mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Remove exllamav1 loaders (#5128)

Browse source
This commit is contained in:
oobabooga 2023-12-31 01:57:06 -03:00 • committed by GitHub
parent 8e397915c9
commit 0e54a09bcb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
18 changed files with 28 additions and 635 deletions
Download patch file Download diff file Expand all files Collapse all files

76
modules/loaders.py
View file

@ -81,15 +81,15 @@ loaders_and_params = OrderedDict({
'trust_remote_code',
'no_use_fast',
],
'ExLlama_HF': [
'ExLlamav2': [
'gpu_split',
'max_seq_len',
'no_flash_attn',
'num_experts_per_token',
'cache_8bit',
'alpha_value',
'rope_freq_base',
'compress_pos_emb',
'cfg_cache',
'trust_remote_code',
'no_use_fast',
'exllamav2_info',
],
'AutoGPTQ': [
'triton',
@ -128,24 +128,6 @@ loaders_and_params = OrderedDict({
'no_use_fast',
'gptq_for_llama_info',
],
'ExLlamav2': [
'gpu_split',
'max_seq_len',
'no_flash_attn',
'num_experts_per_token',
'cache_8bit',
'alpha_value',
'compress_pos_emb',
'exllamav2_info',
],
'ExLlama': [
'gpu_split',
'max_seq_len',
'alpha_value',
'rope_freq_base',
'compress_pos_emb',
'exllama_info',
],
'ctransformers': [
'n_ctx',
'n_gpu_layers',
@ -216,54 +198,6 @@ loaders_samplers = {
'AutoAWQ': transformers_samplers(),
'QuIP#': transformers_samplers(),
'HQQ': transformers_samplers(),
'ExLlama_HF': {
'temperature',
'temperature_last',
'top_p',
'min_p',
'top_k',
'typical_p',
'epsilon_cutoff',
'eta_cutoff',
'tfs',
'top_a',
'repetition_penalty',
'presence_penalty',
'frequency_penalty',
'repetition_penalty_range',
'encoder_repetition_penalty',
'no_repeat_ngram_size',
'min_length',
'seed',
'do_sample',
'mirostat_mode',
'mirostat_tau',
'mirostat_eta',
'grammar_file_row',
'grammar_string',
'guidance_scale',
'negative_prompt',
'ban_eos_token',
'custom_token_bans',
'add_bos_token',
'skip_special_tokens',
'auto_max_new_tokens',
},
'ExLlama': {
'temperature',
'top_p',
'top_k',
'typical_p',
'repetition_penalty',
'repetition_penalty_range',
'seed',
'guidance_scale',
'negative_prompt',
'ban_eos_token',
'add_bos_token',
'custom_token_bans',
'auto_max_new_tokens',
},
'ExLlamav2': {
'temperature',
'top_p',