Instructions to use lewisdog/qwen3-1.7b-cogs-ask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lewisdog/qwen3-1.7b-cogs-ask with Transformers:

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

pipe = pipeline("text-generation", model="lewisdog/qwen3-1.7b-cogs-ask")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lewisdog/qwen3-1.7b-cogs-ask")
model = AutoModelForCausalLM.from_pretrained("lewisdog/qwen3-1.7b-cogs-ask")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use lewisdog/qwen3-1.7b-cogs-ask 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("lewisdog/qwen3-1.7b-cogs-ask")

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

vLLM

How to use lewisdog/qwen3-1.7b-cogs-ask with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lewisdog/qwen3-1.7b-cogs-ask"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lewisdog/qwen3-1.7b-cogs-ask",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lewisdog/qwen3-1.7b-cogs-ask

SGLang

How to use lewisdog/qwen3-1.7b-cogs-ask 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 "lewisdog/qwen3-1.7b-cogs-ask" \
    --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": "lewisdog/qwen3-1.7b-cogs-ask",
		"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 "lewisdog/qwen3-1.7b-cogs-ask" \
        --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": "lewisdog/qwen3-1.7b-cogs-ask",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use lewisdog/qwen3-1.7b-cogs-ask with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lewisdog/qwen3-1.7b-cogs-ask"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lewisdog/qwen3-1.7b-cogs-ask"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lewisdog/qwen3-1.7b-cogs-ask 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 "lewisdog/qwen3-1.7b-cogs-ask"

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 lewisdog/qwen3-1.7b-cogs-ask

Run Hermes

hermes

OpenClaw new

How to use lewisdog/qwen3-1.7b-cogs-ask with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lewisdog/qwen3-1.7b-cogs-ask"

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 "lewisdog/qwen3-1.7b-cogs-ask" \
  --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"

MLX LM

How to use lewisdog/qwen3-1.7b-cogs-ask with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "lewisdog/qwen3-1.7b-cogs-ask"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "lewisdog/qwen3-1.7b-cogs-ask"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "lewisdog/qwen3-1.7b-cogs-ask",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use lewisdog/qwen3-1.7b-cogs-ask with Docker Model Runner:
```
docker model run hf.co/lewisdog/qwen3-1.7b-cogs-ask
```

qwen3-1.7b-cogs-ask

Merged full model (Qwen/Qwen3-1.7B + LoRA, fused, bf16) — the student model for the cogs ask pipeline. Standalone adapter: lewisdog/qwen3-1.7b-cogs-ask-lora. Sibling model for the ingest pipeline: lewisdog/qwen3-1.7b-cogs-ingest.

Two tasks, both emitting compact JSON exactly as the cogs runtime parses it:

task	output JSON
`decompose`	`{"subquestions": [...]}` — question → 1-4 sub-questions
`synthesize`	`{"answer": "... [note-id] ...", "citations": [...], "abstained": bool}` — grounded answer over retrieved notes; abstains on out-of-domain questions

Eval (full 63-record valid set, temp 0, repetition_penalty 1.1)

JSON parse: 100% · decompose non-empty: 100%
synthesize citation-validity: 77% (→ ~90% with the prefix-repair below)
abstention preserved: 100% · false-abstention: 4%

Apple silicon (MLX / omlx)

python3 -m mlx_lm.convert --hf-path lewisdog/qwen3-1.7b-cogs-ask -q --q-bits 8 --mlx-path qwen3-cogs-ask-mlx
# NOTE: if transformers writes v5-format configs, backfill rope_theta / rope_scaling /
# torch_dtype from the base Qwen3-1.7B config and swap in the original Qwen3-1.7B
# tokenizer files before converting. Wire as [llm.ask] in cogs.toml.

⚠️ Serving notes

Decode at temp 0 + repetition_penalty=1.1 (pure greedy runs away on long list outputs), enable_thinking=False, stop on <|im_end|>.

Repair citation prefixes. Most citation errors are a dropped/wrong namespace prefix (enisa-… → sources-enisa-…). Normalize against the notes actually in the prompt and drop anything unverifiable:

PFX = ("sources-", "source-", "concepts-", "concept-", "entities-", "entity-")
core = lambda x: next((x[len(p):] for p in PFX if x.startswith(p)), x)
def repair(cite, note_ids):
    if cite in note_ids: return cite
    return {core(n): n for n in note_ids}.get(core(cite))   # None => drop it

Abstention is reliable — trust it to decline out-of-domain questions.

Training

LoRA r=32/α=64, 5 epochs, eff. batch 16, max_seq 8192, lr 1e-4 cosine, bf16, on a DGX Spark (GB10). Data: cogs distill ask pairs (475 base + abstentions oversampled 3×). Eval loss 1.906 → 0.758; eval token-acc 0.836. Full write-up in the repo RESULTS.md.

PEFT 0.19.1 · TRL 1.7.1 · Transformers 5.13.0 · PyTorch 2.12.1+cu130

Downloads last month: 162

Safetensors

Model size

2B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for lewisdog/qwen3-1.7b-cogs-ask

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Finetuned

(886)

this model