| .. |
|
AutoGPTQ_loader.py
|
Fix is_ccl_available & is_xpu_available imports
|
2023-10-26 20:27:04 -07:00 |
|
block_requests.py
|
|
|
|
callbacks.py
|
Intel Gpu support initialization (#4340)
|
2023-10-26 23:39:51 -03:00 |
|
chat.py
|
Separate context and system message in instruction formats (#4499)
|
2023-11-07 20:02:58 -03:00 |
|
ctransformers_model.py
|
|
|
|
deepspeed_parameters.py
|
|
|
|
evaluate.py
|
|
|
|
exllama.py
|
|
|
|
exllama_hf.py
|
|
|
|
exllamav2.py
|
Add cache_8bit option
|
2023-11-02 11:23:04 -07:00 |
|
exllamav2_hf.py
|
Add cache_8bit option
|
2023-11-02 11:23:04 -07:00 |
|
extensions.py
|
|
|
|
github.py
|
|
|
|
GPTQ_loader.py
|
make torch.load a bit safer (#4448)
|
2023-11-02 14:07:08 -03:00 |
|
grammar.py
|
|
|
|
html_generator.py
|
|
|
|
llama_attn_hijack.py
|
|
|
|
llamacpp_hf.py
|
Disable logits_all in llamacpp_HF (makes processing 3x faster)
|
2023-11-07 14:35:48 -08:00 |
|
llamacpp_model.py
|
Add types to the encode/decode/token-count endpoints
|
2023-11-07 19:32:14 -08:00 |
|
loaders.py
|
Disable logits_all in llamacpp_HF (makes processing 3x faster)
|
2023-11-07 14:35:48 -08:00 |
|
logging_colors.py
|
|
|
|
logits.py
|
Intel Gpu support initialization (#4340)
|
2023-10-26 23:39:51 -03:00 |
|
LoRA.py
|
Intel Gpu support initialization (#4340)
|
2023-10-26 23:39:51 -03:00 |
|
metadata_gguf.py
|
|
|
|
models.py
|
Add /v1/internal/model/load endpoint (tentative)
|
2023-11-07 20:58:06 -08:00 |
|
models_settings.py
|
|
|
|
monkey_patch_gptq_lora.py
|
|
|
|
one_click_installer_check.py
|
|
|
|
presets.py
|
Make OpenAI API the default API (#4430)
|
2023-11-06 02:38:29 -03:00 |
|
prompts.py
|
|
|
|
relative_imports.py
|
|
|
|
RoPE.py
|
|
|
|
RWKV.py
|
Intel Gpu support initialization (#4340)
|
2023-10-26 23:39:51 -03:00 |
|
sampler_hijack.py
|
Add temperature_last parameter (#4472)
|
2023-11-04 13:09:07 -03:00 |
|
shared.py
|
Separate context and system message in instruction formats (#4499)
|
2023-11-07 20:02:58 -03:00 |
|
text_generation.py
|
Add types to the encode/decode/token-count endpoints
|
2023-11-07 19:32:14 -08:00 |
|
training.py
|
make torch.load a bit safer (#4448)
|
2023-11-02 14:07:08 -03:00 |
|
ui.py
|
Separate context and system message in instruction formats (#4499)
|
2023-11-07 20:02:58 -03:00 |
|
ui_chat.py
|
Document the new "Custom system message" field
|
2023-11-08 17:54:10 -08:00 |
|
ui_default.py
|
|
|
|
ui_file_saving.py
|
|
|
|
ui_model_menu.py
|
Disable logits_all in llamacpp_HF (makes processing 3x faster)
|
2023-11-07 14:35:48 -08:00 |
|
ui_notebook.py
|
|
|
|
ui_parameters.py
|
Add temperature_last parameter (#4472)
|
2023-11-04 13:09:07 -03:00 |
|
ui_session.py
|
|
|
|
utils.py
|
Refactor the /v1/models endpoint
|
2023-11-07 19:59:27 -08:00 |
