Text Generation
Transformers
GGUF
English
Inference Endpoints
wikichat-v2 / model_config.json
leafspark's picture
Update model_config.json
e8d6d49 verified
{
"name": "WikiChat2-beta",
"load_params": {
"n_ctx": 8192,
"n_batch": 512,
"rope_freq_base": 0,
"rope_freq_scale": 4,
"n_gpu_layers": -1,
"use_mlock": true,
"main_gpu": 0,
"tensor_split": [
0
],
"seed": -1,
"f16_kv": true,
"use_mmap": true,
"no_kv_offload": false,
"num_experts_used": 0
},
"inference_params": {
"n_threads": 4,
"n_predict": -1,
"top_k": 40,
"min_p": 0.05,
"top_p": 0.95,
"temp": 0.4,
"repeat_penalty": 1.1,
"input_prefix": "### Input:\n",
"input_suffix": "\\n### Response:\\n",
"antiprompt": [
"### Instruction:",
"### Instruction:\\n",
"### Input:\\n"
],
"pre_prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.",
"pre_prompt_suffix": "\\n",
"pre_prompt_prefix": "### Instruction:\n",
"seed": -1,
"tfs_z": 1,
"typical_p": 1,
"repeat_last_n": 64,
"frequency_penalty": 0,
"presence_penalty": 0,
"n_keep": 0,
"logit_bias": {},
"mirostat": 0,
"mirostat_tau": 5,
"mirostat_eta": 0.1,
"memory_f16": true,
"multiline_input": false,
"penalize_nl": true
}
}