vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-15 19:39:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	Package.swift
This commit is contained in:
Concedo 2024-01-05 18:32:54 +08:00
commit c9fdd42da2
9 changed files with 88 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/server/README.md
View file

@ -168,6 +168,12 @@ node index.js
`image_data`: An array of objects to hold base64-encoded image `data` and its `id`s to be reference in `prompt`. You can determine the place of the image in the prompt as in the following: `USER:[img-12]Describe the image in detail.\nASSISTANT:`. In this case, `[img-12]` will be replaced by the embeddings of the image with id `12` in the following `image_data` array: `{..., "image_data": [{"data": "<BASE64_STRING>", "id": 12}]}`. Use `image_data` only with multimodal models, e.g., LLaVA.
`slot_id`: Assign the completion task to an specific slot. If is -1 the task will be assigned to a Idle slot (default: -1)
`cache_prompt`: Save the prompt and generation for avoid reprocess entire prompt if a part of this isn't change (default: false)
`system_prompt`: Change the system prompt (initial prompt of all slots), this is useful for chat applications. [See more](#change-system-prompt-on-runtime)
*Result JSON:*
Note: When using streaming mode (`stream`) only `content` and `stop` will be returned until end of completion.
@ -198,12 +204,6 @@ node index.js
`truncated`: Boolean indicating if the context size was exceeded during generation, i.e. the number of tokens provided in the prompt (`tokens_evaluated`) plus tokens generated (`tokens predicted`) exceeded the context size (`n_ctx`)
`slot_id`: Assign the completion task to an specific slot. If is -1 the task will be assigned to a Idle slot (default: -1)
`cache_prompt`: Save the prompt and generation for avoid reprocess entire prompt if a part of this isn't change (default: false)
`system_prompt`: Change the system prompt (initial prompt of all slots), this is useful for chat applications. [See more](#change-system-prompt-on-runtime)
- **POST** `/tokenize`: Tokenize a given text.
*Options:*

4
examples/server/server.cpp
View file

@ -1266,7 +1266,7 @@ struct llama_server_context
{
std::vector<completion_token_output> probs_output = {};
const std::vector<llama_token> to_send_toks = llama_tokenize(ctx, tkn.text_to_send, false);
size_t probs_pos = std::min(slot.sent_token_probs_index, slot.generated_token_probs.size());
size_t probs_pos = std::min(slot.sent_token_probs_index, slot.generated_token_probs.size());
size_t probs_stop_pos = std::min(slot.sent_token_probs_index + to_send_toks.size(), slot.generated_token_probs.size());
if (probs_pos < probs_stop_pos)
{
@ -1326,7 +1326,7 @@ struct llama_server_context
{
probs = std::vector<completion_token_output>(
slot.generated_token_probs.begin(),
slot.generated_token_probs.begin() + slot.sent_token_probs_index);
slot.generated_token_probs.end());
}
res.result_json["completion_probabilities"] = probs_vector_to_json(ctx, probs);
}