark | Setup | Tests | Score | Status |
+|---|---|---|---:|---|
+| **GSM8K-CoT** | 8-shot, multi-turn, limit 300 | Grade-school math; verify reasoning prior preserved through the second SFT round | _pending_ | 🚧 in progress |
+| **MMLU-Pro** | 5-shot, multi-turn, limit 500 | Hard multi-subject knowledge reasoning | _pending_ | 🚧 in progress |
+| **MMLU-Pro** (per-subject) | Same as above | Biology / Math / Psychology / etc. breakdown | _pending_ | 🚧 in progress |
+| **GPQA Diamond** | 0-shot CoT | Graduate-level STEM | _pending_ | 🚧 in progress |
+| **MATH-500** | 0-shot, `math_verify` metric | Competition math; tests reasoning depth | _pending_ | 🚧 in progress |
+| **AIME 2024 / 2025** | 0-shot CoT | Olympiad-level math; sensitivity to answer-extraction | _pending_ | 🚧 in progress |
+| **HumanEval / MBPP** | pass@1 / pass@10 | Pure code completion (non-agentic baseline) | _pending_ | 🚧 in progress |
+| **IFEval** | 0-shot | Instruction-following adherence | _pending_ | 🚧 in progress |
+| **SWE-bench Lite** (or BCB-Hard) | with agent harness + tool registry | **The key test**: agentic coding ability vs Opus 4.7 base | _pending_ | 🚧 in progress |
+| **`qwen3-6-distill-eval` Space** | 17 head-to-head prompts (12 design + 5 agentic) | Side-by-side qualitative comparison vs Qwen3.6 base + Opus 4.7 + Kimi K2.6 distills, with human-readable HTML output | _pending_ | 🚧 in progress |
+Methodology used (same as the Opus 4.7 / Kimi K2.6 evals on this project):
+- vLLM serving at 64k context so reasoning chains never truncate before answering
+- `<think>…</think>` stripped before regex extractors run (otherwise extractors grab letters/numbers from inside the reasoning, not the final answer)
+- Per-task `num_fewshot` (lm-eval's single global value can't handle GSM8K-8shot + GPQA-0shot together)
+- `fewshot_as_multiturn=True` for chat-template fidelity
+- `math_verify` metric for `MATH-500` and `AIME` (catches semantic equivalence; raw `strict-match` against `\boxed{N}` returns 0% even on correct answers because the model says `**Answer: N**`)
+Standing rule on this project: **numbers stay blank until verified**. If a benchmark hits a known extraction bug we couldn't cleanly fix, the row says so and we omit the score rather than publish a misleading one.
 ## Usage