[GH-ISSUE #11751] /set nothink or --think=false Not working for gpt-oss:20b #69846

New Issue

GiteaMirror · 2026-05-04T19:33:01-05:00

GiteaMirror commented

2026-05-04 19:33:01 -05:00

Originally created by @cyperdev on GitHub (Aug 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11751

When using the gpt-oss:20b model, disabling the thinking output using either /set nothink in the console or the --think=false flag does not work. The model continues to generate and/or expose thinking traces despite the flag being passed.

Steps to reproduce:

Run the model with --think=false (or use /set nothink during an interactive session).

Prompt the model as usual.

Observe that it still outputs or behaves as if thinking mode is enabled.

Expected behaviour:

The model should suppress any thinking traces when --think=false is specified or when /set nothink is used.

Actual behaviour:

No change; the model still produces thinking traces or behaves as if think mode is active.

Environment:

Model: gpt-oss:20b

ollama version is 0.11.2

Originally created by @cyperdev on GitHub (Aug 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11751 When using the gpt-oss:20b model, disabling the thinking output using either /set nothink in the console or the --think=false flag does not work. The model continues to generate and/or expose thinking traces despite the flag being passed. Steps to reproduce: Run the model with --think=false (or use /set nothink during an interactive session). Prompt the model as usual. Observe that it still outputs or behaves as if thinking mode is enabled. Expected behaviour: The model should suppress any thinking traces when --think=false is specified or when /set nothink is used. Actual behaviour: No change; the model still produces thinking traces or behaves as if think mode is active. Environment: Model: gpt-oss:20b ollama version is 0.11.2

GiteaMirror closed this issue

2026-05-04 19:33:02 -05:00

GiteaMirror commented

2026-05-04 19:33:03 -05:00

@AltoRetrato commented on GitHub (Aug 6, 2025):

OpenAI Harmony: OpenAI's response format for its open-weight model series gpt-oss

OpenAI Harmony Response Format: The gpt-oss models were trained on the harmony response format for defining conversation structures, generating reasoning output and structuring function calls.

Role: system
Purpose: A system message is used to specify reasoning effort, meta information like knowledge cutoff and built-in tools

So it seems you can use the Harmony Response Format to set the reasoning "level" to high, medium, or low.

@AltoRetrato commented on GitHub (Aug 6, 2025): [OpenAI Harmony](https://github.com/openai/harmony): OpenAI's response format for its open-weight model series [gpt-oss](https://openai.com/open-models) [OpenAI Harmony Response Format](https://cookbook.openai.com/articles/openai-harmony): The [gpt-oss models](https://openai.com/open-models) were trained on the harmony response format for defining conversation structures, generating reasoning output and structuring function calls. - Role: system - Purpose: A system message is used to **specify reasoning effort**, meta information like knowledge cutoff and built-in tools So it seems you can use the **Harmony Response Format** to set the reasoning "level" to `high`, `medium`, or `low`.

GiteaMirror commented

2026-05-04 19:33:03 -05:00

@AltoRetrato commented on GitHub (Aug 6, 2025):

Reasoning: high example

Prompt

<|start|>system<|message|>Reasoning: high<|end|>
<|start|>user<|message|>
Anna places a red ball inside a cardboard box in the kitchen. She carries the box to the living room, 
then to the bedroom. She leaves the box there and goes to the bathroom for a few minutes. 
When she comes back, she picks up the box again and, without opening it, turns it upside-down in the hallway. 
Then she carries it to the garage and finally to the backyard. She now asks: “Where is the red ball?”
<|end|><|start|>assistant

Thinking (~1.783 chars)

Thinking...
We have a puzzle: Anna places a red ball inside a cardboard box in the kitchen. She carries the box to the living
room, then to the bedroom. She leaves the box there and goes to the bathroom for a few minutes. When she comes
back, she picks up the box again and, without opening it, turns it upside-down in the hallway. Then she carries it
to the garage and finally to the backyard. She now asks: “Where is the red ball?” The question seems to test logic
or location tracking. The ball hasn't been opened or removed. She turned the box upside-down but that doesn't
change its contents. So the ball remains inside the box. She carried the box to the backyard. So the ball is in
the backyard, inside the box. So answer: in the backyard in the box. But maybe trick: "She leaves the box there
and goes to the bathroom" might cause ball to fall? But no. The box is closed. So the ball is inside the box. So
answer: The red ball is in the cardboard box in the backyard. But maybe she didn't open it. So ball still inside
the box. So location: backyard. So the answer: In the backyard, inside the cardboard box. So maybe it's still in
the cardboard box. The question might be from a riddle: The red ball remains in the cardboard box and thus in the
backyard. So answer: It's still in the box. So we can answer: The red ball is in the backyard inside the cardboard
box. Or "In the box" if we are asked "Where is the ball?" The answer: In the cardboard box.

But maybe there's something else: She turned it upside-down in the hallway. Could have thrown it? No, she didn't
open it. So ball remains inside. So answer: In the backyard, in the cardboard box.

Therefore answer: In the backyard, inside the cardboard box.

Let's provide that.
...done thinking.

Answer

The red ball is still inside the cardboard box – the box has been carried all the way to the backyard, so the ball
is in the backyard, inside that box.

Reasoning: low example

Prompt

<|start|>system<|message|>Reasoning: low<|end|>
<|start|>user<|message|>
Anna places a red ball inside a cardboard box in the kitchen. She carries the box to the living room, 
then to the bedroom. She leaves the box there and goes to the bathroom for a few minutes. 
When she comes back, she picks up the box again and, without opening it, turns it upside-down in the hallway. 
Then she carries it to the garage and finally to the backyard. She now asks: “Where is the red ball?”
<|end|><|start|>assistant

Thinking (~576 chars)

Thinking...
We need to answer the riddle: The ball hasn't been opened or removed; she hasn't opened the box, so the ball
remains inside the box. She turns it upside down but no effect. So the red ball is still in the box. She didn't
open it. So answer: In the box. But maybe trick: She didn't mention opening. So ball still in the cardboard box.
So answer: It's still in the box, wherever the box currently is (backyard). She turned it upside down but didn't
open it. So ball remains. So answer: In the cardboard box in the backyard. Provide reasoning.
...done thinking.

Answer

The ball is still inside the cardboard box.
She never opened the box, so the ball didn’t leave it.
After turning it upside‑down she carried the box to the backyard, so the red ball is there, snug inside the
cardboard box.

@AltoRetrato commented on GitHub (Aug 6, 2025): **`Reasoning: high` example** <details> <summary>Prompt</summary> ``` <|start|>system<|message|>Reasoning: high<|end|> <|start|>user<|message|> Anna places a red ball inside a cardboard box in the kitchen. She carries the box to the living room, then to the bedroom. She leaves the box there and goes to the bathroom for a few minutes. When she comes back, she picks up the box again and, without opening it, turns it upside-down in the hallway. Then she carries it to the garage and finally to the backyard. She now asks: “Where is the red ball?” <|end|><|start|>assistant ``` </details> <details> <summary>Thinking (~1.783 chars)</summary> ``` Thinking... We have a puzzle: Anna places a red ball inside a cardboard box in the kitchen. She carries the box to the living room, then to the bedroom. She leaves the box there and goes to the bathroom for a few minutes. When she comes back, she picks up the box again and, without opening it, turns it upside-down in the hallway. Then she carries it to the garage and finally to the backyard. She now asks: “Where is the red ball?” The question seems to test logic or location tracking. The ball hasn't been opened or removed. She turned the box upside-down but that doesn't change its contents. So the ball remains inside the box. She carried the box to the backyard. So the ball is in the backyard, inside the box. So answer: in the backyard in the box. But maybe trick: "She leaves the box there and goes to the bathroom" might cause ball to fall? But no. The box is closed. So the ball is inside the box. So answer: The red ball is in the cardboard box in the backyard. But maybe she didn't open it. So ball still inside the box. So location: backyard. So the answer: In the backyard, inside the cardboard box. So maybe it's still in the cardboard box. The question might be from a riddle: The red ball remains in the cardboard box and thus in the backyard. So answer: It's still in the box. So we can answer: The red ball is in the backyard inside the cardboard box. Or "In the box" if we are asked "Where is the ball?" The answer: In the cardboard box. But maybe there's something else: She turned it upside-down in the hallway. Could have thrown it? No, she didn't open it. So ball remains inside. So answer: In the backyard, in the cardboard box. Therefore answer: In the backyard, inside the cardboard box. Let's provide that. ...done thinking. ``` </details> <details> <summary>Answer</summary> ``` The red ball is still inside the cardboard box – the box has been carried all the way to the backyard, so the ball is in the backyard, inside that box. ``` </details> **`Reasoning: low` example** <details> <summary>Prompt</summary> ``` <|start|>system<|message|>Reasoning: low<|end|> <|start|>user<|message|> Anna places a red ball inside a cardboard box in the kitchen. She carries the box to the living room, then to the bedroom. She leaves the box there and goes to the bathroom for a few minutes. When she comes back, she picks up the box again and, without opening it, turns it upside-down in the hallway. Then she carries it to the garage and finally to the backyard. She now asks: “Where is the red ball?” <|end|><|start|>assistant ``` </details> <details> <summary>Thinking (~576 chars)</summary> ``` Thinking... We need to answer the riddle: The ball hasn't been opened or removed; she hasn't opened the box, so the ball remains inside the box. She turns it upside down but no effect. So the red ball is still in the box. She didn't open it. So answer: In the box. But maybe trick: She didn't mention opening. So ball still in the cardboard box. So answer: It's still in the box, wherever the box currently is (backyard). She turned it upside down but didn't open it. So ball remains. So answer: In the cardboard box in the backyard. Provide reasoning. ...done thinking. ``` </details> <details> <summary>Answer</summary> ``` The ball is still inside the cardboard box. She never opened the box, so the ball didn’t leave it. After turning it upside‑down she carried the box to the backyard, so the red ball is there, snug inside the cardboard box. ``` </details>

GiteaMirror commented

2026-05-04 19:33:04 -05:00

@drifkin commented on GitHub (Aug 7, 2025):

gpt-oss doesn't natively support not thinking. For deepseek-r1 we put in a template hack to prefill it with an empty thinking trace, which doesn't work great. gpt-oss doesn't work well with this technique. If you want to try out something similar, you can pass in a role: "assistant" message as the final message and pass in some very short (but non-empty) "thinking" text to see how it behaves with hardcoded thoughts

@drifkin commented on GitHub (Aug 7, 2025): `gpt-oss` doesn't natively support not thinking. For deepseek-r1 we put in a template hack to prefill it with an empty thinking trace, which doesn't work great. `gpt-oss` doesn't work well with this technique. If you want to try out something similar, you can pass in a `role: "assistant"` message as the final message and pass in some very short (but non-empty) `"thinking"` text to see how it behaves with hardcoded thoughts

GiteaMirror commented

2026-05-04 19:33:04 -05:00

@EmirhanSyl commented on GitHub (Aug 7, 2025):

Interestingly, my model doesn't make rasoning while using it via from langchain_openai import ChatOpenAI class. I want to enable reasoning but model gives direct answer instead of internal reasoning. Here is the definition of the model in my code:

question_agent = ChatOpenAI(
    model="gpt-oss",
    base_url=ollama_url,
    api_key="dummy",
    streaming=True,
    temperature=0.1,
)

It also has 18 different tool bindings about statistics.

@EmirhanSyl commented on GitHub (Aug 7, 2025): Interestingly, my model doesn't make rasoning while using it via `from langchain_openai import ChatOpenAI` class. I want to enable reasoning but model gives direct answer instead of internal reasoning. Here is the definition of the model in my code: ```py question_agent = ChatOpenAI( model="gpt-oss", base_url=ollama_url, api_key="dummy", streaming=True, temperature=0.1, ) ``` It also has 18 different tool bindings about statistics.

GiteaMirror commented

2026-05-04 19:33:05 -05:00

@MarcoFerreiraPerson commented on GitHub (Aug 7, 2025):

Interestingly, my model doesn't make rasoning while using it via from langchain_openai import ChatOpenAI class. I want to enable reasoning but model gives direct answer instead of internal reasoning. Here is the definition of the model in my code:

question_agent = ChatOpenAI(
model="gpt-oss",
base_url=ollama_url,
api_key="dummy",
streaming=True,
temperature=0.1,
)

It also has 18 different tool bindings about statistics.

same issue

@MarcoFerreiraPerson commented on GitHub (Aug 7, 2025): > Interestingly, my model doesn't make rasoning while using it via `from langchain_openai import ChatOpenAI` class. I want to enable reasoning but model gives direct answer instead of internal reasoning. Here is the definition of the model in my code: > > question_agent = ChatOpenAI( > model="gpt-oss", > base_url=ollama_url, > api_key="dummy", > streaming=True, > temperature=0.1, > ) > > It also has 18 different tool bindings about statistics. same issue

GiteaMirror commented

2026-05-04 19:33:05 -05:00

@EmirhanSyl commented on GitHub (Aug 7, 2025):

I fixed this issue by simply updating langchain-ollama and langchain-openai models. After updating it, reasoning content comes under "additional_kwargs" while using ChatOllama. But in any cases model was doing reasoning

Interestingly, my model doesn't make rasoning while using it via from langchain_openai import ChatOpenAI class. I want to enable reasoning but model gives direct answer instead of internal reasoning. Here is the definition of the model in my code:
question_agent = ChatOpenAI(
model="gpt-oss",
base_url=ollama_url,
api_key="dummy",
streaming=True,
temperature=0.1,
)
It also has 18 different tool bindings about statistics.

same issue

@EmirhanSyl commented on GitHub (Aug 7, 2025): I fixed this issue by simply updating `langchain-ollama` and `langchain-openai` models. After updating it, reasoning content comes under "additional_kwargs" while using ChatOllama. But in any cases model was doing reasoning > > Interestingly, my model doesn't make rasoning while using it via `from langchain_openai import ChatOpenAI` class. I want to enable reasoning but model gives direct answer instead of internal reasoning. Here is the definition of the model in my code: > > question_agent = ChatOpenAI( > > model="gpt-oss", > > base_url=ollama_url, > > api_key="dummy", > > streaming=True, > > temperature=0.1, > > ) > > It also has 18 different tool bindings about statistics. > > same issue

GiteaMirror commented

2026-05-04 19:33:06 -05:00

@ggcr commented on GitHub (Sep 2, 2025):

Interestingly, my model doesn't make rasoning while using it via from langchain_openai import ChatOpenAI class. I want to enable reasoning but model gives direct answer instead of internal reasoning. Here is the definition of the model in my code:

question_agent = ChatOpenAI(
model="gpt-oss",
base_url=ollama_url,
api_key="dummy",
streaming=True,
temperature=0.1,
)
It also has 18 different tool bindings about statistics.

Have you tried increasing the temperature? 0.1 might be too low for reasoning models, Unsloth recommends a temperature of 1.0

@ggcr commented on GitHub (Sep 2, 2025): > Interestingly, my model doesn't make rasoning while using it via `from langchain_openai import ChatOpenAI` class. I want to enable reasoning but model gives direct answer instead of internal reasoning. Here is the definition of the model in my code: > > question_agent = ChatOpenAI( > model="gpt-oss", > base_url=ollama_url, > api_key="dummy", > streaming=True, > temperature=0.1, > ) > It also has 18 different tool bindings about statistics. Have you tried increasing the temperature? 0.1 might be too low for reasoning models, [Unsloth](https://docs.unsloth.ai/basics/gpt-oss-how-to-run-and-fine-tune) recommends a temperature of 1.0

GiteaMirror commented

2026-05-04 19:33:06 -05:00

@clort81 commented on GitHub (Jan 30, 2026):

<|start|>system<|message|>Reasoning: low<|end|>
<|start|>user<|message|>
Anna places a red ball inside a cardboard box in the kitchen. She carries the box to the living room,
then to the bedroom. She leaves the box there and goes to the bathroom for a few minutes.
When she comes back, she picks up the box again and, without opening it, turns it upside-down in the hallway.
Then she carries it to the garage and finally to the backyard. She now asks: “Where is the red ball?”
<|end|><|start|>assistant

There is no correct answer since you never specified that she closed the top of the box after placing the ball inside. The box could be open the entire time thus ball could be in hallway.

Yes, if the box is already open, then you can't open it again.

Please think of a logical question next time before 'testing' your model.

@clort81 commented on GitHub (Jan 30, 2026): > <|start|>system<|message|>Reasoning: low<|end|> > <|start|>user<|message|> > Anna places a red ball inside a cardboard box in the kitchen. She carries the box to the living room, > then to the bedroom. She leaves the box there and goes to the bathroom for a few minutes. > When she comes back, she picks up the box again and, without opening it, turns it upside-down in the hallway. > Then she carries it to the garage and finally to the backyard. She now asks: “Where is the red ball?” > <|end|><|start|>assistant There is no correct answer since you never specified that she closed the top of the box after placing the ball inside. The box could be open the entire time thus ball could be in hallway. Yes, if the box is already open, then you can't open it again. Please think of a logical question next time before 'testing' your model.

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

dhiltgen/llama-runner

parth-launch-codex-app

hoyyeva/anthropic-local-image-path

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#69846