Text Generation
MLX
Safetensors
English
Chinese
naive_n05_flash
jang
jangh
quantized
apple-silicon
Mixture of Experts
code
long-context
reasoning
thinking
agent
tool-use
gptq
conversational
8-bit precision
Instructions to use JANGQ-AI/Naive-N0.5-Flash-JANGH2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use JANGQ-AI/Naive-N0.5-Flash-JANGH2 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("JANGQ-AI/Naive-N0.5-Flash-JANGH2") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use JANGQ-AI/Naive-N0.5-Flash-JANGH2 with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "JANGQ-AI/Naive-N0.5-Flash-JANGH2"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "JANGQ-AI/Naive-N0.5-Flash-JANGH2" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use JANGQ-AI/Naive-N0.5-Flash-JANGH2 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "JANGQ-AI/Naive-N0.5-Flash-JANGH2"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "JANGQ-AI/Naive-N0.5-Flash-JANGH2" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JANGQ-AI/Naive-N0.5-Flash-JANGH2", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use JANGQ-AI/Naive-N0.5-Flash-JANGH2 with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "JANGQ-AI/Naive-N0.5-Flash-JANGH2"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default JANGQ-AI/Naive-N0.5-Flash-JANGH2
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use JANGQ-AI/Naive-N0.5-Flash-JANGH2 with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "JANGQ-AI/Naive-N0.5-Flash-JANGH2"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "JANGQ-AI/Naive-N0.5-Flash-JANGH2" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download evaluation/kl_vs_bf16.json from JANGQ-AI/Naive-N0.5-Flash-JANGH2: direct link, hf CLI and curl.
- Browser
- Download file 8.62 kB
-
https://huggingface.co/JANGQ-AI/Naive-N0.5-Flash-JANGH2/resolve/main/evaluation/kl_vs_bf16.json
- Command line
-
hf download hf://JANGQ-AI/Naive-N0.5-Flash-JANGH2/evaluation/kl_vs_bf16.json
-
curl -L -o kl_vs_bf16.json https://huggingface.co/JANGQ-AI/Naive-N0.5-Flash-JANGH2/resolve/main/evaluation/kl_vs_bf16.json
8.62 kB
| { | |
| "reference": "BF16 source, layer-streamed", | |
| "mode": "served (2048-token prefill chunks, runtime caches)", | |
| "note": "text_* fields are the deviation from the reference on documents rendered inside user turns; they are a fidelity number, not a quality metric", | |
| "klref": { | |
| "sequences": 28, | |
| "positions": 68370, | |
| "median_kl": 0.1704166978597641, | |
| "mean_kl": 1.0084285736083984, | |
| "p90": 3.112718105316162, | |
| "p95": 5.369931697845459, | |
| "p99": 10.504664421081543, | |
| "kl_max": 24.663476943969727, | |
| "top1_pct": 64.3513236799766, | |
| "top5_pct": 81.47140558724587, | |
| "top10_pct": 85.58432060845401, | |
| "text_ppl_q": 87.12694549560547, | |
| "text_ppl_ref": 64.08563232421875, | |
| "text_ppl_ratio": 1.3595391511917114, | |
| "text_nll_delta_mean": 0.3071458041667938, | |
| "text_nll_delta_sem": 0.008856940366766429, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 42.59616790990201, | |
| "text_top1_acc_ref_pct": 44.99195553605382, | |
| "per_domain": { | |
| "academic_mc": { | |
| "sequences": 2, | |
| "positions": 3123, | |
| "median_kl": 0.21307168900966644, | |
| "mean_kl": 0.8185907602310181, | |
| "p90": 2.195399522781372, | |
| "p95": 4.076174259185791, | |
| "p99": 9.240348815917969, | |
| "kl_max": 15.55548095703125, | |
| "top1_pct": 62.343900096061475, | |
| "top5_pct": 83.09317963496638, | |
| "top10_pct": 88.3445405059238, | |
| "text_ppl_q": 121.92414093017578, | |
| "text_ppl_ref": 83.09352111816406, | |
| "text_ppl_ratio": 1.4673125743865967, | |
| "text_nll_delta_mean": 0.3834325075149536, | |
| "text_nll_delta_sem": 0.03734057597673582, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 35.510726865193725, | |
| "text_top1_acc_ref_pct": 38.58469420429075 | |
| }, | |
| "agentic": { | |
| "sequences": 4, | |
| "positions": 7411, | |
| "median_kl": 0.23808088898658752, | |
| "mean_kl": 1.1584773063659668, | |
| "p90": 3.5633037090301514, | |
| "p95": 5.776463985443115, | |
| "p99": 10.857256889343262, | |
| "kl_max": 19.707765579223633, | |
| "top1_pct": 60.38321414114155, | |
| "top5_pct": 77.97868034003508, | |
| "top10_pct": 82.52597490217245, | |
| "text_ppl_q": 197.68115234375, | |
| "text_ppl_ref": 144.7749786376953, | |
| "text_ppl_ratio": 1.3654372692108154, | |
| "text_nll_delta_mean": 0.3114747405052185, | |
| "text_nll_delta_sem": 0.02703807786033071, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 38.15949264606665, | |
| "text_top1_acc_ref_pct": 40.08905680744839 | |
| }, | |
| "chinese": { | |
| "sequences": 2, | |
| "positions": 3158, | |
| "median_kl": 0.1715339720249176, | |
| "mean_kl": 0.8395028710365295, | |
| "p90": 2.2756786346435547, | |
| "p95": 4.545201778411865, | |
| "p99": 9.803081512451172, | |
| "kl_max": 17.90928077697754, | |
| "top1_pct": 65.13616212792907, | |
| "top5_pct": 84.26219126029132, | |
| "top10_pct": 88.22039265357822, | |
| "text_ppl_q": 218.26402282714844, | |
| "text_ppl_ref": 139.631103515625, | |
| "text_ppl_ratio": 1.563148021697998, | |
| "text_nll_delta_mean": 0.4467017352581024, | |
| "text_nll_delta_sem": 0.04302379258395983, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 33.69221025965801, | |
| "text_top1_acc_ref_pct": 35.718809373020896 | |
| }, | |
| "coding": { | |
| "sequences": 5, | |
| "positions": 8249, | |
| "median_kl": 0.08199650049209595, | |
| "mean_kl": 0.9424503445625305, | |
| "p90": 3.0316593647003174, | |
| "p95": 5.3630523681640625, | |
| "p99": 10.516594886779785, | |
| "kl_max": 19.948368072509766, | |
| "top1_pct": 68.83258576797188, | |
| "top5_pct": 83.64650260637653, | |
| "top10_pct": 87.11358952600315, | |
| "text_ppl_q": 56.27544021606445, | |
| "text_ppl_ref": 48.28934097290039, | |
| "text_ppl_ratio": 1.1653801202774048, | |
| "text_nll_delta_mean": 0.1530473530292511, | |
| "text_nll_delta_sem": 0.023818490760019757, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 47.957328160989206, | |
| "text_top1_acc_ref_pct": 49.399927263910776 | |
| }, | |
| "cybersec": { | |
| "sequences": 4, | |
| "positions": 6653, | |
| "median_kl": 0.05261153727769852, | |
| "mean_kl": 0.7892881035804749, | |
| "p90": 2.4670655727386475, | |
| "p95": 4.8032917976379395, | |
| "p99": 9.959638595581055, | |
| "kl_max": 18.70598030090332, | |
| "top1_pct": 73.01969036524876, | |
| "top5_pct": 86.38208327070494, | |
| "top10_pct": 89.07259882759658, | |
| "text_ppl_q": 50.75177764892578, | |
| "text_ppl_ref": 40.27240753173828, | |
| "text_ppl_ratio": 1.2602119445800781, | |
| "text_nll_delta_mean": 0.23127995431423187, | |
| "text_nll_delta_sem": 0.024030208570325735, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 50.72899443859913, | |
| "text_top1_acc_ref_pct": 52.72809258980911 | |
| }, | |
| "general": { | |
| "sequences": 3, | |
| "positions": 5311, | |
| "median_kl": 0.2415456622838974, | |
| "mean_kl": 1.014784336090088, | |
| "p90": 3.076566457748413, | |
| "p95": 5.115887641906738, | |
| "p99": 10.112685203552246, | |
| "kl_max": 16.833053588867188, | |
| "top1_pct": 60.6477122952363, | |
| "top5_pct": 80.64394652607795, | |
| "top10_pct": 84.59800414234607, | |
| "text_ppl_q": 191.92210388183594, | |
| "text_ppl_ref": 122.87806701660156, | |
| "text_ppl_ratio": 1.5618903636932373, | |
| "text_nll_delta_mean": 0.44589686393737793, | |
| "text_nll_delta_sem": 0.03573012642731573, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 36.057239691206924, | |
| "text_top1_acc_ref_pct": 39.20165693842967 | |
| }, | |
| "long_agentic": { | |
| "sequences": 2, | |
| "positions": 10190, | |
| "median_kl": 0.2484634965658188, | |
| "mean_kl": 1.3893784284591675, | |
| "p90": 4.4491071701049805, | |
| "p95": 6.867280960083008, | |
| "p99": 11.967666625976562, | |
| "kl_max": 23.30169677734375, | |
| "top1_pct": 58.96957801766438, | |
| "top5_pct": 75.44651619234544, | |
| "top10_pct": 79.96074582924436, | |
| "text_ppl_q": 100.91949462890625, | |
| "text_ppl_ref": 77.45440673828125, | |
| "text_ppl_ratio": 1.3029543161392212, | |
| "text_nll_delta_mean": 0.2646341919898987, | |
| "text_nll_delta_sem": 0.027041340773589443, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 43.49362119725221, | |
| "text_top1_acc_ref_pct": 45.37782139352306 | |
| }, | |
| "long_coding": { | |
| "sequences": 2, | |
| "positions": 9390, | |
| "median_kl": 0.08500003814697266, | |
| "mean_kl": 0.8798364400863647, | |
| "p90": 2.7945637702941895, | |
| "p95": 5.145983695983887, | |
| "p99": 9.630831718444824, | |
| "kl_max": 24.311695098876953, | |
| "top1_pct": 69.86155484558041, | |
| "top5_pct": 83.87646432374866, | |
| "top10_pct": 87.39084132055378, | |
| "text_ppl_q": 41.933414459228516, | |
| "text_ppl_ref": 37.08015441894531, | |
| "text_ppl_ratio": 1.1308856010437012, | |
| "text_nll_delta_mean": 0.1230010911822319, | |
| "text_nll_delta_sem": 0.02238255679146158, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 51.15015974440894, | |
| "text_top1_acc_ref_pct": 52.51331203407881 | |
| }, | |
| "long_longctx": { | |
| "sequences": 2, | |
| "positions": 10990, | |
| "median_kl": 0.22215455770492554, | |
| "mean_kl": 0.8677619099617004, | |
| "p90": 2.328246831893921, | |
| "p95": 4.105473041534424, | |
| "p99": 9.772666931152344, | |
| "kl_max": 24.663476943969727, | |
| "top1_pct": 63.366696997270246, | |
| "top5_pct": 83.31210191082803, | |
| "top10_pct": 87.96178343949045, | |
| "text_ppl_q": 74.3593521118164, | |
| "text_ppl_ref": 48.85396957397461, | |
| "text_ppl_ratio": 1.5220731496810913, | |
| "text_nll_delta_mean": 0.42007333040237427, | |
| "text_nll_delta_sem": 0.020436424192156313, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 38.28935395814377, | |
| "text_top1_acc_ref_pct": 42.029117379435846 | |
| }, | |
| "science": { | |
| "sequences": 2, | |
| "positions": 3895, | |
| "median_kl": 0.3555840253829956, | |
| "mean_kl": 1.227760672569275, | |
| "p90": 3.644615650177002, | |
| "p95": 5.74046516418457, | |
| "p99": 10.63033390045166, | |
| "kl_max": 21.231704711914062, | |
| "top1_pct": 57.201540436457, | |
| "top5_pct": 77.45827984595635, | |
| "top10_pct": 82.84980744544288, | |
| "text_ppl_q": 89.30754089355469, | |
| "text_ppl_ref": 47.66631317138672, | |
| "text_ppl_ratio": 1.8735977411270142, | |
| "text_nll_delta_mean": 0.6278604865074158, | |
| "text_nll_delta_sem": 0.038523879100658555, | |
| "text_positions_compared_pct": 100.0, | |
| "text_ppl_unbiased": true, | |
| "text_top1_acc_q_pct": 36.79075738125802, | |
| "text_top1_acc_ref_pct": 41.54043645699615 | |
| } | |
| }, | |
| "prefill_tok_per_s_full_forward": 596.8083549490221, | |
| "reference": "BF16 (layer-streamed source)" | |
| }, | |
| "peak_memory_gib": 104.80185685772449 | |
| } |