Text Generation
Transformers
Safetensors
PyTorch
English
neollm
causal-lm
research
bf16
attention
normalization
conversational
custom_code
Instructions to use KitsuVp/NeoLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KitsuVp/NeoLLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="KitsuVp/NeoLLM", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("KitsuVp/NeoLLM", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use KitsuVp/NeoLLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "KitsuVp/NeoLLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "KitsuVp/NeoLLM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/KitsuVp/NeoLLM
- SGLang
How to use KitsuVp/NeoLLM 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 "KitsuVp/NeoLLM" \ --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": "KitsuVp/NeoLLM", "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 "KitsuVp/NeoLLM" \ --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": "KitsuVp/NeoLLM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use KitsuVp/NeoLLM with Docker Model Runner:
docker model run hf.co/KitsuVp/NeoLLM
Update modeling_neollm.py
Browse files- modeling_neollm.py +4 -3
modeling_neollm.py
CHANGED
|
@@ -237,7 +237,6 @@ class NeoLLMRMSNormGated(nn.Module):
|
|
| 237 |
|
| 238 |
return hidden_states.to(input_dtype)
|
| 239 |
|
| 240 |
-
|
| 241 |
class PolarPositionalEmbedding(nn.Module):
|
| 242 |
"""
|
| 243 |
Polar Coordinate Position Embedding (PoPE) - FlashAttention2-compatible implementation
|
|
@@ -325,8 +324,10 @@ class PolarPositionalEmbedding(nn.Module):
|
|
| 325 |
|
| 326 |
# Step 3: Convert to Cartesian coordinates (Equations 7-8 from paper)
|
| 327 |
# x = μ * cos(φ), y = μ * sin(φ)
|
| 328 |
-
|
| 329 |
-
|
|
|
|
|
|
|
| 330 |
|
| 331 |
q_real = mu_q * cos_freqs # x_q component
|
| 332 |
q_imag = mu_q * sin_freqs # y_q component
|
|
|
|
| 237 |
|
| 238 |
return hidden_states.to(input_dtype)
|
| 239 |
|
|
|
|
| 240 |
class PolarPositionalEmbedding(nn.Module):
|
| 241 |
"""
|
| 242 |
Polar Coordinate Position Embedding (PoPE) - FlashAttention2-compatible implementation
|
|
|
|
| 324 |
|
| 325 |
# Step 3: Convert to Cartesian coordinates (Equations 7-8 from paper)
|
| 326 |
# x = μ * cos(φ), y = μ * sin(φ)
|
| 327 |
+
# Note: Compute trigonometric functions in float32 for precision, then convert
|
| 328 |
+
# to input dtype (fp8/fp16/bf16) to maintain efficiency in subsequent operations
|
| 329 |
+
cos_freqs = torch.cos(freqs).to(q.dtype)
|
| 330 |
+
sin_freqs = torch.sin(freqs).to(q.dtype)
|
| 331 |
|
| 332 |
q_real = mu_q * cos_freqs # x_q component
|
| 333 |
q_imag = mu_q * sin_freqs # y_q component
|