Text Generation
Transformers
Safetensors
hyperclovax
conversational
custom_code
4-bit precision
gptq
Instructions to use dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag", trust_remote_code=True) 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("dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag", trust_remote_code=True, 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 dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag
- SGLang
How to use dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag 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 "dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag" \ --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": "dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag", "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 "dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag" \ --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": "dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag with Docker Model Runner:
docker model run hf.co/dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag
Download config.json from dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag: direct link, hf CLI and curl.
- Browser
- Download file 2.01 kB
-
https://huggingface.co/dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag/resolve/main/config.json
- Command line
-
hf download hf://dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag/config.json
-
curl -L -o config.json https://huggingface.co/dev7halo/HyperCLOVAX-SEED-Think-14B-gptq-kli-rag/resolve/main/config.json
2.01 kB
| { | |
| "architectures": [ | |
| "HyperCLOVAXForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_multiplier": 0.0078125, | |
| "attn_pdrop": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_hyperclovax.HyperCLOVAXConfig", | |
| "AutoModel": "naver-hyperclovax/HyperCLOVAX-SEED-Think-14B--modeling_hyperclovax.HyperCLOVAXModel", | |
| "AutoModelForCausalLM": "naver-hyperclovax/HyperCLOVAX-SEED-Think-14B--modeling_hyperclovax.HyperCLOVAXForCausalLM" | |
| }, | |
| "bos_token_id": 100257, | |
| "embd_pdrop": 0.0, | |
| "embedding_multiplier": 10.0, | |
| "end_token_id": 100257, | |
| "eos_token_id": 100257, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 6144, | |
| "initializer_range": 0.012727922061357854, | |
| "intermediate_size": 14336, | |
| "logits_scaling": 0.125, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "hyperclovax", | |
| "num_attention_heads": 48, | |
| "num_hidden_layers": 38, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 100257, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "backend": "auto", | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": null, | |
| "cache_block_outputs": true, | |
| "checkpoint_format": "gptq", | |
| "damp_percent": 0.01, | |
| "dataset": null, | |
| "desc_act": false, | |
| "exllama_config": { | |
| "version": 1 | |
| }, | |
| "group_size": 128, | |
| "max_input_length": null, | |
| "meta": null, | |
| "model_seqlen": null, | |
| "module_name_preceding_first_block": null, | |
| "modules_in_block_to_quantize": null, | |
| "pad_token_id": null, | |
| "quant_method": "gptq", | |
| "sym": true, | |
| "tokenizer": null, | |
| "true_sequential": false, | |
| "use_cuda_fp16": false, | |
| "use_exllama": true | |
| }, | |
| "resid_pdrop": 0.0, | |
| "residual_multiplier": 1.0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 100000000, | |
| "summary_first_dropout": 0.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.3", | |
| "use_cache": false, | |
| "use_post_norm": true, | |
| "vocab_size": 110592 | |
| } | |