Instructions to use Maxtimer97/Llama2SWA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Maxtimer97/Llama2SWA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Maxtimer97/Llama2SWA", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Maxtimer97/Llama2SWA", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Maxtimer97/Llama2SWA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Maxtimer97/Llama2SWA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Maxtimer97/Llama2SWA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Maxtimer97/Llama2SWA
- SGLang
How to use Maxtimer97/Llama2SWA 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 "Maxtimer97/Llama2SWA" \ --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": "Maxtimer97/Llama2SWA", "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 "Maxtimer97/Llama2SWA" \ --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": "Maxtimer97/Llama2SWA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Maxtimer97/Llama2SWA with Docker Model Runner:
docker model run hf.co/Maxtimer97/Llama2SWA
| { | |
| "architectures": [ | |
| "HymbaForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attn_hidden_size": -1, | |
| "attn_implementation": "flash_attention_2", | |
| "attn_implementation_new": "flash_attention_2", | |
| "attn_only_wo_proj": true, | |
| "auto_map": { | |
| "AutoConfig": "configuration_hymba.HymbaConfig", | |
| "AutoModelForCausalLM": "modeling_hymba.HymbaForCausalLM" | |
| }, | |
| "bos_token_id": 128000, | |
| "calc_logits_for_entire_prompt": false, | |
| "conv_dim": { | |
| "0": 3200, | |
| "1": 3200, | |
| "10": 3200, | |
| "11": 3200, | |
| "12": 3200, | |
| "13": 3200, | |
| "14": 3200, | |
| "15": 3200, | |
| "16": 3200, | |
| "17": 3200, | |
| "18": 3200, | |
| "19": 3200, | |
| "2": 3200, | |
| "20": 3200, | |
| "21": 3200, | |
| "22": 3200, | |
| "23": 3200, | |
| "24": 3200, | |
| "25": 3200, | |
| "26": 3200, | |
| "27": 3200, | |
| "28": 3200, | |
| "29": 3200, | |
| "3": 3200, | |
| "30": 3200, | |
| "31": 3200, | |
| "4": 3200, | |
| "5": 3200, | |
| "6": 3200, | |
| "7": 3200, | |
| "8": 3200, | |
| "9": 3200 | |
| }, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "global_attn_idx": [ | |
| 0, | |
| 8, | |
| 15 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "kq_head_dim": 64, | |
| "kq_norm": "none", | |
| "kv_reuse_every_i_layer": -1, | |
| "kv_reuse_group": null, | |
| "kv_weight_reuse": false, | |
| "layer_type": [ | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h", | |
| "h" | |
| ], | |
| "mamba_conv_bias": true, | |
| "mamba_d_conv": 4, | |
| "mamba_d_state": 16, | |
| "mamba_dt_rank": 100, | |
| "mamba_expand": 1, | |
| "mamba_inner_layernorms": true, | |
| "mamba_proj_bias": false, | |
| "max_position_embeddings": 131072, | |
| "memory_tokens_interspersed_every": 0, | |
| "mlp_hidden_act": "silu", | |
| "model_type": "hymba", | |
| "num_attention_heads": 32, | |
| "num_experts": 1, | |
| "num_experts_per_tok": 1, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "num_mamba": 1, | |
| "num_memory_tokens": 0, | |
| "orig_max_position_embeddings": 2048, | |
| "output_router_logits": false, | |
| "pad_token_id": null, | |
| "pure_attn": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope": true, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "rope_type": "ntk", | |
| "router_aux_loss_coef": 0.001, | |
| "seq_length": 8192, | |
| "sliding_window": 1024, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.53.0", | |
| "use_cache": true, | |
| "use_mamba_kernels": true, | |
| "v_head_dim": 64, | |
| "vocab_size": 128256 | |
| } | |