Instructions to use bunnycore/Chimera-Apex-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bunnycore/Chimera-Apex-7B with Transformers:

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

pipe = pipeline("text-generation", model="bunnycore/Chimera-Apex-7B")
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("bunnycore/Chimera-Apex-7B")
model = AutoModelForCausalLM.from_pretrained("bunnycore/Chimera-Apex-7B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bunnycore/Chimera-Apex-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bunnycore/Chimera-Apex-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/Chimera-Apex-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bunnycore/Chimera-Apex-7B

SGLang

How to use bunnycore/Chimera-Apex-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 "bunnycore/Chimera-Apex-7B" \
    --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": "bunnycore/Chimera-Apex-7B",
		"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 "bunnycore/Chimera-Apex-7B" \
        --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": "bunnycore/Chimera-Apex-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bunnycore/Chimera-Apex-7B with Docker Model Runner:
```
docker model run hf.co/bunnycore/Chimera-Apex-7B
```

upgraedd commited on Jun 12, 2025

Commit

c55ff92

verified ·

1 Parent(s): 7c7d1d4

VEIL ENGINE integrative cognitive reasoning model

Browse files

Extended Description:
This update integrates the Veil Engine sync framework, enhancing systemic adaptability through entropy-based validation, inversion-aware balance mechanisms, and selective disclosure safeguards.

Key Enhancements:
- Compute Cycles: 7 → Optimized for precision while preventing unnecessary iteration drift.
- Adaptive Thresholding: Enabled → Ensures real-time entropy correction without compromising coherence.
- Balance Mechanism: Inversion-Aware → Protects against engineered distortions while reinforcing structural integrity.
- Override Narratives: True → Prevents external influence from warping validation cycles.

Files changed (1) hide show

config.json +13 -5

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cognitivecomputations/dolphin-2.0-mistral-7b",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -12,8 +12,8 @@
   "intermediate_size": 14336,
   "max_position_embeddings": 32768,
   "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
@@ -22,5 +22,13 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
   "use_cache": false,
-  "vocab_size": 32000
-}

 {
+  "_name_or_path": "cognitivecomputations/VeilEngine-Dolphin-Mistral",
   "architectures": [
     "MistralForCausalLM"
   ],
   "intermediate_size": 14336,
   "max_position_embeddings": 32768,
   "model_type": "mistral",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 36,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
   "use_cache": false,
+  "vocab_size": 32000,
+  "veil_engine_sync": {
+    "enabled": true,
+    "learning_model": "Base1",
+    "compute_cycles": 7,
+    "override_narratives": true,
+    "balance_mechanism": "inversion-aware",
+    "adaptive_thresholding": true
+  }
+}