
--- license: apache-2.0 datasets: - CoIR-Retrieval/CodeSearchNet-python-queries-corpus language: - en - ar - zh - ru - fr metrics: - loss - accuracy base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 pipeline_tag: text-generation library_name: transformers tags: - chat - conversational - programming - algorithms - ethical-hacking - open-source - tinyllama new_version: v1.0 training_data: 156GB of diverse text data (including programming and algorithmic content) model-index: - name: TINYLAMA results: - task: type: text-generation dataset: type: custom name: Local Dataset (156GB) metrics: - type: loss value: TBD (To Be Determined after retraining) - type: accuracy value: TBD (To Be Determined after retraining) eval_results: - task: Text Generation dataset: Local Dataset (156GB) metrics: - name: Loss value: TBD (To Be Determined after retraining) - name: Accuracy value: TBD (To Be Determined after retraining)
cdf548f
verified
{ | |
"_num_labels": 1, | |
"activation_function": "gelu_new", | |
"architectures": [ | |
"GPT2LMHeadModel" | |
], | |
"attn_pdrop": 0.1, | |
"bos_token_id": 50256, | |
"embd_pdrop": 0.1, | |
"eos_token_id": 50256, | |
"id2label": { | |
"0": "LABEL_0" | |
}, | |
"initializer_range": 0.02, | |
"label2id": { | |
"LABEL_0": 0 | |
}, | |
"layer_norm_epsilon": 1e-05, | |
"model_type": "gpt2", | |
"n_ctx": 1024, | |
"n_embd": 768, | |
"n_head": 12, | |
"n_inner": null, | |
"n_layer": 6, | |
"n_positions": 1024, | |
"reorder_and_upcast_attn": false, | |
"resid_pdrop": 0.1, | |
"scale_attn_by_inverse_layer_idx": false, | |
"scale_attn_weights": true, | |
"summary_activation": null, | |
"summary_first_dropout": 0.1, | |
"summary_proj_to_labels": true, | |
"summary_type": "cls_index", | |
"summary_use_proj": true, | |
"task_specific_params": { | |
"text-generation": { | |
"do_sample": true, | |
"max_length": 50 | |
} | |
}, | |
"torch_dtype": "float16", | |
"transformers_version": "4.51.1", | |
"use_cache": true, | |
"vocab_size": 50257 | |
} | |