Instructions to use continuum-ai/qwen2.5-coder-7b-compacted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use continuum-ai/qwen2.5-coder-7b-compacted 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("continuum-ai/qwen2.5-coder-7b-compacted")

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

How to use continuum-ai/qwen2.5-coder-7b-compacted with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "continuum-ai/qwen2.5-coder-7b-compacted"

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": "continuum-ai/qwen2.5-coder-7b-compacted"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use continuum-ai/qwen2.5-coder-7b-compacted with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "continuum-ai/qwen2.5-coder-7b-compacted"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "continuum-ai/qwen2.5-coder-7b-compacted"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "continuum-ai/qwen2.5-coder-7b-compacted",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use continuum-ai/qwen2.5-coder-7b-compacted 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 "continuum-ai/qwen2.5-coder-7b-compacted"

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 continuum-ai/qwen2.5-coder-7b-compacted

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use continuum-ai/qwen2.5-coder-7b-compacted with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "continuum-ai/qwen2.5-coder-7b-compacted"

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 "continuum-ai/qwen2.5-coder-7b-compacted" \
  --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"

qwen2.5-coder-7b-compacted

Commit History

Apr 11

17:16
fix: use hf.co (CORS-open) in verify URLs

EnricoFermi

Verified signature
e1acab4
16:53
fix: verify URL uses source@hash for direct fetch (no search needed)

EnricoFermi

Verified signature
9c4204d

Apr 9

04:34
Regenerate QR for new verify URL (4fe422e9b01fa8f0)

EnricoFermi

Verified signature
4d7b3ff
04:34
Regenerate model card from corrected alloy (alloyHash 4fe422e9b01fa8f0)

EnricoFermi

Verified signature
6ab6114
04:34
Correct v2-7b-coder-compensated.alloy.json pass@1 to canonical evalplus convention (v1.2.1)

EnricoFermi

Verified signature
a2e77c7

Apr 8

16:39
card: footer v3 — OLMoE shipped + §4.1.3.4.1 discipline gate

EnricoFermi

Verified signature
49cffac
15:54
card: refresh footer with comprehensive forge queue (10 architectures)

EnricoFermi

Verified signature
f8e8bd4
15:07
card: rename to qwen2.5-coder-7b-compacted source-aligned + org front-door footer

EnricoFermi

Verified signature
00c09bc
05:03
Upload README.md with huggingface_hub

EnricoFermi

Verified signature
7e5e130
05:03
Upload MODEL_METHODOLOGY.md with huggingface_hub

EnricoFermi

Verified signature
0abc8fe
05:03
Upload alloy-qr.png with huggingface_hub

EnricoFermi

Verified signature
decd729
05:03
Upload v2-7b-coder-compensated.alloy.json with huggingface_hub

EnricoFermi

Verified signature
d5ac309
05:02
Upload README.md with huggingface_hub

EnricoFermi

Verified signature
c117684
05:02
Upload MODEL_METHODOLOGY.md with huggingface_hub

EnricoFermi

Verified signature
98ebeb2
05:02
Upload alloy-qr.png with huggingface_hub

EnricoFermi

Verified signature
f0cdd38
05:02
Upload v2-7b-coder-compensated.alloy.json with huggingface_hub

EnricoFermi

Verified signature
df4efa2
04:54
Upload README.md with huggingface_hub

EnricoFermi

Verified signature
25cf91b
04:54
Upload alloy-qr.png with huggingface_hub

EnricoFermi

Verified signature
ef20ccc
04:54
Upload v2-7b-coder-compensated.alloy.json with huggingface_hub

EnricoFermi

Verified signature
05f837f
04:54
Upload eval/humaneval/humaneval_samples.jsonl with huggingface_hub

EnricoFermi

Verified signature
c786f9f
04:54
Upload eval/calibrated_eval_results.json with huggingface_hub

EnricoFermi

Verified signature
c8371e7
04:51
card: rich prose (about + journey + ablation + stage notes)

EnricoFermi

Verified signature
b099f13
04:45
Upload README.md with huggingface_hub

EnricoFermi

Verified signature
abe8eb5
04:45
Upload alloy-qr.png with huggingface_hub

EnricoFermi

Verified signature
3ff567f
04:45
Upload v2-7b-coder-compensated.alloy.json with huggingface_hub

EnricoFermi

Verified signature
3e1f331
04:45
Upload chat_template.jinja with huggingface_hub

EnricoFermi

Verified signature
f26596b
04:45
Upload generation_config.json with huggingface_hub

EnricoFermi

Verified signature
8b1f22a
04:45
Upload tokenizer_config.json with huggingface_hub

EnricoFermi

Verified signature
acb4dac
04:45
Upload tokenizer.json with huggingface_hub

EnricoFermi

Verified signature
83c79de
04:45
Upload config.json with huggingface_hub

EnricoFermi

Verified signature
c1c740d
04:45
Upload model.safetensors with huggingface_hub

EnricoFermi

Verified signature
81d999a
04:41
initial commit

EnricoFermi

Verified signature
4c1a3d7

Commit History

Apr 11

fix: use hf.co (CORS-open) in verify URLs

fix: verify URL uses source@hash for direct fetch (no search needed)

Apr 9

Regenerate QR for new verify URL (4fe422e9b01fa8f0)

Regenerate model card from corrected alloy (alloyHash 4fe422e9b01fa8f0)

Correct v2-7b-coder-compensated.alloy.json pass@1 to canonical evalplus convention (v1.2.1)

Apr 8

card: footer v3 — OLMoE shipped + §4.1.3.4.1 discipline gate

card: refresh footer with comprehensive forge queue (10 architectures)

card: rename to qwen2.5-coder-7b-compacted source-aligned + org front-door footer

Upload README.md with huggingface_hub

Upload MODEL_METHODOLOGY.md with huggingface_hub

Upload alloy-qr.png with huggingface_hub

Upload v2-7b-coder-compensated.alloy.json with huggingface_hub

Upload README.md with huggingface_hub

Upload MODEL_METHODOLOGY.md with huggingface_hub

Upload alloy-qr.png with huggingface_hub

Upload v2-7b-coder-compensated.alloy.json with huggingface_hub

Upload README.md with huggingface_hub

Upload alloy-qr.png with huggingface_hub

Upload v2-7b-coder-compensated.alloy.json with huggingface_hub

Upload eval/humaneval/humaneval_samples.jsonl with huggingface_hub

Upload eval/calibrated_eval_results.json with huggingface_hub

card: rich prose (about + journey + ablation + stage notes)

Upload README.md with huggingface_hub

Upload alloy-qr.png with huggingface_hub

Upload v2-7b-coder-compensated.alloy.json with huggingface_hub

Upload chat_template.jinja with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload config.json with huggingface_hub

Upload model.safetensors with huggingface_hub

initial commit