akshaybharadwaj96/nl-code-gen-python

1{2  "_name_or_path": "Salesforce/codegen-350M-mono",3  "activation_function": "gelu_new",4  "architectures": [5    "CodeGenForCausalLM"6  ],7  "attn_pdrop": 0.0,8  "bos_token_id": 1,9  "embd_pdrop": 0.0,10  "eos_token_id": 50256,11  "gradient_checkpointing": false,12  "initializer_range": 0.02,13  "layer_norm_epsilon": 1e-05,14  "model_type": "codegen",15  "n_ctx": 2048,16  "n_embd": 1024,17  "n_head": 16,18  "n_inner": null,19  "n_layer": 20,20  "n_positions": 2048,21  "quantization_config": {22    "bnb_4bit_compute_dtype": "bfloat16",23    "bnb_4bit_quant_type": "nf4",24    "bnb_4bit_use_double_quant": true,25    "llm_int8_enable_fp32_cpu_offload": false,26    "llm_int8_has_fp16_weight": false,27    "llm_int8_skip_modules": null,28    "llm_int8_threshold": 6.0,29    "load_in_4bit": true,30    "load_in_8bit": false,31    "quant_method": "bitsandbytes"32  },33  "resid_pdrop": 0.0,34  "rotary_dim": 32,35  "scale_attn_weights": true,36  "summary_activation": null,37  "summary_first_dropout": 0.1,38  "summary_proj_to_labels": true,39  "summary_type": "cls_index",40  "summary_use_proj": true,41  "task_specific_params": {42    "text-generation": {43      "do_sample": true,44      "max_length": 50,45      "temperature": 1.046    }47  },48  "tie_word_embeddings": false,49  "tokenizer_class": "GPT2Tokenizer",50  "torch_dtype": "float16",51  "transformers_version": "4.36.2",52  "use_cache": true,53  "use_flash_attention_2": true,54  "vocab_size": 5120055}56