Text Generation
Transformers
Safetensors
llama
Merge
mergekit
lazymergekit
TinyLlama/TinyLlama-1.1B-Chat-v1.0
cognitivecomputations/TinyDolphin-2.8.2-1.1b-laser
cognitivecomputations/TinyDolphin-2.8.1-1.1b
TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T
text-generation-inference
Inference Endpoints
{ | |
"_name_or_path": "jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 1, | |
"eos_token_id": 32000, | |
"hidden_act": "silu", | |
"hidden_size": 2048, | |
"initializer_range": 0.02, | |
"intermediate_size": 5632, | |
"max_position_embeddings": 4096, | |
"model_type": "llama", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 22, | |
"num_key_value_heads": 4, | |
"pretraining_tp": 1, | |
"rms_norm_eps": 1e-05, | |
"rope_scaling": null, | |
"rope_theta": 10000.0, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float32", | |
"transformers_version": "4.38.1", | |
"use_cache": true, | |
"vocab_size": 32064 | |
} | |