oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-09 00:23:38 +00:00
Code Issues Projects Releases Packages Wiki Activity

New llama.cpp loader (#6846)

Browse source
This commit is contained in:
oobabooga 2025-04-18 09:59:37 -03:00 • committed by GitHub
parent 5c2f8d828e
commit ae54d8faaa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 471 additions and 999 deletions
Download patch file Download diff file Expand all files Collapse all files

67
modules/loaders.py
View file

@ -30,51 +30,20 @@ loaders_and_params = OrderedDict({
'n_gpu_layers',
'threads',
'threads_batch',
'n_batch',
'batch_size',
'n_ctx',
'cache_type',
'tensor_split',
'rope_freq_base',
'compress_pos_emb',
'attention_sink_size',
'tensorcores',
'flash_attn',
'streaming_llm',
'cpu',
'row_split',
'no_offload_kqv',
'no_kv_offload',
'no_mul_mat_q',
'no_mmap',
'mlock',
'numa',
],
'llamacpp_HF': [
'n_gpu_layers',
'threads',
'threads_batch',
'n_batch',
'n_ctx',
'cache_type',
'tensor_split',
'rope_freq_base',
'compress_pos_emb',
'attention_sink_size',
'tensorcores',
'flash_attn',
'streaming_llm',
'cpu',
'row_split',
'no_offload_kqv',
'no_mul_mat_q',
'no_mmap',
'mlock',
'numa',
'cfg_cache',
'logits_all',
'trust_remote_code',
'no_use_fast',
'llamacpp_HF_info',
],
'ExLlamav3_HF': [
'max_seq_len',
'gpu_split',
@ -307,66 +276,34 @@ loaders_samplers = {
'dry_sequence_breakers',
},
'llama.cpp': {
'temperature',
'min_p',
'top_p',
'top_k',
'typical_p',
'tfs',
'repetition_penalty',
'frequency_penalty',
'presence_penalty',
'mirostat_mode',
'mirostat_tau',
'mirostat_eta',
'ban_eos_token',
'seed',
'custom_token_bans',
'grammar_string',
'grammar_file_row',
},
'llamacpp_HF': {
'temperature',
'dynatemp_low',
'dynatemp_high',
'dynatemp_exponent',
'smoothing_factor',
'smoothing_curve',
'min_p',
'top_p',
'top_k',
'typical_p',
'xtc_threshold',
'xtc_probability',
'epsilon_cutoff',
'eta_cutoff',
'tfs',
'top_a',
'top_n_sigma',
'dry_multiplier',
'dry_allowed_length',
'dry_base',
'repetition_penalty',
'frequency_penalty',
'presence_penalty',
'encoder_repetition_penalty',
'no_repeat_ngram_size',
'repetition_penalty_range',
'guidance_scale',
'mirostat_mode',
'mirostat_tau',
'mirostat_eta',
'do_sample',
'dynamic_temperature',
'temperature_last',
'auto_max_new_tokens',
'ban_eos_token',
'add_bos_token',
'skip_special_tokens',
'seed',
'sampler_priority',
'custom_token_bans',
'negative_prompt',
'dry_sequence_breakers',
'grammar_string',
'grammar_file_row',