Text Generation
Transformers
Safetensors
llama
mergekit
Merge
abacusai/Dracarys-Llama-3.1-70B-Instruct
Sao10K/L3-70B-Euryale-v2.1
gbueno86/Cathallama-70B
sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1
nothingiisreal/L3.1-70B-Celeste-V0.1-BF16
Fizzarolli/L3.1-70b-glitz-v0.2
cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
conversational
text-generation-inference
Inference Endpoints
{ | |
"_name_or_path": "Fizzarolli/L3.1-70b-glitz-v0.2", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 128000, | |
"eos_token_id": 128009, | |
"hidden_act": "silu", | |
"hidden_size": 8192, | |
"initializer_range": 0.02, | |
"intermediate_size": 28672, | |
"max_position_embeddings": 131072, | |
"mlp_bias": false, | |
"model_type": "llama", | |
"num_attention_heads": 64, | |
"num_hidden_layers": 80, | |
"num_key_value_heads": 8, | |
"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": "bfloat16", | |
"transformers_version": "4.44.0", | |
"use_cache": false, | |
"vocab_size": 128256 | |
} | |