Instructions to use fableforge-ai/ReasonCritic-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fableforge-ai/ReasonCritic-7B with Transformers:

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

pipe = pipeline("text-generation", model="fableforge-ai/ReasonCritic-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("fableforge-ai/ReasonCritic-7B")
model = AutoModelForMultimodalLM.from_pretrained("fableforge-ai/ReasonCritic-7B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fableforge-ai/ReasonCritic-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fableforge-ai/ReasonCritic-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fableforge-ai/ReasonCritic-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fableforge-ai/ReasonCritic-7B

SGLang

How to use fableforge-ai/ReasonCritic-7B 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 "fableforge-ai/ReasonCritic-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fableforge-ai/ReasonCritic-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "fableforge-ai/ReasonCritic-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fableforge-ai/ReasonCritic-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fableforge-ai/ReasonCritic-7B with Docker Model Runner:
```
docker model run hf.co/fableforge-ai/ReasonCritic-7B
```

Configuration Parsing Warning:In UNKNOWN_FILENAME: "tokenizer_config.bos_token.__type" is required

Configuration Parsing Warning:In UNKNOWN_FILENAME: "tokenizer_config.eos_token.__type" is required

Configuration Parsing Warning:In UNKNOWN_FILENAME: "tokenizer_config.unk_token.__type" is required

Configuration Parsing Warning:In UNKNOWN_FILENAME: "tokenizer_config.pad_token.__type" is required

ReasonCritic-7B

A 7B parameter reasoning critic model that evaluates, scores, and improves logical reasoning chains. Trained to identify fallacies, unsupported claims, and logical gaps in agent outputs.

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "fableforge-ai/ReasonCritic-7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

prompt = """You are an AI agent. Complete the following task:

Task: Write a Python function to calculate the Fibonacci sequence.

Reasoning:"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6, top_p=0.9)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Use Cases

Reasoning chain verification and scoring
Logical fallacy detection in agent outputs
Self-consistency checking across multi-step plans
Quality gate for agent production deployments

Integration with FableForge Ecosystem

from fableforge_agent_runtime import AgentRuntime
from fableforge_agent_skills import SkillLibrary

runtime = AgentRuntime(
    model="fableforge-ai/ReasonCritic-7B",
    skills=SkillLibrary.all(),
    verification=True
)

result = runtime.run("Deploy a web server on AWS")
print(result.output)
print(result.verification_score)

Ecosystem Integration

Part of the FableForge Agent Ecosystem - 21 open-source projects for building, testing, and deploying AI agents.

Package	Install	Purpose
`fableforge`	`pip install fableforge`	Unified CLI
`fableforge-anvil-agent`	`pip install fableforge-anvil-agent`	Self-verified coding agent
`fableforge-agent-swarm`	`pip install fableforge-agent-swarm`	Multi-agent orchestration
`fableforge-agent-runtime`	`pip install fableforge-agent-runtime`	Production agent runtime
`fableforge-agent-skills`	`pip install fableforge-agent-skills`	Skill library
`verifyloop`	`pip install verifyloop`	Verification loops
`reason-critic`	`pip install reason-critic`	Reasoning assessment

Model Details

Attribute	Value
Architecture	MistralForCausalLM
Parameters	7B
Hidden Size	4096
Layers	32
Attention Heads	32
KV Heads	8
Max Context	32768
Training Data	Fable5 agent traces + curated reasoning datasets
License	MIT

Limitations

May generate incorrect code -- always use with verifyloop for critical tasks
Trained primarily on English data; multilingual performance is limited
Can hallucinate API signatures or tool parameters
Not suitable for medical, legal, or financial advice without human review

Citation

@misc{reasoncritic7b2024,
  title={ReasonCritic-7B: Agent Orchestration via Fine-Tuned Language Models},
  author={FableForge Team},
  year={2024},
  url={https://huggingface.co/fableforge-ai/ReasonCritic-7B}
}

License

MIT License - see LICENSE for details.

Built with hammer by the FableForge team. Part of the FableForge ecosystem.

Downloads last month: 39

Model tree for fableforge-ai/ReasonCritic-7B

Base model

mistralai/Mistral-7B-Instruct-v0.2

Finetuned

(1094)

this model