Instructions to use aksern/compctx-0.8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aksern/compctx-0.8b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="aksern/compctx-0.8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aksern/compctx-0.8b")
model = AutoModelForCausalLM.from_pretrained("aksern/compctx-0.8b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aksern/compctx-0.8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aksern/compctx-0.8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aksern/compctx-0.8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aksern/compctx-0.8b

SGLang

How to use aksern/compctx-0.8b 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 "aksern/compctx-0.8b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aksern/compctx-0.8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "aksern/compctx-0.8b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aksern/compctx-0.8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aksern/compctx-0.8b with Docker Model Runner:
```
docker model run hf.co/aksern/compctx-0.8b
```

akaruineko commited on 3 days ago

Commit

cb59dea

verified ·

1 Parent(s): e331dfb

Update README.md

Browse files

Files changed (1) hide show

README.md +36 -19

README.md CHANGED Viewed

@@ -3,12 +3,14 @@ license: openmdw-1.1
 library_name: transformers
 pipeline_tag: text-generation
 tags:
-  - qwen3.5
-  - text-generation
-  - agent-memory
-  - trace-summarization
-  - text-only
-  - lora
 ---
 # compctx-0.8b
@@ -66,35 +68,51 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 trace = """
-[user] Fix the error in script.py.
-[assistant] Reading the file.
-[tool_call] view_file(path="script.py")
-[tool_result] print('Hello' + 5)
-[assistant] Fixing the expression.
-[tool_call] edit_file(path="script.py")
-[tool_result] OK
 """
 messages = [
     {"role": "user", "content": trace},
 ]
-inputs = tokenizer.apply_chat_template(
     messages,
-    tokenize=True,
     add_generation_prompt=True,
     return_tensors="pt",
 ).to(model.device)
 with torch.inference_mode():
     output = model.generate(
-        inputs,
         max_new_tokens=512,
         do_sample=False,
     )
 result = tokenizer.decode(
-    output[0][inputs.shape[1]:],
     skip_special_tokens=True,
 )
@@ -122,7 +140,6 @@ The chat template automatically:
 ## Limitations
 - Not a general-purpose conversational assistant.
-- Accepts text traces only; images and video are not supported.
 - Designed around the specific structured output format above.
 - Accuracy depends on the information available in the input trace.
 - May omit details when the input exceeds its context or output budget.
@@ -137,4 +154,4 @@ The resulting adapter was merged into a standalone text-only checkpoint.
 ## License
-This model is based on Qwen3.5-0.8B. Check the base model's license and applicable terms before redistribution or commercial use. The license for this model is OpenMDW-1.1

 library_name: transformers
 pipeline_tag: text-generation
 tags:
+- qwen3.5
+- text-generation
+- agent-memory
+- trace-summarization
+- text-only
+- lora
+base_model:
+- Qwen/Qwen3.5-0.8B
 ---
 # compctx-0.8b
 )
 trace = """
+[TRACE] [2026-10-30 06:24:00] [AGENT: Orchestrator]
+User Prompt: "Find the errors in the file script.py and fix them."
+[SPAN] [Thinking Process]
+"To solve the task, I first need to read the contents of the file script.py. I will use the view_file tool."
+[SPAN] [Tool Call: view_file]
+Arguments: {"path": "script.py"}
+Response: "def main():\n  print('Hello' + 5)"
+[SPAN] [Thinking Process]
+"There is a TypeError in the code: you cannot add a string and a number together. You need to replace 5 with '5' or use an f-string. I am invoking the patch_file tool."
+[SPAN] [Tool Call: patch_file]
+Arguments: {"path": "script.py", "edit": "print(f'Hello {5}')"}
+Response: "File patched successfully."
+[TRACE END] Agent completed the task.
 """
 messages = [
     {"role": "user", "content": trace},
 ]
+prompt = tokenizer.apply_chat_template(
     messages,
+    tokenize=False,
     add_generation_prompt=True,
+)
+inputs = tokenizer(
+    prompt,
     return_tensors="pt",
+    add_special_tokens=False,
 ).to(model.device)
 with torch.inference_mode():
     output = model.generate(
+        **inputs,
         max_new_tokens=512,
         do_sample=False,
     )
 result = tokenizer.decode(
+    output[0][inputs["input_ids"].shape[1]:],
     skip_special_tokens=True,
 )
 ## Limitations
 - Not a general-purpose conversational assistant.
 - Designed around the specific structured output format above.
 - Accuracy depends on the information available in the input trace.
 - May omit details when the input exceeds its context or output budget.
 ## License
+This model is based on Qwen3.5-0.8B. Check the base model's license and applicable terms before redistribution or commercial use. The license for this model is OpenMDW-1.1