github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-27 16:17:28 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

Text Generation Documentation #3715

New Issue
Open
opened 2025-11-12 11:50:06 -06:00 by GiteaMirror · 5 comments
GiteaMirror commented 2025-11-12 11:50:06 -06:00
Owner
Copy Link

Originally created by @Demirrr on GitHub (Jul 25, 2024).

Dear all,

we ❤️ Ollama. Thank you for this great framework. I wa

There are many parameters for text generation Many of such parameters overlap with llama.ccp, while few of them do not, e.g.

  1. num_thread
  2. repeat_last_n
  3. num_batch
  4. f16_kv

I guess It would be great if you guys could write few sentences.

curl http://localhost:11434/api/generate -d '{
  "model": "llama3",
  "prompt": "Why is the sky blue?",
  "stream": false,
  "options": {
    "num_keep": 5,
    "seed": 42,
    "num_predict": 100,
    "top_k": 20,
    "top_p": 0.9,
    "tfs_z": 0.5,
    "typical_p": 0.7,
    "repeat_last_n": 33,
    "temperature": 0.8,
    "repeat_penalty": 1.2,
    "presence_penalty": 1.5,
    "frequency_penalty": 1.0,
    "mirostat": 1,
    "mirostat_tau": 0.8,
    "mirostat_eta": 0.6,
    "penalize_newline": true,
    "stop": ["\n", "user:"],
    "numa": false,
    "num_ctx": 1024,
    "num_batch": 2,
    "num_gpu": 1,
    "main_gpu": 0,
    "low_vram": false,
    "f16_kv": true,
    "vocab_only": false,
    "use_mmap": true,
    "use_mlock": false,
    "num_thread": 8
  }
}'
Originally created by @Demirrr on GitHub (Jul 25, 2024). Dear all, we ❤️ Ollama. Thank you for this great framework. I wa There are many parameters for text generation Many of such parameters overlap with [llama.ccp](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md#common-options), while few of them do not, e.g. 1. num_thread 2. repeat_last_n 3. num_batch 4. f16_kv I guess It would be great if you guys could write few sentences. ``` curl http://localhost:11434/api/generate -d '{ "model": "llama3", "prompt": "Why is the sky blue?", "stream": false, "options": { "num_keep": 5, "seed": 42, "num_predict": 100, "top_k": 20, "top_p": 0.9, "tfs_z": 0.5, "typical_p": 0.7, "repeat_last_n": 33, "temperature": 0.8, "repeat_penalty": 1.2, "presence_penalty": 1.5, "frequency_penalty": 1.0, "mirostat": 1, "mirostat_tau": 0.8, "mirostat_eta": 0.6, "penalize_newline": true, "stop": ["\n", "user:"], "numa": false, "num_ctx": 1024, "num_batch": 2, "num_gpu": 1, "main_gpu": 0, "low_vram": false, "f16_kv": true, "vocab_only": false, "use_mmap": true, "use_mlock": false, "num_thread": 8 } }' ```
GiteaMirror added the apifeature requestdocumentation labels 2025-11-12 11:50:07 -06:00
GiteaMirror commented 2025-11-12 11:50:08 -06:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 25, 2024):

num_thread is the same as llama.cpp --threads parameter.
repeat_last_n is --repeat-last-n.
num_batch is --batch-size
f16_kv is the inverse of --memory-f32. If f16_kv is set, --memory-f32 is not set. The default value for f16_kv is true.

@rick-github commented on GitHub (Jul 25, 2024): `num_thread` is the same as llama.cpp [`--threads`](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md#:~:text=%2Dt%20N%2C%20%2D%2Dthreads%20N%3A%20Set%20the%20number%20of%20threads%20to%20use%20during%20generation.%20For%20optimal%20performance%2C%20it%20is%20recommended%20to%20set%20this%20value%20to%20the%20number%20of%20physical%20CPU%20cores%20your%20system%20has.) parameter. `repeat_last_n` is [`--repeat-last-n`](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md#:~:text=%2D%2Drepeat%2Dlast%2Dn%20N%3A%20Last%20n%20tokens%20to%20consider%20for%20penalizing%20repetition%20(default%3A%2064%2C%200%20%3D%20disabled%2C%20%2D1%20%3D%20ctx%2Dsize).). `num_batch` is [`--batch-size`](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md#:~:text=%2Db%20N%2C%20%2D%2Dbatch%2Dsize%20N%3A%20Set%20the%20batch%20size%20for%20prompt%20processing%20(default%3A%202048).) `f16_kv` is the inverse of [`--memory-f32`](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md#:~:text=%2D%2Dmemory%2Df32%3A%20Use%2032%2Dbit%20floats%20instead%20of%2016%2Dbit%20floats%20for%20memory%20key%2Bvalue). If `f16_kv` is set, `--memory-f32` is not set. The default value for `f16_kv` is `true`.
GiteaMirror commented 2025-11-12 11:50:08 -06:00
Author
Owner
Copy Link

@Demirrr commented on GitHub (Jul 25, 2024):

Perfect! Thank you !

@Demirrr commented on GitHub (Jul 25, 2024): Perfect! Thank you !
GiteaMirror commented 2025-11-12 11:50:08 -06:00
Author
Owner
Copy Link

@Demirrr commented on GitHub (Jul 25, 2024):

@rick-github what about vocab_only ?

@Demirrr commented on GitHub (Jul 25, 2024): @rick-github what about vocab_only ?
GiteaMirror commented 2025-11-12 11:50:08 -06:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 25, 2024):

As far as I can tell, vocab_only is not currently used. It may be a deprecated option, or a placeholder for future use.

@rick-github commented on GitHub (Jul 25, 2024): As far as I can tell, `vocab_only` is not currently used. It may be a deprecated option, or a placeholder for future use.
GiteaMirror commented 2025-11-12 11:50:09 -06:00
Author
Owner
Copy Link

@Demirrr commented on GitHub (Jul 26, 2024):

Great thank you!

@Demirrr commented on GitHub (Jul 26, 2024): Great thank you!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
client2
cloud
compatibility
context-length
create
docker
documentation
embeddings
engine
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
install
integration
intel
js
linux
macos
memory
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
windows
wsl
No Label api documentation feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama-ollama#3715
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?