Instructions to use T-EVEN/krx_llama3.1_8b_instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Desktop
Download config.json from T-EVEN/krx_llama3.1_8b_instruct: direct link, hf CLI and curl.
- Browser
- Download file 929 Bytes
-
https://huggingface.co/T-EVEN/krx_llama3.1_8b_instruct/resolve/main/config.json
- Command line
-
hf download hf://T-EVEN/krx_llama3.1_8b_instruct/config.json
-
curl -L -o config.json https://huggingface.co/T-EVEN/krx_llama3.1_8b_instruct/resolve/main/config.json
929 Bytes
| { | |
| "_name_or_path": "unsloth/Meta-Llama-3.1-8B", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 128004, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.44.2", | |
| "unsloth_version": "2024.10.3", | |
| "use_cache": false, | |
| "vocab_size": 128256 | |
| } | |