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"

EnricoFermi commited on Apr 8

Commit

df4efa2

verified ·

1 Parent(s): 25cf91b

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

Browse files

Files changed (1) hide show

v2-7b-coder-compensated.alloy.json +10 -3

v2-7b-coder-compensated.alloy.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "name": "v2-7b-coder-compensated",
-  "version": "1.1.0",
   "description": "Methodology validation artifact for the v2 forge pipeline + KL-distillation compensation LoRA. Demonstrates that aggressive head pruning + activation-metric importance + pad-mode defrag, when paired with output-distribution distillation against the unmodified teacher, recovers near-base HumanEval capability (61.0 vs 62.2 base, within calibration tolerance). This is the empirical anchor for PLASTICITY-COMPACTION \u00a74.1.3.3 and the loss-function ablation that closes the \u00a74.1.3.2 PPL/HumanEval disconnect. NOT a Pareto improvement over the unmodified base 7B at any single VRAM tier \u2014 published as proof that the methodology stack works end-to-end, in preparation for the Qwen3.5-35B-A3B and 397B-A17B forges where the pruning dimension actually wins.",
   "author": "continuum-ai",
   "tags": [
@@ -179,14 +179,21 @@
       "trustLevel": "self-attested"
     }
   },
   "receipt": {
     "publications": [
       {
         "target": "huggingface",
         "url": "https://huggingface.co/continuum-ai/v2-7b-coder-compensated",
-        "publishedAt": "2026-04-08T04:54:26.954862+00:00"
       }
     ],
-    "issuedAt": "2026-04-08T04:54:26.954862+00:00"
   }
 }

 {
   "name": "v2-7b-coder-compensated",
+  "version": "1.2.0",
   "description": "Methodology validation artifact for the v2 forge pipeline + KL-distillation compensation LoRA. Demonstrates that aggressive head pruning + activation-metric importance + pad-mode defrag, when paired with output-distribution distillation against the unmodified teacher, recovers near-base HumanEval capability (61.0 vs 62.2 base, within calibration tolerance). This is the empirical anchor for PLASTICITY-COMPACTION \u00a74.1.3.3 and the loss-function ablation that closes the \u00a74.1.3.2 PPL/HumanEval disconnect. NOT a Pareto improvement over the unmodified base 7B at any single VRAM tier \u2014 published as proof that the methodology stack works end-to-end, in preparation for the Qwen3.5-35B-A3B and 397B-A17B forges where the pruning dimension actually wins.",
   "author": "continuum-ai",
   "tags": [
       "trustLevel": "self-attested"
     }
   },
+  "methodologyPaperUrl": "https://github.com/CambrianTech/continuum/blob/main/docs/papers/PLASTICITY-COMPACTION.md",
+  "limitations": [
+    "This model is currently a methodology demonstration rather than a Pareto-optimal artifact at any specific hardware tier. For production code workloads on smaller hardware, the unmodified Qwen2.5-Coder-7B at standard quantization (Q4_K_M / Q5_K_M / Q8_0) may be a better fit pending the larger Qwen3.5+ forges that exercise the pruning dimension where this methodology actually wins.",
+    "Validated on HumanEval / HumanEval+ for English-language Python code completion. Performance on other programming languages, code paradigms (functional, embedded, kernel), or code-adjacent domains (SQL, regex, shell) has not been measured.",
+    "Ships as fp16 only. GGUF quantization tiers (Q5_K_S / Q3_K_M / Q2_K) are not yet published for this artifact; the per-tier comparison from the development log showed base+quant dominates v2+quant at every VRAM tier on the same 7B base, which is why the methodology validation here uses fp16 and the production GGUF publishes are reserved for the Qwen3.5+ forges where the dimension flips.",
+    "Vision modality not yet wired in. The Continuum sensory architecture treats vision as first-class for personas, but this 7B coder artifact is text-only."
+  ],
   "receipt": {
     "publications": [
       {
         "target": "huggingface",
         "url": "https://huggingface.co/continuum-ai/v2-7b-coder-compensated",
+        "publishedAt": "2026-04-08T05:01:40.446154+00:00"
       }
     ],
+    "issuedAt": "2026-04-08T05:01:40.446154+00:00"
   }
 }