Instructions to use katuni4ka/tiny-random-baichuan2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use katuni4ka/tiny-random-baichuan2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="katuni4ka/tiny-random-baichuan2", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("katuni4ka/tiny-random-baichuan2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use katuni4ka/tiny-random-baichuan2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "katuni4ka/tiny-random-baichuan2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "katuni4ka/tiny-random-baichuan2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/katuni4ka/tiny-random-baichuan2
- SGLang
How to use katuni4ka/tiny-random-baichuan2 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 "katuni4ka/tiny-random-baichuan2" \ --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": "katuni4ka/tiny-random-baichuan2", "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 "katuni4ka/tiny-random-baichuan2" \ --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": "katuni4ka/tiny-random-baichuan2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use katuni4ka/tiny-random-baichuan2 with Docker Model Runner:
docker model run hf.co/katuni4ka/tiny-random-baichuan2
Update modeling_baichuan.py
Browse files- modeling_baichuan.py +2 -2
modeling_baichuan.py
CHANGED
|
@@ -230,8 +230,8 @@ class Attention(nn.Module):
|
|
| 230 |
query_states, key_states, value_states, attn_bias=xops.LowerTriangularMask()
|
| 231 |
)
|
| 232 |
else:
|
| 233 |
-
with torch.backends.cuda.sdp_kernel(enable_flash=True, enable_math=True, enable_mem_efficient=True):
|
| 234 |
-
|
| 235 |
attn_output = attn_output.transpose(1, 2)
|
| 236 |
attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
|
| 237 |
attn_output = self.o_proj(attn_output)
|
|
|
|
| 230 |
query_states, key_states, value_states, attn_bias=xops.LowerTriangularMask()
|
| 231 |
)
|
| 232 |
else:
|
| 233 |
+
#with torch.backends.cuda.sdp_kernel(enable_flash=True, enable_math=True, enable_mem_efficient=True):
|
| 234 |
+
attn_output = F.scaled_dot_product_attention(query_states, key_states, value_states, attn_mask = attention_mask)
|
| 235 |
attn_output = attn_output.transpose(1, 2)
|
| 236 |
attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
|
| 237 |
attn_output = self.o_proj(attn_output)
|