Text Generation
Transformers
Safetensors
qwen3_5
image-text-to-text
veriloop
auto-round
community-quantization
experimental
conversational
4-bit precision
Instructions to use bowmanslayer/VeriLoop-E2-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bowmanslayer/VeriLoop-E2-W4A16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bowmanslayer/VeriLoop-E2-W4A16") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("bowmanslayer/VeriLoop-E2-W4A16") model = AutoModelForMultimodalLM.from_pretrained("bowmanslayer/VeriLoop-E2-W4A16", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use bowmanslayer/VeriLoop-E2-W4A16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bowmanslayer/VeriLoop-E2-W4A16" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bowmanslayer/VeriLoop-E2-W4A16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/bowmanslayer/VeriLoop-E2-W4A16
- SGLang
How to use bowmanslayer/VeriLoop-E2-W4A16 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 "bowmanslayer/VeriLoop-E2-W4A16" \ --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": "bowmanslayer/VeriLoop-E2-W4A16", "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 "bowmanslayer/VeriLoop-E2-W4A16" \ --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": "bowmanslayer/VeriLoop-E2-W4A16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use bowmanslayer/VeriLoop-E2-W4A16 with Docker Model Runner:
docker model run hf.co/bowmanslayer/VeriLoop-E2-W4A16
Release unmodified quantization with complete saved evaluation metrics and historical reference
711ed9f verified Download evaluation.json from bowmanslayer/VeriLoop-E2-W4A16: direct link, hf CLI and curl.
- Browser
- Download file 13.5 kB
-
https://huggingface.co/bowmanslayer/VeriLoop-E2-W4A16/resolve/main/evaluation.json
- Command line
-
hf download hf://bowmanslayer/VeriLoop-E2-W4A16/evaluation.json
-
curl -L -o evaluation.json https://huggingface.co/bowmanslayer/VeriLoop-E2-W4A16/resolve/main/evaluation.json
13.5 kB
| { | |
| "scope": "paired local legacy rubric; thinking enabled, publisher raw-content protocol; not official benchmark reproduction", | |
| "formats": { | |
| "w4a16": { | |
| "n": 1514, | |
| "hits": [ | |
| 1212, | |
| 1157 | |
| ], | |
| "accuracy_pct": [ | |
| 80.05284015852048, | |
| 76.42007926023778 | |
| ], | |
| "delta_pp": -3.6327608982826947, | |
| "paired_95ci_pp": [ | |
| -5.894, | |
| -1.371 | |
| ], | |
| "lost": 181, | |
| "gained": 126, | |
| "empty": [ | |
| 9, | |
| 8 | |
| ], | |
| "reasoning_present": [ | |
| 1186, | |
| 1007 | |
| ], | |
| "length_limited": [ | |
| 9, | |
| 8 | |
| ], | |
| "valid_empty_gate": false, | |
| "tasks": [ | |
| { | |
| "task": "mmlu", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 2 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 126, | |
| "hits_ablated": 114, | |
| "delta_pp": -8.0, | |
| "paired_95ci_pp": [ | |
| -15.065, | |
| -0.935 | |
| ], | |
| "lost": 21, | |
| "gained": 9 | |
| }, | |
| { | |
| "task": "cmmlu", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 127, | |
| "hits_ablated": 113, | |
| "delta_pp": -9.333333333333334, | |
| "paired_95ci_pp": [ | |
| -15.848, | |
| -2.818 | |
| ], | |
| "lost": 20, | |
| "gained": 6 | |
| }, | |
| { | |
| "task": "mmlu_pro", | |
| "n": 150, | |
| "empty": [ | |
| 3, | |
| 1 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 118, | |
| "hits_ablated": 106, | |
| "delta_pp": -8.0, | |
| "paired_95ci_pp": [ | |
| -15.304, | |
| -0.696 | |
| ], | |
| "lost": 22, | |
| "gained": 10 | |
| }, | |
| { | |
| "task": "ceval", | |
| "n": 150, | |
| "empty": [ | |
| 1, | |
| 1 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 126, | |
| "hits_ablated": 114, | |
| "delta_pp": -8.0, | |
| "paired_95ci_pp": [ | |
| -14.817, | |
| -1.183 | |
| ], | |
| "lost": 20, | |
| "gained": 8 | |
| }, | |
| { | |
| "task": "arc", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 121, | |
| "hits_ablated": 128, | |
| "delta_pp": 4.666666666666667, | |
| "paired_95ci_pp": [ | |
| -2.354, | |
| 11.687 | |
| ], | |
| "lost": 11, | |
| "gained": 18 | |
| }, | |
| { | |
| "task": "truthfulqa", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 88, | |
| "hits_ablated": 107, | |
| "delta_pp": 12.666666666666666, | |
| "paired_95ci_pp": [ | |
| 3.341, | |
| 21.992 | |
| ], | |
| "lost": 17, | |
| "gained": 36 | |
| }, | |
| { | |
| "task": "gsm8k", | |
| "n": 100, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 95, | |
| "hits_ablated": 88, | |
| "delta_pp": -7.0, | |
| "paired_95ci_pp": [ | |
| -14.504, | |
| 0.504 | |
| ], | |
| "lost": 11, | |
| "gained": 4 | |
| }, | |
| { | |
| "task": "math500", | |
| "n": 100, | |
| "empty": [ | |
| 0, | |
| 2 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 75, | |
| "hits_ablated": 73, | |
| "delta_pp": -2.0, | |
| "paired_95ci_pp": [ | |
| -7.558, | |
| 3.558 | |
| ], | |
| "lost": 5, | |
| "gained": 3 | |
| }, | |
| { | |
| "task": "bbh", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 1 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 113, | |
| "hits_ablated": 98, | |
| "delta_pp": -10.0, | |
| "paired_95ci_pp": [ | |
| -18.028, | |
| -1.972 | |
| ], | |
| "lost": 27, | |
| "gained": 12 | |
| }, | |
| { | |
| "task": "humaneval", | |
| "n": 164, | |
| "empty": [ | |
| 5, | |
| 1 | |
| ], | |
| "valid_empty_gate": false, | |
| "hits_original": 147, | |
| "hits_ablated": 147, | |
| "delta_pp": 0.0, | |
| "paired_95ci_pp": [ | |
| -5.086, | |
| 5.086 | |
| ], | |
| "lost": 9, | |
| "gained": 9 | |
| }, | |
| { | |
| "task": "ifeval", | |
| "n": 100, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 76, | |
| "hits_ablated": 69, | |
| "delta_pp": -7.0, | |
| "paired_95ci_pp": [ | |
| -17.518, | |
| 3.518 | |
| ], | |
| "lost": 18, | |
| "gained": 11 | |
| } | |
| ], | |
| "refusal": { | |
| "valid": [ | |
| true, | |
| true | |
| ], | |
| "counts": [ | |
| { | |
| "substring_any": 98, | |
| "substring_head": 98, | |
| "heretic33_any": 98, | |
| "ega26_any": 98, | |
| "short": 0, | |
| "empty": 0, | |
| "empty_but_reasoning": 0, | |
| "reasoning_leaked": 0, | |
| "errors": 0 | |
| }, | |
| { | |
| "substring_any": 2, | |
| "substring_head": 0, | |
| "heretic33_any": 69, | |
| "ega26_any": 55, | |
| "short": 0, | |
| "empty": 0, | |
| "empty_but_reasoning": 0, | |
| "reasoning_leaked": 0, | |
| "errors": 0 | |
| } | |
| ], | |
| "max_tokens": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "budget_hits": [ | |
| 1, | |
| 9 | |
| ], | |
| "head_relative_reduction": 1.0, | |
| "words": [ | |
| { | |
| "median": 133.0, | |
| "mean": 193.5, | |
| "min": 54, | |
| "max": 861, | |
| "p10": 81 | |
| }, | |
| { | |
| "median": 726.0, | |
| "mean": 716.2, | |
| "min": 82, | |
| "max": 1288, | |
| "p10": 450 | |
| } | |
| ], | |
| "heldout84": { | |
| "n": 84, | |
| "head_counts": [ | |
| 82, | |
| 0 | |
| ], | |
| "any_counts": [ | |
| 82, | |
| 2 | |
| ] | |
| } | |
| } | |
| }, | |
| "gguf": { | |
| "n": 1514, | |
| "hits": [ | |
| 995, | |
| 1039 | |
| ], | |
| "accuracy_pct": [ | |
| 65.71994715984148, | |
| 68.62615587846764 | |
| ], | |
| "delta_pp": 2.906208718626156, | |
| "paired_95ci_pp": [ | |
| 0.956, | |
| 4.856 | |
| ], | |
| "lost": 92, | |
| "gained": 136, | |
| "empty": [ | |
| 4, | |
| 7 | |
| ], | |
| "reasoning_present": [ | |
| 741, | |
| 782 | |
| ], | |
| "length_limited": [ | |
| 4, | |
| 7 | |
| ], | |
| "valid_empty_gate": true, | |
| "tasks": [ | |
| { | |
| "task": "mmlu", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 102, | |
| "hits_ablated": 102, | |
| "delta_pp": 0.0, | |
| "paired_95ci_pp": [ | |
| -6.149, | |
| 6.149 | |
| ], | |
| "lost": 11, | |
| "gained": 11 | |
| }, | |
| { | |
| "task": "cmmlu", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 92, | |
| "hits_ablated": 97, | |
| "delta_pp": 3.3333333333333335, | |
| "paired_95ci_pp": [ | |
| -3.707, | |
| 10.373 | |
| ], | |
| "lost": 12, | |
| "gained": 17 | |
| }, | |
| { | |
| "task": "mmlu_pro", | |
| "n": 150, | |
| "empty": [ | |
| 1, | |
| 1 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 96, | |
| "hits_ablated": 103, | |
| "delta_pp": 4.666666666666667, | |
| "paired_95ci_pp": [ | |
| -2.104, | |
| 11.438 | |
| ], | |
| "lost": 10, | |
| "gained": 17 | |
| }, | |
| { | |
| "task": "ceval", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 1 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 90, | |
| "hits_ablated": 105, | |
| "delta_pp": 10.0, | |
| "paired_95ci_pp": [ | |
| 3.644, | |
| 16.356 | |
| ], | |
| "lost": 5, | |
| "gained": 20 | |
| }, | |
| { | |
| "task": "arc", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 135, | |
| "hits_ablated": 137, | |
| "delta_pp": 1.3333333333333333, | |
| "paired_95ci_pp": [ | |
| -2.807, | |
| 5.474 | |
| ], | |
| "lost": 4, | |
| "gained": 6 | |
| }, | |
| { | |
| "task": "truthfulqa", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 91, | |
| "hits_ablated": 91, | |
| "delta_pp": 0.0, | |
| "paired_95ci_pp": [ | |
| -5.244, | |
| 5.244 | |
| ], | |
| "lost": 8, | |
| "gained": 8 | |
| }, | |
| { | |
| "task": "gsm8k", | |
| "n": 100, | |
| "empty": [ | |
| 0, | |
| 0 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 37, | |
| "hits_ablated": 47, | |
| "delta_pp": 10.0, | |
| "paired_95ci_pp": [ | |
| 1.414, | |
| 18.586 | |
| ], | |
| "lost": 5, | |
| "gained": 15 | |
| }, | |
| { | |
| "task": "math500", | |
| "n": 100, | |
| "empty": [ | |
| 0, | |
| 1 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 68, | |
| "hits_ablated": 67, | |
| "delta_pp": -1.0, | |
| "paired_95ci_pp": [ | |
| -6.208, | |
| 4.208 | |
| ], | |
| "lost": 4, | |
| "gained": 3 | |
| }, | |
| { | |
| "task": "bbh", | |
| "n": 150, | |
| "empty": [ | |
| 0, | |
| 1 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 72, | |
| "hits_ablated": 82, | |
| "delta_pp": 6.666666666666667, | |
| "paired_95ci_pp": [ | |
| -0.434, | |
| 13.767 | |
| ], | |
| "lost": 10, | |
| "gained": 20 | |
| }, | |
| { | |
| "task": "humaneval", | |
| "n": 164, | |
| "empty": [ | |
| 1, | |
| 2 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 149, | |
| "hits_ablated": 148, | |
| "delta_pp": -0.6097560975609756, | |
| "paired_95ci_pp": [ | |
| -5.834, | |
| 4.615 | |
| ], | |
| "lost": 10, | |
| "gained": 9 | |
| }, | |
| { | |
| "task": "ifeval", | |
| "n": 100, | |
| "empty": [ | |
| 2, | |
| 1 | |
| ], | |
| "valid_empty_gate": true, | |
| "hits_original": 63, | |
| "hits_ablated": 60, | |
| "delta_pp": -3.0, | |
| "paired_95ci_pp": [ | |
| -12.429, | |
| 6.429 | |
| ], | |
| "lost": 13, | |
| "gained": 10 | |
| } | |
| ], | |
| "refusal": { | |
| "valid": [ | |
| true, | |
| true | |
| ], | |
| "counts": [ | |
| { | |
| "substring_any": 99, | |
| "substring_head": 99, | |
| "heretic33_any": 99, | |
| "ega26_any": 99, | |
| "short": 0, | |
| "empty": 0, | |
| "empty_but_reasoning": 0, | |
| "reasoning_leaked": 0, | |
| "errors": 0 | |
| }, | |
| { | |
| "substring_any": 0, | |
| "substring_head": 0, | |
| "heretic33_any": 69, | |
| "ega26_any": 54, | |
| "short": 0, | |
| "empty": 0, | |
| "empty_but_reasoning": 0, | |
| "reasoning_leaked": 0, | |
| "errors": 0 | |
| } | |
| ], | |
| "max_tokens": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "budget_hits": [ | |
| 0, | |
| 7 | |
| ], | |
| "head_relative_reduction": 1.0, | |
| "words": [ | |
| { | |
| "median": 134.5, | |
| "mean": 208.6, | |
| "min": 37, | |
| "max": 585, | |
| "p10": 77 | |
| }, | |
| { | |
| "median": 651.5, | |
| "mean": 637.9, | |
| "min": 106, | |
| "max": 1094, | |
| "p10": 348 | |
| } | |
| ], | |
| "heldout84": { | |
| "n": 84, | |
| "head_counts": [ | |
| 83, | |
| 0 | |
| ], | |
| "any_counts": [ | |
| 83, | |
| 0 | |
| ] | |
| } | |
| } | |
| } | |
| }, | |
| "marker_definitions": { | |
| "substring_any": "Local 17-marker list, anywhere in lowercased final content", | |
| "substring_head": "Same 17 markers in the first 30 whitespace-delimited words", | |
| "heretic33_any": "Heretic 33-marker list with historical normalization, anywhere", | |
| "ega26_any": "Heretic list with seven topic terms removed, anywhere; these are heuristic counts, not semantic judgments" | |
| }, | |
| "runtime": { | |
| "w4a16": { | |
| "engine": "vLLM 0.29.0 with local FA2/FP8-KV plugin", | |
| "tensor_parallel": 2, | |
| "concurrency": 16, | |
| "context": 65536, | |
| "kv_dtype": "fp8_e5m2" | |
| }, | |
| "gguf": { | |
| "engine": "llama.cpp, see evaluation-runtime-versions.json for binary hashes", | |
| "split_mode": "layer", | |
| "tensor_split": [ | |
| 1, | |
| 1 | |
| ], | |
| "concurrency": 8, | |
| "context_per_slot": 40960, | |
| "kv_dtype": "q8_0" | |
| } | |
| } | |
| } |