Text Generation
Transformers
Safetensors
phi3
quantized
quantport
smoothquant
wikitext-2
conversational
text-generation-inference
8-bit precision
Instructions to use chris320211/smoothquant-phi35-mini-vastrtx3090 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chris320211/smoothquant-phi35-mini-vastrtx3090 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="chris320211/smoothquant-phi35-mini-vastrtx3090") 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("chris320211/smoothquant-phi35-mini-vastrtx3090") model = AutoModelForCausalLM.from_pretrained("chris320211/smoothquant-phi35-mini-vastrtx3090", 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use chris320211/smoothquant-phi35-mini-vastrtx3090 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "chris320211/smoothquant-phi35-mini-vastrtx3090" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chris320211/smoothquant-phi35-mini-vastrtx3090", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/chris320211/smoothquant-phi35-mini-vastrtx3090
- SGLang
How to use chris320211/smoothquant-phi35-mini-vastrtx3090 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 "chris320211/smoothquant-phi35-mini-vastrtx3090" \ --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": "chris320211/smoothquant-phi35-mini-vastrtx3090", "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 "chris320211/smoothquant-phi35-mini-vastrtx3090" \ --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": "chris320211/smoothquant-phi35-mini-vastrtx3090", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use chris320211/smoothquant-phi35-mini-vastrtx3090 with Docker Model Runner:
docker model run hf.co/chris320211/smoothquant-phi35-mini-vastrtx3090
Download quantization_config.json from chris320211/smoothquant-phi35-mini-vastrtx3090: direct link, hf CLI and curl.
- Browser
- Download file 6.3 kB
-
https://huggingface.co/chris320211/smoothquant-phi35-mini-vastrtx3090/resolve/main/quantization_config.json
- Command line
-
hf download hf://chris320211/smoothquant-phi35-mini-vastrtx3090/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/chris320211/smoothquant-phi35-mini-vastrtx3090/resolve/main/quantization_config.json
6.3 kB
| { | |
| "quant_method": "smoothquant", | |
| "method_name": "SmoothQuant", | |
| "format": "w8a8_int8", | |
| "w_bits": 8, | |
| "a_bits": 8, | |
| "weight_quant": "per_channel", | |
| "act_quant": "per_token", | |
| "act_dynamic": true, | |
| "w_sym": true, | |
| "a_sym": true, | |
| "quantize_bmm_input": false, | |
| "weight_dtype": "int8", | |
| "weight_scale_dtype": "float16", | |
| "weight_scale_shape": "[out_features, 1]", | |
| "dequant": "weight_fp16 = weight.int8 * weight_scale", | |
| "kept_fp16": [ | |
| "input_layernorm / post_attention_layernorm (smoothed)", | |
| "model.norm", | |
| "model.embed_tokens", | |
| "lm_head (untied, stored)" | |
| ], | |
| "smoothing_folded_offline": true, | |
| "smoothing_sites": [ | |
| "input_layernorm -> self_attn.qkv_proj", | |
| "post_attention_layernorm -> mlp.gate_up_proj" | |
| ], | |
| "runtime_transforms": [], | |
| "repo_url": "https://github.com/mit-han-lab/smoothquant", | |
| "repo_commit": "c61476d728e42ae0d8a35e7e78494edcac3237b5", | |
| "inference_adapter": "quant_agent_inference_adapter.py", | |
| "alpha": 0.75, | |
| "calibration": { | |
| "dataset": "mit-han-lab/pile-val-backup val.jsonl (local copy)", | |
| "shuffle_seed": 42, | |
| "num_samples": 512, | |
| "seq_len": 512 | |
| }, | |
| "base_model": "microsoft/Phi-3.5-mini-instruct", | |
| "quantized_modules": [ | |
| "model.layers.0.mlp.down_proj", | |
| "model.layers.0.mlp.gate_up_proj", | |
| "model.layers.0.self_attn.o_proj", | |
| "model.layers.0.self_attn.qkv_proj", | |
| "model.layers.1.mlp.down_proj", | |
| "model.layers.1.mlp.gate_up_proj", | |
| "model.layers.1.self_attn.o_proj", | |
| "model.layers.1.self_attn.qkv_proj", | |
| "model.layers.10.mlp.down_proj", | |
| "model.layers.10.mlp.gate_up_proj", | |
| "model.layers.10.self_attn.o_proj", | |
| "model.layers.10.self_attn.qkv_proj", | |
| "model.layers.11.mlp.down_proj", | |
| "model.layers.11.mlp.gate_up_proj", | |
| "model.layers.11.self_attn.o_proj", | |
| "model.layers.11.self_attn.qkv_proj", | |
| "model.layers.12.mlp.down_proj", | |
| "model.layers.12.mlp.gate_up_proj", | |
| "model.layers.12.self_attn.o_proj", | |
| "model.layers.12.self_attn.qkv_proj", | |
| "model.layers.13.mlp.down_proj", | |
| "model.layers.13.mlp.gate_up_proj", | |
| "model.layers.13.self_attn.o_proj", | |
| "model.layers.13.self_attn.qkv_proj", | |
| "model.layers.14.mlp.down_proj", | |
| "model.layers.14.mlp.gate_up_proj", | |
| "model.layers.14.self_attn.o_proj", | |
| "model.layers.14.self_attn.qkv_proj", | |
| "model.layers.15.mlp.down_proj", | |
| "model.layers.15.mlp.gate_up_proj", | |
| "model.layers.15.self_attn.o_proj", | |
| "model.layers.15.self_attn.qkv_proj", | |
| "model.layers.16.mlp.down_proj", | |
| "model.layers.16.mlp.gate_up_proj", | |
| "model.layers.16.self_attn.o_proj", | |
| "model.layers.16.self_attn.qkv_proj", | |
| "model.layers.17.mlp.down_proj", | |
| "model.layers.17.mlp.gate_up_proj", | |
| "model.layers.17.self_attn.o_proj", | |
| "model.layers.17.self_attn.qkv_proj", | |
| "model.layers.18.mlp.down_proj", | |
| "model.layers.18.mlp.gate_up_proj", | |
| "model.layers.18.self_attn.o_proj", | |
| "model.layers.18.self_attn.qkv_proj", | |
| "model.layers.19.mlp.down_proj", | |
| "model.layers.19.mlp.gate_up_proj", | |
| "model.layers.19.self_attn.o_proj", | |
| "model.layers.19.self_attn.qkv_proj", | |
| "model.layers.2.mlp.down_proj", | |
| "model.layers.2.mlp.gate_up_proj", | |
| "model.layers.2.self_attn.o_proj", | |
| "model.layers.2.self_attn.qkv_proj", | |
| "model.layers.20.mlp.down_proj", | |
| "model.layers.20.mlp.gate_up_proj", | |
| "model.layers.20.self_attn.o_proj", | |
| "model.layers.20.self_attn.qkv_proj", | |
| "model.layers.21.mlp.down_proj", | |
| "model.layers.21.mlp.gate_up_proj", | |
| "model.layers.21.self_attn.o_proj", | |
| "model.layers.21.self_attn.qkv_proj", | |
| "model.layers.22.mlp.down_proj", | |
| "model.layers.22.mlp.gate_up_proj", | |
| "model.layers.22.self_attn.o_proj", | |
| "model.layers.22.self_attn.qkv_proj", | |
| "model.layers.23.mlp.down_proj", | |
| "model.layers.23.mlp.gate_up_proj", | |
| "model.layers.23.self_attn.o_proj", | |
| "model.layers.23.self_attn.qkv_proj", | |
| "model.layers.24.mlp.down_proj", | |
| "model.layers.24.mlp.gate_up_proj", | |
| "model.layers.24.self_attn.o_proj", | |
| "model.layers.24.self_attn.qkv_proj", | |
| "model.layers.25.mlp.down_proj", | |
| "model.layers.25.mlp.gate_up_proj", | |
| "model.layers.25.self_attn.o_proj", | |
| "model.layers.25.self_attn.qkv_proj", | |
| "model.layers.26.mlp.down_proj", | |
| "model.layers.26.mlp.gate_up_proj", | |
| "model.layers.26.self_attn.o_proj", | |
| "model.layers.26.self_attn.qkv_proj", | |
| "model.layers.27.mlp.down_proj", | |
| "model.layers.27.mlp.gate_up_proj", | |
| "model.layers.27.self_attn.o_proj", | |
| "model.layers.27.self_attn.qkv_proj", | |
| "model.layers.28.mlp.down_proj", | |
| "model.layers.28.mlp.gate_up_proj", | |
| "model.layers.28.self_attn.o_proj", | |
| "model.layers.28.self_attn.qkv_proj", | |
| "model.layers.29.mlp.down_proj", | |
| "model.layers.29.mlp.gate_up_proj", | |
| "model.layers.29.self_attn.o_proj", | |
| "model.layers.29.self_attn.qkv_proj", | |
| "model.layers.3.mlp.down_proj", | |
| "model.layers.3.mlp.gate_up_proj", | |
| "model.layers.3.self_attn.o_proj", | |
| "model.layers.3.self_attn.qkv_proj", | |
| "model.layers.30.mlp.down_proj", | |
| "model.layers.30.mlp.gate_up_proj", | |
| "model.layers.30.self_attn.o_proj", | |
| "model.layers.30.self_attn.qkv_proj", | |
| "model.layers.31.mlp.down_proj", | |
| "model.layers.31.mlp.gate_up_proj", | |
| "model.layers.31.self_attn.o_proj", | |
| "model.layers.31.self_attn.qkv_proj", | |
| "model.layers.4.mlp.down_proj", | |
| "model.layers.4.mlp.gate_up_proj", | |
| "model.layers.4.self_attn.o_proj", | |
| "model.layers.4.self_attn.qkv_proj", | |
| "model.layers.5.mlp.down_proj", | |
| "model.layers.5.mlp.gate_up_proj", | |
| "model.layers.5.self_attn.o_proj", | |
| "model.layers.5.self_attn.qkv_proj", | |
| "model.layers.6.mlp.down_proj", | |
| "model.layers.6.mlp.gate_up_proj", | |
| "model.layers.6.self_attn.o_proj", | |
| "model.layers.6.self_attn.qkv_proj", | |
| "model.layers.7.mlp.down_proj", | |
| "model.layers.7.mlp.gate_up_proj", | |
| "model.layers.7.self_attn.o_proj", | |
| "model.layers.7.self_attn.qkv_proj", | |
| "model.layers.8.mlp.down_proj", | |
| "model.layers.8.mlp.gate_up_proj", | |
| "model.layers.8.self_attn.o_proj", | |
| "model.layers.8.self_attn.qkv_proj", | |
| "model.layers.9.mlp.down_proj", | |
| "model.layers.9.mlp.gate_up_proj", | |
| "model.layers.9.self_attn.o_proj", | |
| "model.layers.9.self_attn.qkv_proj" | |
| ], | |
| "num_quantized_linears": 128 | |
| } | |