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

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

Qwen-2.5-1B-RLCD-Fast / mac_mps_continuation.json

epsilon3

Add tree-attention fast path and CUDA/M4 benchmarks

f36843f verified about 1 month ago

Raw History Blame Contribute Delete

3.52 kB

{
  "environment": {
    "model": "Qwen/Qwen2.5-1.5B-Instruct",
    "revision": "989aa7980e4cf806f80c7fef2b1adb7bc71aa306",
    "torch": "2.11.0",
    "transformers": "4.57.6",
    "gpu": "mps",
    "platform": "macOS-26.6.2-arm64-arm-64bit",
    "dtype": "torch.float16",
    "attention": "sdpa"
  },
  "arguments": {
    "model": "Qwen/Qwen2.5-1.5B-Instruct",
    "presets": [
      "fintech_fraud"
    ],
    "fields": [
      4
    ],
    "steps": 4,
    "repeats": 8,
    "warmup": 2,
    "output": "mac_mps_continuation.json",
    "device": "mps",
    "dtype": "float16"
  },
  "cases": [
    {
      "preset": "fintech_fraud",
      "fields": 4,
      "prefix_tokens": 291,
      "suffix_tokens": 28,
      "batch_padded_tokens": 32,
      "correctness": {
        "max_abs_logit_error": 0.0390625,
        "mean_abs_logit_error": 0.005111373495310545,
        "full_vocab_argmax_agreement": 1.0,
        "candidate_decisions_equal": true,
        "candidate_disagreements": [],
        "candidate_collision_fields": []
      },
      "decode": {
        "batch": {
          "median_ms": 222.27393699722597,
          "min_ms": 218.0314580036793,
          "p90_ms": 225.18500000296626,
          "samples_ms": [
            218.92137500981335,
            218.0314580036793,
            218.31691700208467,
            221.5709159936523,
            222.97695800079964,
            225.18500000296626,
            224.5981669984758,
            223.11737500422169
          ]
        },
        "tree": {
          "median_ms": 92.20895849284716,
          "min_ms": 91.14341699751094,
          "p90_ms": 93.54945798986591,
          "samples_ms": [
            91.56537499802653,
            91.14341699751094,
            92.22362498985603,
            91.70979099872056,
            92.8215000021737,
            93.54945798986591,
            92.19429199583828,
            92.9221249971306
          ]
        }
      },
      "end_to_end": {
        "batch": {
          "median_ms": 363.8185415038606,
          "min_ms": 360.70520800421946,
          "p90_ms": 368.3792500087293,
          "samples_ms": [
            362.8430419921642,
            364.4052500021644,
            360.70520800421946,
            366.33004099712707,
            368.3792500087293,
            361.49850000219885,
            363.23183300555684,
            364.8465419973945
          ]
        },
        "tree": {
          "median_ms": 236.11554150556913,
          "min_ms": 235.26033300731797,
          "p90_ms": 242.17433400917798,
          "samples_ms": [
            235.6036670098547,
            236.22883300413378,
            237.20962500374299,
            235.26033300731797,
            242.17433400917798,
            236.00225000700448,
            235.61708399211057,
            237.31533299724106
          ]
        }
      },
      "memory": {
        "batch": {
          "driver_high_water_mib": 3372.140625,
          "extra_driver_mib": 204.0
        },
        "tree": {
          "driver_high_water_mib": 3196.140625,
          "extra_driver_mib": 40.0
        }
      },
      "decode_speedup": 2.410546010173927,
      "end_to_end_speedup": 1.5408496161836913,
      "decode_speedup_ci95": [
        2.370532995531195,
        2.427722584229317
      ],
      "end_to_end_speedup_ci95": [
        1.5291795474631322,
        1.5495758989220285
      ]
    }
  ]
}

	{
	"environment": {
	"model": "Qwen/Qwen2.5-1.5B-Instruct",
	"revision": "989aa7980e4cf806f80c7fef2b1adb7bc71aa306",
	"torch": "2.11.0",
	"transformers": "4.57.6",
	"gpu": "mps",
	"platform": "macOS-26.6.2-arm64-arm-64bit",
	"dtype": "torch.float16",
	"attention": "sdpa"
	},
	"arguments": {
	"model": "Qwen/Qwen2.5-1.5B-Instruct",
	"presets": [
	"fintech_fraud"
	],
	"fields": [
	4
	],
	"steps": 4,
	"repeats": 8,
	"warmup": 2,
	"output": "mac_mps_continuation.json",
	"device": "mps",
	"dtype": "float16"
	},
	"cases": [
	{
	"preset": "fintech_fraud",
	"fields": 4,
	"prefix_tokens": 291,
	"suffix_tokens": 28,
	"batch_padded_tokens": 32,
	"correctness": {
	"max_abs_logit_error": 0.0390625,
	"mean_abs_logit_error": 0.005111373495310545,
	"full_vocab_argmax_agreement": 1.0,
	"candidate_decisions_equal": true,
	"candidate_disagreements": [],
	"candidate_collision_fields": []
	},
	"decode": {
	"batch": {
	"median_ms": 222.27393699722597,
	"min_ms": 218.0314580036793,
	"p90_ms": 225.18500000296626,
	"samples_ms": [
	218.92137500981335,
	218.0314580036793,
	218.31691700208467,
	221.5709159936523,
	222.97695800079964,
	225.18500000296626,
	224.5981669984758,
	223.11737500422169
	]
	},
	"tree": {
	"median_ms": 92.20895849284716,
	"min_ms": 91.14341699751094,
	"p90_ms": 93.54945798986591,
	"samples_ms": [
	91.56537499802653,
	91.14341699751094,
	92.22362498985603,
	91.70979099872056,
	92.8215000021737,
	93.54945798986591,
	92.19429199583828,
	92.9221249971306
	]
	}
	},
	"end_to_end": {
	"batch": {
	"median_ms": 363.8185415038606,
	"min_ms": 360.70520800421946,
	"p90_ms": 368.3792500087293,
	"samples_ms": [
	362.8430419921642,
	364.4052500021644,
	360.70520800421946,
	366.33004099712707,
	368.3792500087293,
	361.49850000219885,
	363.23183300555684,
	364.8465419973945
	]
	},
	"tree": {
	"median_ms": 236.11554150556913,
	"min_ms": 235.26033300731797,
	"p90_ms": 242.17433400917798,
	"samples_ms": [
	235.6036670098547,
	236.22883300413378,
	237.20962500374299,
	235.26033300731797,
	242.17433400917798,
	236.00225000700448,
	235.61708399211057,
	237.31533299724106
	]
	}
	},
	"memory": {
	"batch": {
	"driver_high_water_mib": 3372.140625,
	"extra_driver_mib": 204.0
	},
	"tree": {
	"driver_high_water_mib": 3196.140625,
	"extra_driver_mib": 40.0
	}
	},
	"decode_speedup": 2.410546010173927,
	"end_to_end_speedup": 1.5408496161836913,
	"decode_speedup_ci95": [
	2.370532995531195,
	2.427722584229317
	],
	"end_to_end_speedup_ci95": [
	1.5291795474631322,
	1.5495758989220285
	]
	}
	]
	}