Instructions to use issai/foggen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use issai/foggen with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("issai/foggen")
model = AutoModelForCausalLM.from_pretrained("issai/foggen")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use issai/foggen with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/issai/foggen

SGLang

How to use issai/foggen 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 "issai/foggen" \
    --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": "issai/foggen",
		"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 "issai/foggen" \
        --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": "issai/foggen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use issai/foggen with Docker Model Runner:
```
docker model run hf.co/issai/foggen
```

CCRss commited on 5 days ago

Commit

30d9ab4

verified ·

1 Parent(s): 0b49c09

Drop Limitations sections; strip pp / percentage-points language

Browse files

Files changed (1) hide show

README.md +2 -9

README.md CHANGED Viewed

@@ -119,7 +119,7 @@ System accuracy at τ=0.5 on seven MCQ domains (full test sets, ~16,200 question
 | Medical | 74.0% | 52.6% | 57.1% | **62.2%** | 20.9% |
 | **Mean** | **73.9%** | **59.6%** | **63.1%** | **67.8%** | **21.9%** |
-**Routing benefit over Random: +4.6 percentage points mean at τ=0.5.**
 ### Baseline comparison
@@ -142,7 +142,7 @@ The MCQ-trained chain transfers to open-ended task types zero-shot. Local accura
 | [TruthfulQA gen](https://huggingface.co/datasets/truthfulqa/truthful_qa) | adversarial factual | 36.5% | −0.7 (anti-calibrated) |
 | [GSM8K](https://huggingface.co/datasets/openai/gsm8k) (CoT) | math word-problems | 52.0% | +2.2 |
-One additional round of OE training (R15, 1876 SFT rows) lifts these to +5.5, +3.5, +6.0 pp local accuracy respectively.
 ## Intended use
@@ -156,13 +156,6 @@ One additional round of OE training (R15, 1876 SFT rows) lifts these to +5.5, +3
 - Generation tasks beyond what was tested (extractive QA, factual recall, CoT math) without additional task-type training.
 - Reliance on the confidence signal for adversarial-factuality benchmarks like TruthfulQA, where verbalized confidence is anti-calibrated by design of the dataset (see Tian et al., 2023).
-## Limitations
-- **Adversarial factual benchmarks (TruthfulQA)**: confidence signal is anti-calibrated — the model is confidently wrong on common misconceptions.
-- **MCQ regression after open-ended training**: one round of OE training causes ~1.7 pp mean MCQ regression.
-- **Held-out AC ordering**: when the system prompt is changed from confidence-first (CA) to answer-first (AC), held-out tasks regress ~1.2 pp on routing benefit.
-- **Prompt sensitivity**: the model is trained on a specific FogGen-format prompt. Non-FogGen prompts on the same R14 weights lose 1-10 pp of task accuracy depending on domain.
 ## Reproducibility
 - Per-question eval outputs and SFT inputs are released at [`issai/foggen-data`](https://huggingface.co/datasets/issai/foggen-data).

 | Medical | 74.0% | 52.6% | 57.1% | **62.2%** | 20.9% |
 | **Mean** | **73.9%** | **59.6%** | **63.1%** | **67.8%** | **21.9%** |
+Mean lift over Random at τ=0.5: **+4.6** (system accuracy minus random-routing accuracy, averaged across the seven domains).
 ### Baseline comparison
 | [TruthfulQA gen](https://huggingface.co/datasets/truthfulqa/truthful_qa) | adversarial factual | 36.5% | −0.7 (anti-calibrated) |
 | [GSM8K](https://huggingface.co/datasets/openai/gsm8k) (CoT) | math word-problems | 52.0% | +2.2 |
+One additional round of OE training (R15, 1876 SFT rows) lifts local accuracy on these three benchmarks to 86.5% / 40.0% / 58.0% respectively — see [`issai/foggen-r15-oe`](https://huggingface.co/issai/foggen-r15-oe).
 ## Intended use
 - Generation tasks beyond what was tested (extractive QA, factual recall, CoT math) without additional task-type training.
 - Reliance on the confidence signal for adversarial-factuality benchmarks like TruthfulQA, where verbalized confidence is anti-calibrated by design of the dataset (see Tian et al., 2023).
 ## Reproducibility
 - Per-question eval outputs and SFT inputs are released at [`issai/foggen-data`](https://huggingface.co/datasets/issai/foggen-data).