Instructions to use JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge with Transformers:

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

pipe = pipeline("text-generation", model="JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge")
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("JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge")
model = AutoModelForCausalLM.from_pretrained("JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge", 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 JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge

SGLang

How to use JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge 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 "JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge" \
    --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": "JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge",
		"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 "JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge" \
        --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": "JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge with Docker Model Runner:
```
docker model run hf.co/JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge
```

Uploaded finetuned model

Developed by: JPQ24
License: apache-2.0
Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

🧠 CSR-8B: Creative Synthesis & Reasoning (v3)

CSR-8B is a specialized fine-tune of Llama-3, designed to simulate expert-level analytical thinking through a structured Creative Synthesis & Reasoning (CSR) cycle.

Unlike standard models that attempt to solve problems in a linear pass, CSR-8B is trained to navigate a four-phase cognitive architecture: Divergence ➡ Evaluation ➡ Synthesis ➡ Self-Correction.

⚙️ The CSR Methodology (v3)

This model instills a disciplined cognitive workflow. Instead of rushing to a conclusion, the model iterates through the following phases:

🌌 Phase 1: Divergent Exploration

Broad Activation: Activates multiple conceptual frameworks simultaneously.
Hypothesis Generation: Enumerates competing hypotheses and solution pathways.
Strategy Mapping: Identifies whether to use analogical, counterfactual, or mathematical reasoning.

🔍 Phase 2: Evaluation & Insight

Stress Testing: Rigorously tests hypotheses against logical constraints.
Contradiction Analysis: Detects internal conflicts in the reasoning chain.
Prioritization: Filters pathways based on explanatory power, discarding weak links.

🧩 Phase 3: Convergent Synthesis

Argument Construction: Weaves validated elements into logical chains.
Pattern Application: Applies domain-specific structures (e.g., experimental design, formal proofs).
Defensible Conclusions: Synthesizes findings into a coherent, polished output.

🔄 Phase 4: Iterative Self-Correction

Metacognitive Review: The model "looks back" at its own reasoning to identify gaps or unsupported leaps.
Verification: Checks alignment with original constraints.
Looping: Determines if re-iteration is necessary before finalizing the answer.

⚠️ Limitations

Verbosity: Due to the 4-phase cycle, this model produces longer outputs than standard Llama-3.
Latency: Inference takes longer as the model "thinks" through the phases.
Complexity: Best used for complex analytical queries, not simple factual lookup (e.g., "What is the capital of France?").

Downloads last month: 22

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for JPQ24/llama-3-8b-Cognitive-curriculum-Lora-Merge

Base model

unsloth/llama-3-8b-Instruct-bnb-4bit

Adapter

(183)

this model