Text Generation
Transformers
PyTorch
MLX
English
tree-attention
apple-m4
mps
structured-generation
parallel-decoding
constrained-decoding
apple-silicon
classification
json
Instructions to use epsilon3/Qwen-2.5-1B-RLCD-Fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use epsilon3/Qwen-2.5-1B-RLCD-Fast with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="epsilon3/Qwen-2.5-1B-RLCD-Fast")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("epsilon3/Qwen-2.5-1B-RLCD-Fast", device_map="auto") - MLX
How to use epsilon3/Qwen-2.5-1B-RLCD-Fast with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("epsilon3/Qwen-2.5-1B-RLCD-Fast") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- vLLM
How to use epsilon3/Qwen-2.5-1B-RLCD-Fast with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "epsilon3/Qwen-2.5-1B-RLCD-Fast" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "epsilon3/Qwen-2.5-1B-RLCD-Fast", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/epsilon3/Qwen-2.5-1B-RLCD-Fast
- SGLang
How to use epsilon3/Qwen-2.5-1B-RLCD-Fast 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 "epsilon3/Qwen-2.5-1B-RLCD-Fast" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "epsilon3/Qwen-2.5-1B-RLCD-Fast", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "epsilon3/Qwen-2.5-1B-RLCD-Fast" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "epsilon3/Qwen-2.5-1B-RLCD-Fast", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - MLX LM
How to use epsilon3/Qwen-2.5-1B-RLCD-Fast with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "epsilon3/Qwen-2.5-1B-RLCD-Fast" --prompt "Once upon a time"
- Docker Model Runner
How to use epsilon3/Qwen-2.5-1B-RLCD-Fast with Docker Model Runner:
docker model run hf.co/epsilon3/Qwen-2.5-1B-RLCD-Fast
- Atomic Chat
Download h2h_cpu.json from epsilon3/Qwen-2.5-1B-RLCD-Fast: direct link, hf CLI and curl.
- Browser
- Download file 9.43 kB
-
https://huggingface.co/epsilon3/Qwen-2.5-1B-RLCD-Fast/resolve/main/h2h_cpu.json
- Command line
-
hf download hf://epsilon3/Qwen-2.5-1B-RLCD-Fast/h2h_cpu.json
-
curl -L -o h2h_cpu.json https://huggingface.co/epsilon3/Qwen-2.5-1B-RLCD-Fast/resolve/main/h2h_cpu.json
9.43 kB
| { | |
| "environment": { | |
| "model": "Qwen/Qwen2.5-1.5B-Instruct", | |
| "revision": "989aa7980e4cf806f80c7fef2b1adb7bc71aa306", | |
| "torch": "2.11.0", | |
| "transformers": "4.57.6", | |
| "platform": "macOS-26.6.2-arm64-arm-64bit", | |
| "device": "cpu", | |
| "dtype": "torch.float32", | |
| "attention": "sdpa", | |
| "threads": 4 | |
| }, | |
| "arguments": { | |
| "model": "Qwen/Qwen2.5-1.5B-Instruct", | |
| "revision": "989aa7980e4cf806f80c7fef2b1adb7bc71aa306", | |
| "device": "cpu", | |
| "dtype": "float32", | |
| "presets": [ | |
| "fintech_fraud" | |
| ], | |
| "fields": [ | |
| 4, | |
| 16, | |
| 28 | |
| ], | |
| "repeats": 6, | |
| "warmup": 2, | |
| "threads": 4, | |
| "output": "h2h_cpu.json" | |
| }, | |
| "cases": [ | |
| { | |
| "preset": "fintech_fraud", | |
| "fields": 4, | |
| "decisions_identical": true, | |
| "upstream_json": { | |
| "is_fraudulent": true, | |
| "risk_tier": "HIGH", | |
| "recommended_action": "BLOCK_TRANSACTION", | |
| "primary_anomaly": "IP_GEOLOCATION_MISMATCH" | |
| }, | |
| "release_json": { | |
| "is_fraudulent": true, | |
| "risk_tier": "HIGH", | |
| "recommended_action": "BLOCK_TRANSACTION", | |
| "primary_anomaly": "IP_GEOLOCATION_MISMATCH" | |
| }, | |
| "collision_fields": [], | |
| "wall": { | |
| "upstream_batch": { | |
| "median_ms": 548.3662289989297, | |
| "min_ms": 533.6810839944519, | |
| "p90_ms": 712.2898329980671, | |
| "samples_ms": [ | |
| 551.7348329885863, | |
| 712.2898329980671, | |
| 533.6810839944519, | |
| 544.9976250092732, | |
| 538.0564169900026, | |
| 551.9341250037542 | |
| ] | |
| }, | |
| "release_tree": { | |
| "median_ms": 484.92377100046724, | |
| "min_ms": 480.0681250053458, | |
| "p90_ms": 489.24579200684093, | |
| "samples_ms": [ | |
| 484.3823749979492, | |
| 489.24579200684093, | |
| 480.0681250053458, | |
| 481.98054199747276, | |
| 487.2161670064088, | |
| 485.46516700298525 | |
| ] | |
| } | |
| }, | |
| "internal_stage_medians": { | |
| "upstream_batch": { | |
| "elapsed_ms": 548.3, | |
| "prefill_ms": 416.44, | |
| "suffix_eval_ms": 128.195 | |
| }, | |
| "release_tree": { | |
| "elapsed_ms": 484.87, | |
| "prefill_ms": 369.125, | |
| "suffix_eval_ms": 113.66 | |
| } | |
| }, | |
| "speedup": 1.13082975467994, | |
| "speedup_ci95": [ | |
| 1.1063364704905627, | |
| 1.2970244628070058 | |
| ] | |
| }, | |
| { | |
| "preset": "fintech_fraud", | |
| "fields": 16, | |
| "decisions_identical": true, | |
| "upstream_json": { | |
| "is_fraudulent": false, | |
| "risk_tier": "HIGH", | |
| "recommended_action": "BLOCK_TRANSACTION", | |
| "primary_anomaly": "TOR_EXIT_NODE", | |
| "secondary_anomaly": "CARD_NOT_PRESENT", | |
| "requires_human_escalation": true, | |
| "can_auto_block": false, | |
| "aml_sar_filing_required": true, | |
| "fincen_flag_threshold": true, | |
| "sanctions_screening_risk": "HIGH_CONFIDENCE_MATCH", | |
| "tor_exit_node_detected": true, | |
| "device_fingerprint_mismatch": true, | |
| "velocity_score": "ELEVATED", | |
| "block_card_immediately": true, | |
| "freeze_online_banking": true, | |
| "notify_cardholder_sms": true | |
| }, | |
| "release_json": { | |
| "is_fraudulent": false, | |
| "risk_tier": "HIGH", | |
| "recommended_action": "BLOCK_TRANSACTION", | |
| "primary_anomaly": "TOR_EXIT_NODE", | |
| "secondary_anomaly": "CARD_NOT_PRESENT", | |
| "requires_human_escalation": true, | |
| "can_auto_block": false, | |
| "aml_sar_filing_required": true, | |
| "fincen_flag_threshold": true, | |
| "sanctions_screening_risk": "HIGH_CONFIDENCE_MATCH", | |
| "tor_exit_node_detected": true, | |
| "device_fingerprint_mismatch": true, | |
| "velocity_score": "ELEVATED", | |
| "block_card_immediately": true, | |
| "freeze_online_banking": true, | |
| "notify_cardholder_sms": true | |
| }, | |
| "collision_fields": [], | |
| "wall": { | |
| "upstream_batch": { | |
| "median_ms": 981.7173124974943, | |
| "min_ms": 940.7524590060348, | |
| "p90_ms": 1021.6882499953499, | |
| "samples_ms": [ | |
| 940.7524590060348, | |
| 960.8952910057269, | |
| 992.677874994115, | |
| 1021.6882499953499, | |
| 1007.7015830029268, | |
| 970.7567500008736 | |
| ] | |
| }, | |
| "release_tree": { | |
| "median_ms": 799.4022920101997, | |
| "min_ms": 748.7089589994866, | |
| "p90_ms": 831.0671670042211, | |
| "samples_ms": [ | |
| 748.7089589994866, | |
| 756.4683340024203, | |
| 805.0330000114627, | |
| 831.0671670042211, | |
| 820.0667500059353, | |
| 793.7715840089368 | |
| ] | |
| } | |
| }, | |
| "internal_stage_medians": { | |
| "upstream_batch": { | |
| "elapsed_ms": 980.6800000000001, | |
| "prefill_ms": 639.4549999999999, | |
| "suffix_eval_ms": 335.36 | |
| }, | |
| "release_tree": { | |
| "elapsed_ms": 799.34, | |
| "prefill_ms": 565.895, | |
| "suffix_eval_ms": 232.09 | |
| } | |
| }, | |
| "speedup": 1.22806417033011, | |
| "speedup_ci95": [ | |
| 1.222967374440484, | |
| 1.2702386178172165 | |
| ] | |
| }, | |
| { | |
| "preset": "fintech_fraud", | |
| "fields": 28, | |
| "decisions_identical": true, | |
| "upstream_json": { | |
| "is_fraudulent": true, | |
| "risk_tier": "HIGH", | |
| "recommended_action": "MANUAL_REVIEW", | |
| "primary_anomaly": "TOR_EXIT_NODE", | |
| "secondary_anomaly": "CARD_NOT_PRESENT", | |
| "requires_human_escalation": true, | |
| "can_auto_block": true, | |
| "aml_sar_filing_required": true, | |
| "fincen_flag_threshold": true, | |
| "sanctions_screening_risk": "HIGH_CONFIDENCE_MATCH", | |
| "tor_exit_node_detected": true, | |
| "device_fingerprint_mismatch": true, | |
| "velocity_score": "ELEVATED", | |
| "block_card_immediately": true, | |
| "freeze_online_banking": true, | |
| "notify_cardholder_sms": true, | |
| "notify_cardholder_email": true, | |
| "requires_identity_verification": true, | |
| "merchant_category_risk": "HIGH_RISK_CRYPTO", | |
| "chargeback_probability": "LOW", | |
| "counterparty_jurisdiction_risk": "TIER_1_LOW", | |
| "auto_reverse_transfer": true, | |
| "fraud_ring_association": true, | |
| "alert_clearing_house": true, | |
| "escalate_to_fiu": true, | |
| "confidence_score_tier": "HIGH_CONFIDENCE_FRAUD", | |
| "loss_prevention_priority": "LOW_PRIORITY", | |
| "account_takeover_suspected": true | |
| }, | |
| "release_json": { | |
| "is_fraudulent": true, | |
| "risk_tier": "HIGH", | |
| "recommended_action": "MANUAL_REVIEW", | |
| "primary_anomaly": "TOR_EXIT_NODE", | |
| "secondary_anomaly": "CARD_NOT_PRESENT", | |
| "requires_human_escalation": true, | |
| "can_auto_block": true, | |
| "aml_sar_filing_required": true, | |
| "fincen_flag_threshold": true, | |
| "sanctions_screening_risk": "HIGH_CONFIDENCE_MATCH", | |
| "tor_exit_node_detected": true, | |
| "device_fingerprint_mismatch": true, | |
| "velocity_score": "ELEVATED", | |
| "block_card_immediately": true, | |
| "freeze_online_banking": true, | |
| "notify_cardholder_sms": true, | |
| "notify_cardholder_email": true, | |
| "requires_identity_verification": true, | |
| "merchant_category_risk": "HIGH_RISK_CRYPTO", | |
| "chargeback_probability": "LOW", | |
| "counterparty_jurisdiction_risk": "TIER_1_LOW", | |
| "auto_reverse_transfer": true, | |
| "fraud_ring_association": true, | |
| "alert_clearing_house": true, | |
| "escalate_to_fiu": true, | |
| "confidence_score_tier": "HIGH_CONFIDENCE_FRAUD", | |
| "loss_prevention_priority": "LOW_PRIORITY", | |
| "account_takeover_suspected": true | |
| }, | |
| "collision_fields": [ | |
| "counterparty_jurisdiction_risk" | |
| ], | |
| "wall": { | |
| "upstream_batch": { | |
| "median_ms": 1467.4180835063453, | |
| "min_ms": 1438.9877909998177, | |
| "p90_ms": 1560.9218330064323, | |
| "samples_ms": [ | |
| 1455.4514170013135, | |
| 1438.9877909998177, | |
| 1462.3930829984602, | |
| 1473.0905829928815, | |
| 1472.4430840142304, | |
| 1560.9218330064323 | |
| ] | |
| }, | |
| "release_tree": { | |
| "median_ms": 1087.4221669946564, | |
| "min_ms": 1040.6132920033997, | |
| "p90_ms": 1166.4362079900457, | |
| "samples_ms": [ | |
| 1040.6132920033997, | |
| 1076.157166986377, | |
| 1060.7517919997917, | |
| 1098.687167002936, | |
| 1166.4362079900457, | |
| 1122.5379169918597 | |
| ] | |
| } | |
| }, | |
| "internal_stage_medians": { | |
| "upstream_batch": { | |
| "elapsed_ms": 1464.3400000000001, | |
| "prefill_ms": 822.0699999999999, | |
| "suffix_eval_ms": 637.77 | |
| }, | |
| "release_tree": { | |
| "elapsed_ms": 1087.355, | |
| "prefill_ms": 743.6800000000001, | |
| "suffix_eval_ms": 341.7 | |
| } | |
| }, | |
| "speedup": 1.3494465425161377, | |
| "speedup_ci95": [ | |
| 1.2865528429910673, | |
| 1.3885471507126947 | |
| ] | |
| } | |
| ] | |
| } | |