Instructions to use collision-10M/Collision-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use collision-10M/Collision-1B with Transformers:

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

pipe = pipeline("text-generation", model="collision-10M/Collision-1B", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("collision-10M/Collision-1B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use collision-10M/Collision-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "collision-10M/Collision-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "collision-10M/Collision-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/collision-10M/Collision-1B

SGLang

How to use collision-10M/Collision-1B 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 "collision-10M/Collision-1B" \
    --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": "collision-10M/Collision-1B",
		"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 "collision-10M/Collision-1B" \
        --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": "collision-10M/Collision-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use collision-10M/Collision-1B with Docker Model Runner:
```
docker model run hf.co/collision-10M/Collision-1B
```

Collision-1B / model_metadata.json

collision-10M

Release collision-10M/Collision-1B with In-House NLP Engine & Grounded Intelligence

a711f64 verified about 1 month ago

Raw History Blame Contribute Delete

1.35 kB

	{
	"name": "COLLISION-1B",
	"version": "1.0.0",
	"parameters": 999376128,
	"architecture": "Decoder-only Transformer",
	"layers": 24,
	"hidden_size": 2048,
	"attention_heads": 16,
	"d_ff": 5376,
	"context_length": 1024,
	"vocab_size": 32000,
	"training_tokens": 10000000,
	"dataset": "collision_dataset_v5_expanded",
	"tokenizer": "Custom BPE Tokenizer",
	"checkpoint_sha256": "bdd986e2a4964a6a204224dbd973625abe192cd4f6e23dceb79e273a29b19c88",
	"nlp_engine": {
	"module": "collision.nlp",
	"version": "1.0.0",
	"capabilities": [
	"conversational_dialogue",
	"textrank_keyphrase_extraction",
	"topic_classification_10_domains",
	"tone_and_formality_scoring",
	"grammar_and_spell_proofreading",
	"readability_indices_flesch_fog",
	"reading_comprehension_context_qa",
	"style_transformations",
	"semantic_text_similarity",
	"deterministic_math_geometry_statistics",
	"grounded_answer_synthesis"
	]
	},
	"cognitive_brain": {
	"module": "collision.brain",
	"version": "2.0.0",
	"capabilities": [
	"dual_process_system_1_2",
	"graph_of_thoughts_dag",
	"hegelian_dialectic_synthesis",
	"global_workspace_theory",
	"synaptic_working_memory_ltp",
	"cross_domain_knowledge_lattice",
	"information_entropy_profiling"
	]
	}
	}