Instructions to use rodrigoramosrs/veriloop-coder-e2-nvfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rodrigoramosrs/veriloop-coder-e2-nvfp4 with Transformers:

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

pipe = pipeline("text-generation", model="rodrigoramosrs/veriloop-coder-e2-nvfp4")
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("rodrigoramosrs/veriloop-coder-e2-nvfp4")
model = AutoModelForCausalLM.from_pretrained("rodrigoramosrs/veriloop-coder-e2-nvfp4", 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 rodrigoramosrs/veriloop-coder-e2-nvfp4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rodrigoramosrs/veriloop-coder-e2-nvfp4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rodrigoramosrs/veriloop-coder-e2-nvfp4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rodrigoramosrs/veriloop-coder-e2-nvfp4

SGLang

How to use rodrigoramosrs/veriloop-coder-e2-nvfp4 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 "rodrigoramosrs/veriloop-coder-e2-nvfp4" \
    --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": "rodrigoramosrs/veriloop-coder-e2-nvfp4",
		"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 "rodrigoramosrs/veriloop-coder-e2-nvfp4" \
        --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": "rodrigoramosrs/veriloop-coder-e2-nvfp4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rodrigoramosrs/veriloop-coder-e2-nvfp4 with Docker Model Runner:
```
docker model run hf.co/rodrigoramosrs/veriloop-coder-e2-nvfp4
```

rodrigoramosrs commited on Sep 26

Commit

137dbc8

verified ·

1 Parent(s): 179ebf1

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +7 -5

README.md CHANGED Viewed

@@ -58,18 +58,20 @@ Quantized by [Rodrigo Ramos](https://github.com/rodrigoramosrs).
 ## Quantization Approach
-Produced with [NVIDIA Model Optimizer](https://github.com/NVIDIA/Model-Optimizer) using the canonical **`NVFP4_W4A4_WEIGHT_LOCAL_HESSIAN_CFG`** recipe, verbatim: static per-block 4-bit weights (group size 16) + dynamic 4-bit activations, FP8 attention, local-Hessian calibration with MSE and fp8 scale sweep.
 Calibration ran on **512 samples × 512 tokens** (262144 tokens) of competitive-programming code from `nvidia/Nemotron-Competitive-Programming-v1`, keeping quantization faithful on the distributions that matter most for coding tasks.
-The result retains the original model's strong software-engineering capabilities at roughly one third of the BF16 footprint, ready for NVFP4-capable inference stacks on Blackwell GPUs.
 ## Files
 | File | Size | Notes |
 |---|---|---|
-| `model-00001-of-00005.safetensors` … `model-00005-of-00005.safetensors` | ~17.5 GB total | NVFP4 weights (packed U8 + FP8 block scales) |
-| `model.safetensors.index.json` | — | Shard index (2051 tensors) |
 | `hf_quant_config.json` | — | `quant_algo: NVFP4`, group size 16 |
 | `config.json`, `tokenizer.*`, `merges.txt`, `vocab.json` | — | Config + tokenizer from the base model |
 | `scripts/quantize_veriloop.py` | — | Full reproduction script (multi-GPU PTQ) |
@@ -79,7 +81,7 @@ The result retains the original model's strong software-engineering capabilities
 This checkpoint targets **NVFP4-capable runtimes** (Blackwell GPUs). Plain `transformers` cannot load modelopt NVFP4 checkpoints directly.
-> **Compatibility note:** per the NVIDIA recipe, a small set of projections (`linear_attn.in_proj_a/b`, `conv1d`), plus the embeddings and `lm_head`, intentionally ship in BF16. The `exclude_modules` list in `hf_quant_config.json` (mirrored in `config.json`) declares exactly which modules those are — inference loaders must honor it and serve those modules unquantized. If a loader errors with *"weight is torch.bfloat16 but the quant config declares NVFP4"*, it is ignoring the exclusion list, not a checkpoint defect.
 ### vLLM

 ## Quantization Approach
+Produced with [NVIDIA Model Optimizer](https://github.com/NVIDIA/Model-Optimizer) using the canonical **`NVFP4_W4A4_WEIGHT_LOCAL_HESSIAN_CFG`** recipe: static per-block 4-bit weights (group size 16) + dynamic 4-bit activations, FP8 attention, local-Hessian calibration with MSE and fp8 scale sweep.
+The `linear_attn` (Gated Delta Net) blocks ship in BF16 on purpose — the same granularity as NVIDIA's official NVFP4 releases (e.g. `nvidia/Qwen3.5-397B-A17B-NVFP4`, which excludes `linear_attn*` per layer). Only self-attention, MLP and output projections are NVFP4. Embeddings, `lm_head` and small projections stay BF16 per the recipe.
 Calibration ran on **512 samples × 512 tokens** (262144 tokens) of competitive-programming code from `nvidia/Nemotron-Competitive-Programming-v1`, keeping quantization faithful on the distributions that matter most for coding tasks.
+The result retains the original model's strong software-engineering capabilities at roughly half of the BF16 footprint, ready for NVFP4-capable inference stacks on Blackwell GPUs.
 ## Files
 | File | Size | Notes |
 |---|---|---|
+| `model-00001-of-00007.safetensors` … `model-00007-of-00007.safetensors` | ~26.8 GB total | NVFP4 weights (packed U8 + FP8 block scales) + BF16 `linear_attn`/embeddings/head |
+| `model.safetensors.index.json` | — | Shard index (1619 tensors) |
 | `hf_quant_config.json` | — | `quant_algo: NVFP4`, group size 16 |
 | `config.json`, `tokenizer.*`, `merges.txt`, `vocab.json` | — | Config + tokenizer from the base model |
 | `scripts/quantize_veriloop.py` | — | Full reproduction script (multi-GPU PTQ) |
 This checkpoint targets **NVFP4-capable runtimes** (Blackwell GPUs). Plain `transformers` cannot load modelopt NVFP4 checkpoints directly.
+> **Compatibility note:** per the NVIDIA recipe, the `linear_attn` blocks, a small set of projections (`linear_attn.in_proj_a/b`, `conv1d`), plus the embeddings and `lm_head`, intentionally ship in BF16. The `exclude_modules` list in `hf_quant_config.json` (mirrored in `config.json`, including fused names such as `in_proj_ba`/`in_proj_qkvz` that some loaders synthesize) declares exactly which modules those are — inference loaders must honor it and serve those modules unquantized. If a loader errors with *"weight is torch.bfloat16 but the quant config declares NVFP4"*, it is ignoring the exclusion list, not a checkpoint defect.
 ### vLLM