_service

@@ -3,7 +3,7 @@
   <service name="obs_scm" mode="manual">
     <param name="url">https://github.com/ollama/ollama.git</param>
     <param name="scm">git</param>
-    <param name="revision">v0.5.7</param>
+    <param name="revision">v0.3.6</param>
     <param name="versionformat">@PARENT_TAG@</param>
     <param name="versionrewrite-pattern">v(.*)</param>
     <param name="changesgenerate">enable</param>
@@ -19,5 +19,5 @@
   <service name="tar" mode="buildtime">
     <param name="package-meta">yes</param>
   </service>
-
+  
 </services>

_servicedata

@@ -1,4 +1,4 @@
 <servicedata>
 <service name="tar_scm">
                 <param name="url">https://github.com/ollama/ollama.git</param>
-              <param name="changesrevision">a420a453b4783841e3e79c248ef0fe9548df6914</param></service></servicedata>
+              <param name="changesrevision">4c4fe3f87fe1858b35bd0d41e093a0039ec4cee4</param></service></servicedata>

enable-lto.patch

@@ -0,0 +1,28 @@
+diff --git a/llm/generate/gen_linux.sh b/llm/generate/gen_linux.sh
+index db2c6c3..8194cd9 100755
+--- a/llm/generate/gen_linux.sh
++++ b/llm/generate/gen_linux.sh
+@@ -52,6 +52,7 @@ if [ -z "${CUDACXX}" ]; then
+     fi
+ fi
+ COMMON_CMAKE_DEFS="-DBUILD_SHARED_LIBS=off -DCMAKE_POSITION_INDEPENDENT_CODE=on -DGGML_NATIVE=off -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_OPENMP=off"
++COMMON_CMAKE_DEFS="${COMMON_CMAKE_DEFS} -DGGML_LTO=on -DCMAKE_BUILD_TYPE=Release"
+ source $(dirname $0)/gen_common.sh
+ init_vars
+ git_module_setup
+@@ -78,6 +79,7 @@ if [ -z "${OLLAMA_SKIP_CPU_GENERATE}" ]; then
+         init_vars
+         echo "OLLAMA_CUSTOM_CPU_DEFS=\"${OLLAMA_CUSTOM_CPU_DEFS}\""
+         CMAKE_DEFS="${OLLAMA_CUSTOM_CPU_DEFS} -DBUILD_SHARED_LIBS=off -DCMAKE_POSITION_INDEPENDENT_CODE=on ${CMAKE_DEFS}"
++        CMAKE_DEFS="${CMAKE_DEFS} -DGGML_LTO=on"
+         BUILD_DIR="../build/linux/${ARCH}/cpu"
+         echo "Building custom CPU"
+         build
+@@ -94,6 +96,7 @@ if [ -z "${OLLAMA_SKIP_CPU_GENERATE}" ]; then
+         # -DGGML_AVX512_VNNI -- 2021 Intel Alder Lake
+ 
+         COMMON_CPU_DEFS="-DBUILD_SHARED_LIBS=off -DCMAKE_POSITION_INDEPENDENT_CODE=on -DGGML_NATIVE=off -DGGML_OPENMP=off"
++        COMMON_CPU_DEFS="${COMMON_CPU_DEFS} -DGGML_LTO=on -DCMAKE_BUILD_TYPE=Release"
+         if [ -z "${OLLAMA_CPU_TARGET}" -o "${OLLAMA_CPU_TARGET}" = "cpu" ]; then
+             #
+             # CPU first for the default library, set up as lowest common denominator for maximum compatibility (including Rosetta)

ollama-0.5.7.obscpio

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:efb1f1510c40a71f933e8b1ad3b88acb499f017e1bfd271492d9ccf5b7a69d2c
-size 154515982

ollama.changes

@@ -1,438 +1,3 @@
--------------------------------------------------------------------
-Mon Jan 27 14:21:42 UTC 2025 - Adrian Schröter <adrian@suse.de>
-
-- Make ollama configurable by the admin via /etc/sysconfig/ollama
-  (boo#1236008)
-- cleanup reproducible.patch
-
--------------------------------------------------------------------
-Thu Jan 16 23:52:45 UTC 2025 - Eyad Issa <eyadlorenzo@gmail.com>
-
-- Removed 01-build-verbose.patch: embedded GOFLAG into .spec file
-- Disabled reproducible.patch: should be not needed, as .gz is
-  not produced anymore
-
-- Update to version 0.5.7:
-  * Fixed issue where using two FROM commands in Modelfile
-  * Support importing Command R and Command R+ architectures
-    from safetensors
-
-- Update to version 0.5.6:
-  * Fixed errors that would occur when running ollama create on
-    Windows and when using absolute paths
-
-- Update to version 0.5.5:
-  * New models:
-    ~ Phi-4
-    ~ Command R7B
-    ~ DeepSeek-V3
-    ~ OLMo 2
-    ~ Dolphin 3
-    ~ SmallThinker:
-    ~ Granite 3.1 Dense
-    ~ Granite 3.1 MoE
-  * The /api/create API endpoint that powers ollama create has
-    been changed to improve conversion time and also accept a JSON
-    object.
-  * Fixed runtime error that would occur when filling the model's
-    context window
-  * Fixed crash that would occur when quotes were used in /save
-  * Fixed errors that would occur when sending x-stainless headers
-    from OpenAI clients
-
-- Update to version 0.5.4:
-  * New model: Falcon3
-  * Fixed issue where providing null to format would result in
-    an error
-
-- Update to version 0.5.3:
-  * Fixed runtime errors on older Intel Macs
-  * Fixed issue where setting the format field to "" would cause
-    an error
-
-
-- Update to version 0.5.2:
-  * New model: EXAONE 3.5
-  * Fixed issue where whitespace would get trimmed from prompt
-    when images were provided
-  * Improved memory estimation when scheduling models
-  * OLLAMA_ORIGINS will now check hosts in a case insensitive
-    manner
-
--------------------------------------------------------------------
-Thu Dec 12 14:00:56 UTC 2024 - Bernhard Wiedemann <bwiedemann@suse.com>
-
-- Add reproducible.patch for deterministic .gz creation (boo#1047218)
-
--------------------------------------------------------------------
-Sat Dec 07 18:24:04 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
-
-- Update to version 0.5.1:
-  * Fixed issue where Ollama's API would generate JSON output when
-    specifying "format": null
-  * Fixed issue where passing --format json to ollama run would
-    cause an error
-
-- Update to version 0.5.0:
-  * New models:
-    ~ Llama 3.3: a new state of the art 70B model.
-    ~ Snowflake Arctic Embed 2: Snowflake's frontier embedding
-      model.
-  * Ollama now supports structured outputs, making it possible to
-    constrain a model's output to a specific format defined by a
-    JSON schema. The Ollama Python and JavaScript libraries have
-    been updated to support structured outputs, together with
-    Ollama's OpenAI-compatible API endpoints.
-  * Fixed error importing model vocabulary files
-  * Experimental: new flag to set KV cache quantization to 4-bit
-    (q4_0), 8-bit (q8_0) or 16-bit (f16). This reduces VRAM
-    requirements for longer context windows.
-
-- Update to version 0.4.7:
-  * Enable index tracking for tools - openai api support (#7888)
-  * llama: fix typo and formatting in readme (#7876)
-  * readme: add SpaceLlama, YouLama, and DualMind to community
-    integrations (#7216)
-
--------------------------------------------------------------------
-Sat Nov 30 19:47:23 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
-
-- Update to version 0.4.6:
-  * New model: QwQ: an experimental research model by the Qwen
-    team, focused on advancing AI reasoning capabilities.
-  * Tool calls will now be included in streaming responses
-  * Ollama will now provide an error when submitting SVG images
-  * Image tokens will no longer be counted in token counts when
-    running a text-only model
-
-- Update to version 0.4.5:
-  * The Ollama Python Library has been updated
-  * Fixed issue where HTTPS_PROXY and HTTP_PROXY environment
-    variables would have no effect
-  * Ollama will now accept X-Stainless-Retry-Count used by many
-    OpenAI API clients
-  * Fix issue where importing certain GGUF files would result in
-    the incorrect quantization level
-  * ollama push will now print the uploaded model URL on
-    ollama.com
-
-- Update to version 0.4.4:
-  * Marco-o1: An open large reasoning model for real-world
-    solutions by the Alibaba International Digital Commerce Group
-    (AIDC-AI).
-  * Fixed issue where Ollama would freeze when processing requests
-    in parallel (e.g. when using code completion tools)
-  * Redirecting output to a file no longer outputs progress bars
-    or spinners
-
-- Update to version 0.4.3:
-  * New model: Tülu 3 is a leading instruction following model
-    family, offering fully open-source data, code, and recipes by
-    the The Allen Institute for AI.
-  * New model: Mistral Large: a new version of Mistral Large with
-    improved Long Context, Function Calling and System Prompt
-    support.
-  * Improved performance issues that occurred in Ollama versions
-    0.4.0-0.4.2
-  * Fixed issue that would cause granite3-dense to generate empty
-    responses
-  * Fixed crashes and hanging caused by KV cache management
-
--------------------------------------------------------------------
-Sat Nov 16 16:07:38 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
-
-- Update to version 0.4.2:
-  * runner.go: Propagate panics back to the user.
-  * runner.go: Increase survivability of main processing loop
-  * build: fix arm container image (#7674)
-  * add line numbers for parser errors (#7326)
-  * chore(deps): bump golang.org/x dependencies (#7655)
-  * runner.go: Don't trim whitespace from inputs
-  * runner.go: Enforce NUM_PARALLEL directly in the runner
-  * cmd: preserve exact bytes when displaying template/system layers (#7586)
-  * fix(mllama): sync backend between batches
-  * runner.go: Fix off-by-one for num predicted
-  * CI: give windows lint more time (#7635)
-  * Jetpack support for Go server (#7217)
-  * doc: capture numeric group requirement (#6941)
-  * docs: Capture docker cgroup workaround (#7519)
-  * runner.go: Make KV entry accounting more robust
-  * readme: add aichat terminal app to community integrations (#7418)
-  * api: fix typos in Go Doc comments (#7620)
-  * readme: add GoLamify to community integrations (#7521)
-  * readme: add browser extension that enables using Ollama for interacting with web pages (#5827)
-  * docs: add mentions of Llama 3.2 (#7517)
-  * api: fix typo in python ClientFromEnvironment docs (#7604)
-  * readme: add llama3.2-vision to model list (#7580)
-
--------------------------------------------------------------------
-Mon Nov 11 13:57:46 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
-
-- Add patch 01-build-verbose.patch to add the -v option
-  to go build
-
-- Update to version 0.4.1:
-  * runner.go: Check for zero length images
-  * docs: update langchainpy.md with proper model name (#7527)
-  * Set macos min version for all architectures (#7579)
-  * win: remove preview title from installer (#7529)
-  * Workaround buggy P2P ROCm copy on windows (#7466)
-  * Debug logging for nvcuda init (#7532)
-  * Align rocm compiler flags (#7467)
-  * Be explicit for gpu library link dir (#7560)
-  * docs: OLLAMA_NEW_RUNNERS no longer exists
-  * runner.go: Remove unused arguments
-  * sched: Lift parallel restriction for multimodal models except mllama
-
--------------------------------------------------------------------
-Thu Nov 07 12:06:09 UTC 2024 - adrian@suse.de
-
-- Update to version 0.4.0:
-  * Update README.md (#7516)
-  * One corrupt manifest should not wedge model operations (#7515)
-  * prompt: Use a single token when estimating mllama context size
-  * readme: add Hexabot to the list of community integrations
-  * Quiet down debug log of image payload (#7454)
-
--------------------------------------------------------------------
-Wed Nov 06 12:31:53 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
-
-- Update to version 0.4.0-rc8:
-  * CI: Switch to v13 macos runner (#7498)
-  * CI: matrix strategy fix (#7496)
-  * Sign windows arm64 official binaries (#7493)
-  * readme: add TextCraft to community integrations (#7377)
-  * nvidia libs have inconsistent ordering (#7473)
-  * CI: omit unused tools for faster release builds (#7432)
-  * llama: Improve error handling
-  * runner.go: Only allocate 1 element embedding batches for mllama
-  * refactor kv estimation
-  * mllama cross attention
-  * Add basic mllama integration tests (#7455)
-  * runner.go: Don't set cross attention before sending embeddings
-  * Give unicode test more time to run (#7437)
-
--------------------------------------------------------------------
-Fri Nov 01 02:18:50 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
-
-- Remove enable-lto.patch
-
-- Update to version 0.4.0-rc6:
-  * Refine default thread selection for NUMA systems (#7322)
-  * runner.go: Better abstract vision model integration
-  * Soften windows clang requirement (#7428)
-  * Remove submodule and shift to Go server - 0.4.0  (#7157)
-  * Move windows app out of preview (#7347)
-  * windows: Support alt install paths, fit and finish (#6967)
-  * add more tests for getting the optimal tiled canvas (#7411)
-  * Switch windows to clang (#7407)
-  * tests: Add test for Unicode processing
-  * runner.go: Better handle return NULL values from llama.cpp
-  * add mllama image processing to the generate handler (#7384)
-  * Bump to latest Go 1.22 patch (#7379)
-  * Fix deepseek deseret regex (#7369)
-  * Better support for AMD multi-GPU on linux (#7212)
-  * Fix unicode output on windows with redirect to file (#7358)
-  * Fix incremental build file deps (#7361)
-  * Improve dependency gathering logic (#7345)
-  * fix #7247 - invalid image input (#7249)
-  * integration: harden embedding test (#7306)
-  * default to "FROM ." if a Modelfile isn't present (#7250)
-  * Fix rocm windows build and clean up dependency gathering (#7305)
-  * runner.go: Merge partial unicode characters before sending
-  * readme: add Ollama for Swift to the community integrations (#7295)
-  * server: allow vscode-webview origin (#7273)
-  * image processing for llama3.2 (#6963)
-  * llama: Decouple patching script from submodule (#7139)
-  * llama: add compiler tags for cpu features (#7137)
-
--------------------------------------------------------------------
-Wed Oct 30 01:47:37 UTC 2024 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
-
-- Update to version 0.3.14:
-  * New Models
-    + Granite 3 MoE: The IBM Granite 1B and 3B models are the
-      first mixture of experts (MoE) Granite models from IBM
-      designed for low latency usage.
-    + Granite 3 Dense: The IBM Granite 2B and 8B models are
-      designed to support tool-based use cases and support for
-      retrieval augmented generation (RAG), streamlining code
-      generation, translation and bug fixing.
-
--------------------------------------------------------------------
-Sat Oct 12 20:55:18 UTC 2024 - eyadlorenzo@gmail.com
-
-- Update to version 0.3.13:
-  * New safety models:
-    ~ Llama Guard 3: a series of models by Meta, fine-tuned for
-      content safety classification of LLM inputs and responses.
-    ~ ShieldGemma: ShieldGemma is set of instruction tuned models
-      from Google DeepMind for evaluating the safety of text
-      prompt input and text output responses against a set of
-      defined safety policies.
-  * Fixed issue where ollama pull would leave connections when
-    encountering an error
-  * ollama rm will now stop a model if it is running prior to
-    deleting it
--------------------------------------------------------------------
-Sat Sep 28 03:53:10 UTC 2024 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
-
-- Update to version 0.3.12:
-  * Llama 3.2: Meta's Llama 3.2 goes small with 1B and 3B
-    models.
-  * Qwen 2.5 Coder: The latest series of Code-Specific Qwen
-    models, with significant improvements in code generation,
-    code reasoning, and code fixing.
-  * Ollama now supports ARM Windows machines
-  * Fixed rare issue where Ollama would report a missing .dll
-    file on Windows
-  * Fixed performance issue for Windows without GPUs
-
--------------------------------------------------------------------
-Fri Sep 20 08:29:30 UTC 2024 - adrian@suse.de
-
-- Update to version 0.3.11:
-  * llm: add solar pro (preview) (#6846)
-  * server: add tool parsing support for nemotron-mini (#6849)
-  * make patches git am-able
-  * CI: dist directories no longer present (#6834)
-  * CI: clean up naming, fix tagging latest (#6832)
-  * CI: set platform build build_linux script to keep buildx happy (#6829)
-  * readme: add Agents-Flex to community integrations (#6788)
-  * fix typo in import docs (#6828)
-  * readme: add vim-intelligence-bridge to Terminal section (#6818)
-  * readme: add Obsidian Quiz Generator plugin to community integrations (#6789)
-  * Fix incremental builds on linux (#6780)
-  * Use GOARCH for build dirs (#6779)
-  * Optimize container images for startup (#6547)
-  * examples: updated requirements.txt for privategpt example
-  * examples: polish loganalyzer example (#6744)
-  * readme: add ollama_moe to community integrations (#6752)
-  * runner: Flush pending responses before returning
-  * add "stop" command (#6739)
-  * refactor show ouput
-  * readme: add QodeAssist to community integrations (#6754)
-  * Verify permissions for AMD GPU (#6736)
-  * add *_proxy for debugging
-  * docs: update examples to use llama3.1 (#6718)
-  * Quiet down dockers new lint warnings (#6716)
-  * catch when model vocab size is set correctly (#6714)
-  * readme: add crewAI to community integrations (#6699)
-  * readme: add crewAI with mesop to community integrations
-
--------------------------------------------------------------------
-Tue Sep 17 10:48:34 UTC 2024 - adrian@suse.de
-
-- Update to version 0.3.10:
-  * openai: align chat temperature and frequency_penalty options with completion (#6688)
-  * docs: improve linux install documentation (#6683)
-  * openai: don't scale temperature or frequency_penalty (#6514)
-  * readme: add Archyve to community integrations (#6680)
-  * readme: add Plasmoid Ollama Control to community integrations (#6681)
-  * Improve logging on GPU too small (#6666)
-  * openai: fix "presence_penalty" typo and add test (#6665)
-  * Fix gemma2 2b conversion (#6645)
-  * Document uninstall on windows (#6663)
-  * Revert "Detect running in a container (#6495)" (#6662)
-  * llm: make load time stall duration configurable via OLLAMA_LOAD_TIMEOUT
-  * Introduce GPU Overhead env var (#5922)
-  * Detect running in a container (#6495)
-  * readme: add AiLama to the list of community integrations (#4957)
-  * Update gpu.md: Add RTX 3050 Ti and RTX 3050 Ti (#5888)
-  * server: fix blob download when receiving a 200 response  (#6656)
-  * readme: add Gentoo package manager entry to community integrations (#5714)
-  * Update install.sh：Replace "command -v" with encapsulated functionality (#6035)
-  * readme: include Enchanted for Apple Vision Pro (#4949)
-  * readme: add lsp-ai to community integrations (#5063)
-  * readme: add ollama-php library to community integrations (#6361)
-  * readme: add vnc-lm discord bot community integration (#6644)
-  * llm: use json.hpp from common (#6642)
-  * readme: add confichat to community integrations (#6378)
-  * docs: add group to manual Linux isntructions and verify service is running (#6430)
-  * readme: add gollm to the list of community libraries (#6099)
-  * readme: add Cherry Studio to community integrations (#6633)
-  * readme: add Go fun package (#6421)
-  * docs: fix spelling error (#6391)
-  * install.sh: update instructions to use WSL2 (#6450)
-  * readme: add claude-dev to community integrations (#6630)
-  * readme: add PyOllaMx project (#6624)
-  * llm: update llama.cpp commit to 8962422 (#6618)
-  * Use cuda v11 for driver 525 and older (#6620)
-  * Log system memory at info (#6617)
-  * readme: add Painting Droid community integration (#5514)
-  * readme: update Ollama4j link and add link to Ollama4j Web UI (#6608)
-  * Fix sprintf to snprintf (#5664)
-  * readme: add PartCAD tool to readme for generating 3D CAD models using Ollama (#6605)
-  * Reduce docker image size (#5847)
-  * readme: add OllamaFarm project (#6508)
-  * readme: add go-crew and Ollamaclient projects (#6583)
-  * docs: update faq.md for OLLAMA_MODELS env var permissions (#6587)
-  * fix(cmd): show info may have nil ModelInfo (#6579)
-  * docs: update GGUF examples and references (#6577)
-  * Add findutils to base images (#6581)
-  * remove any unneeded build artifacts
-  * doc: Add Nix and Flox to package manager listing (#6074)
-  * update the openai docs to explain how to set the context size (#6548)
-  * fix(test): do not clobber models directory
-  * add llama3.1 chat template (#6545)
-  * update deprecated warnings
-  * validate model path
-  * throw an error when encountering unsupport tensor sizes (#6538)
-  * Move ollama executable out of bin dir (#6535)
-  * update templates to use messages
-  * more tokenizer tests
-  * add safetensors to the modelfile docs (#6532)
-  * Fix import image width (#6528)
-  * Update manual instructions with discrete ROCm bundle (#6445)
-  * llm: fix typo in comment (#6530)
-  * adjust image sizes
-  * clean up convert tokenizer
-  * detect chat template from configs that contain lists
-  * update the import docs (#6104)
-  * server: clean up route names for consistency (#6524)
-  * Only enable numa on CPUs (#6484)
-  * gpu: Group GPU Library sets by variant (#6483)
-  * update faq
-  * passthrough OLLAMA_HOST path to client
-  * convert safetensor adapters into GGUF (#6327)
-  * gpu: Ensure driver version set before variant (#6480)
-  * llm: Align cmake define for cuda no peer copy (#6455)
-  * Fix embeddings memory corruption (#6467)
-  * llama3.1
-  * convert gemma2
-  * create bert models from cli
-  * bert
-  * Split rocm back out of bundle (#6432)
-  * CI: remove directories from dist dir before upload step (#6429)
-  * CI: handle directories during checksum (#6427)
-  * Fix overlapping artifact name on CI
-  * Review comments
-  * Adjust layout to bin+lib/ollama
-  * Remove Jetpack
-  * Add windows cuda v12 + v11 support
-  * Enable cuda v12 flags
-  * Add cuda v12 variant and selection logic
-  * Report GPU variant in log
-  * Add Jetson cuda variants for arm
-  * Wire up ccache and pigz in the docker based build
-  * Refactor linux packaging
-  * server: limit upload parts to 16 (#6411)
-  * Fix white space.
-  * Reset NumCtx.
-  * Override numParallel only if unset.
-  * fix: chmod new layer to 0o644 when creating it
-  * fix: Add tooltip to system tray icon
-  * only skip invalid json manifests
-  * skip invalid manifest files
-  * fix noprune
-  * add `CONTRIBUTING.md` (#6349)
-  * Fix typo and improve readability (#5964)
-  * server: reduce max connections used in download (#6347)
-  * update chatml template format to latest in docs (#6344)
-  * lint
-  * Update openai.md to remove extra checkbox (#6345)
-  * llama3.1 memory
-
 -------------------------------------------------------------------
 Thu Aug 15 18:59:48 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 
@@ -455,23 +20,23 @@ Sun Aug 11 02:40:06 UTC 2024 - Alessandro de Oliveira Faria <cabelo@opensuse.org
 
 - Update to version 0.3.4:
  * New embedding models
-  - BGE-M3: a large embedding model from BAAI distinguished for
+  - BGE-M3: a large embedding model from BAAI distinguished for 
-    its versatility in Multi-Functionality, Multi-Linguality, and
+    its versatility in Multi-Functionality, Multi-Linguality, and 
     Multi-Granularity.
   - BGE-Large: a large embedding model trained in english.
-  - Paraphrase-Multilingual: A multilingual embedding model
+  - Paraphrase-Multilingual: A multilingual embedding model 
     trained on parallel data for 50+ languages.
  * New embedding API with batch support
-   - Ollama now supports a new API endpoint /api/embed for
+   - Ollama now supports a new API endpoint /api/embed for 
      embedding generation:
  * This API endpoint supports new features:
-   - Batches: generate embeddings for several documents in
+   - Batches: generate embeddings for several documents in 
      one request
-   - Normalized embeddings: embeddings are now normalized,
+   - Normalized embeddings: embeddings are now normalized, 
      improving similarity results
-   - Truncation: a new truncate parameter that will error if
+   - Truncation: a new truncate parameter that will error if 
      set to false
-   - Metrics: responses include load_duration, total_duration and
+   - Metrics: responses include load_duration, total_duration and 
      prompt_eval_count metrics
 
 -------------------------------------------------------------------
@@ -482,17 +47,17 @@ Sat Aug 03 09:41:56 UTC 2024 - eyadlorenzo@gmail.com
     load_duration, and prompt_eval_count
   * Added usage metrics to the /v1/embeddings OpenAI compatibility
     API
-  * Fixed issue where /api/generate would respond with an empty
+  * Fixed issue where /api/generate would respond with an empty 
     string if provided a context
-  * Fixed issue where /api/generate would return an incorrect
+  * Fixed issue where /api/generate would return an incorrect 
     value for context
   * /show modefile will now render MESSAGE commands correctly
 
 - Update to version 0.3.2:
-  * Fixed issue where ollama pull would not resume download
+  * Fixed issue where ollama pull would not resume download 
     progress
   * Fixed issue where phi3 would report an error on older versions
-
+  
 -------------------------------------------------------------------
 Tue Jul 30 07:08:37 UTC 2024 - Adrian Schröter <adrian@suse.de>
 
@@ -557,16 +122,16 @@ Wed Jul 24 14:28:08 UTC 2024 - adrian@suse.de
 -------------------------------------------------------------------
 Thu Jul 18 13:09:10 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 
-- Fixed issue with shared libraries
+- Fixed issue with shared libraries 
 
 -------------------------------------------------------------------
 Thu Jul 18 12:27:54 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 
 - Added %check section
-- Use -v when building
+- Use -v when building 
 
 - Update to version 0.2.6:
-  * New models: MathΣtral is a 7B model designed for math
+  * New models: MathΣtral is a 7B model designed for math 
     reasoning and scientific discovery by Mistral AI.
   * Fixed issue where uppercase roles such as USER would no longer
     work in the chat endpoints
@@ -580,62 +145,62 @@ Sun Jul 14 17:48:36 UTC 2024 - eyadlorenzo@gmail.com
   * Fixed issue where a model's SYSTEM message not be applied
 
 - Update to version 0.2.4:
-  * Fixed issue where context, load_duration and total_duration
+  * Fixed issue where context, load_duration and total_duration 
     fields would not be set in the /api/generate endpoint.
-  * Ollama will no longer error if loading models larger than
+  * Ollama will no longer error if loading models larger than 
     system memory if disk space is available
 
 - Update to version 0.2.3:
   * Fix issue where system prompt would not be applied
 
 - Update to version 0.2.2:
-  * Fixed errors that occurred when using Ollama with Nvidia V100
+  * Fixed errors that occurred when using Ollama with Nvidia V100 
     GPUs
   * glm4 models will no longer fail to load from out of memory
     errors
-  * Fixed error that would occur when running deepseek-v2 and
+  * Fixed error that would occur when running deepseek-v2 and 
     deepseek-coder-v2 models
   * Fixed a series of out of memory issues when using Nvidia
     GPUs
-  * Fixed a series of errors that would occur when using multiple
+  * Fixed a series of errors that would occur when using multiple 
     Radeon GPUs
 
 - Update to version 0.2.1:
-  * Fixed issue where setting OLLAMA_NUM_PARALLEL would cause
+  * Fixed issue where setting OLLAMA_NUM_PARALLEL would cause 
     models to be reloaded after each request
 
 - Update to version 0.2.0:
-  * Ollama 0.2.0 is now available with concurrency support.
+  * Ollama 0.2.0 is now available with concurrency support. 
     This unlocks 2 specific features:
     ~ Ollama can now serve multiple requests at the same time
     ~ Ollama now supports loading different models at the same time
-  * New models: GLM-4: A strong multi-lingual general language
+  * New models: GLM-4: A strong multi-lingual general language 
     model with competitive performance to Llama 3.
-  * New models: CodeGeeX4: A versatile model for AI software
+  * New models: CodeGeeX4: A versatile model for AI software 
     development scenarios, including code completion.
-  * New models: Gemma 2: Improved output quality and base text
+  * New models: Gemma 2: Improved output quality and base text 
     generation models now available
-  * Ollama will now show a better error if a model architecture
+  * Ollama will now show a better error if a model architecture 
     isn't supported
   * Improved handling of quotes and spaces in Modelfile FROM lines
-  * Ollama will now return an error if the system does not have
+  * Ollama will now return an error if the system does not have 
     enough memory to run a model on Linux
 -------------------------------------------------------------------
 Sun Jul 07 19:18:11 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 
 - Update to version 0.1.48:
-  * Fixed issue where Gemma 2 would continuously output when
+  * Fixed issue where Gemma 2 would continuously output when 
     reaching context limits
   * Fixed out of memory and core dump errors when running Gemma 2
   * /show info will now show additional model information in
     ollama run
-  * Fixed issue where ollama show would result in an error on
+  * Fixed issue where ollama show would result in an error on 
     certain vision models
 
 - Update to version 0.1.48:
   * Added support for Google Gemma 2 models (9B and 27B)
   * Fixed issues with ollama create when importing from Safetensors
-
+  
 -------------------------------------------------------------------
 Mon Jun 24 10:11:17 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 
@@ -670,44 +235,44 @@ Sat Jun 22 10:08:00 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 -------------------------------------------------------------------
 Tue Jun 18 12:12:41 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 
-- Added documentation files to .spec
+- Added documentation files to .spec 
 
 - Update to version 0.1.44:
-  * Fixed issue where unicode characters such as emojis would not
+  * Fixed issue where unicode characters such as emojis would not 
     be loaded correctly when running ollama create
   * Fixed certain cases where Nvidia GPUs would not be detected and
     reported as compute capability 1.0 devices
 
 - Update to version 0.1.43:
-  * New import.md guide for converting and importing models to
+  * New import.md guide for converting and importing models to 
     Ollama
-  * Fixed issue where embedding vectors resulting from
+  * Fixed issue where embedding vectors resulting from 
     /api/embeddings would not be accurate
-  * JSON mode responses will no longer include invalid escape
+  * JSON mode responses will no longer include invalid escape 
     characters
-  * Removing a model will no longer show incorrect File not found
+  * Removing a model will no longer show incorrect File not found 
     errors
-  * Fixed issue where running ollama create would result in an
+  * Fixed issue where running ollama create would result in an 
     error on Windows with certain file formatting
 
 - Update to version 0.1.42:
-  * New models: Qwen 2: a new series of large language models
+  * New models: Qwen 2: a new series of large language models 
     from Alibaba group
-  * Qwen 2: a new series of large language models from Alibaba
+  * Qwen 2: a new series of large language models from Alibaba 
     group
-  * ollama pull is now faster if it detects a model is already
+  * ollama pull is now faster if it detects a model is already 
     downloaded
   * ollama create will now automatically detect prompt templates
-    for popular model architectures such as Llama, Gemma, Phi and
+    for popular model architectures such as Llama, Gemma, Phi and 
     more.
-  * Ollama can now be accessed from local apps built with Electron
+  * Ollama can now be accessed from local apps built with Electron 
     and Tauri, as well as in developing apps in local html files
   * Update welcome prompt in Windows to llama3
-  * Fixed issues where /api/ps and /api/tags would show invalid
+  * Fixed issues where /api/ps and /api/tags would show invalid 
     timestamps in responses
 
 - Update to version 0.1.41:
-  * Fixed issue on Windows 10 and 11 with Intel CPUs with
+  * Fixed issue on Windows 10 and 11 with Intel CPUs with 
     integrated GPUs where Ollama would encounter an error
 
 -------------------------------------------------------------------
@@ -717,12 +282,12 @@ Sat Jun 01 21:12:20 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
   * New model: Codestral: Codestral is Mistral AI’s first-ever code
   	model designed for code generation tasks.
   * New model: IBM Granite Code: now in 3B and 8B parameter sizes.
-  * New model: Deepseek V2: A Strong, Economical, and Efficient
+  * New model: Deepseek V2: A Strong, Economical, and Efficient 
   	Mixture-of-Experts Language Model
-  * Fixed out of memory and incorrect token issues when running
+  * Fixed out of memory and incorrect token issues when running 
   	Codestral on 16GB Macs
-  * Fixed issue where full-width characters (e.g. Japanese,
+  * Fixed issue where full-width characters (e.g. Japanese, 
-  	Chinese, Russian) were deleted at end of the line when using
+  	Chinese, Russian) were deleted at end of the line when using 
   	ollama run
 
 -------------------------------------------------------------------
@@ -731,9 +296,9 @@ Wed May 29 11:38:26 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 - Update to version 0.1.39:
   * New model: Cohere Aya 23: A new state-of-the-art, multilingual
   	LLM covering 23 different languages.
-  * New model: Mistral 7B 0.3: A new version of Mistral 7B with
+  * New model: Mistral 7B 0.3: A new version of Mistral 7B with 
   	initial support for function calling.
-  * New model: Phi-3 Medium: a 14B parameters, lightweight,
+  * New model: Phi-3 Medium: a 14B parameters, lightweight, 
   	state-of-the-art open model by Microsoft.
   * New model: Phi-3 Mini 128K and Phi-3 Medium 128K: versions of
   	the Phi-3 models that support a context window size of 128K
@@ -741,7 +306,7 @@ Wed May 29 11:38:26 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
   	IBM for Code Intelligence
   * It is now possible to import and quantize Llama 3 and its
   	finetunes from Safetensors format to Ollama.
-  * Full changelog at
+  * Full changelog at 
   	https://github.com/ollama/ollama/releases/tag/v0.1.39
 
 -------------------------------------------------------------------
@@ -755,7 +320,7 @@ Thu May 16 19:55:51 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 - Update to version 0.1.38:
   * New model: Falcon 2: A new 11B parameters causal decoder-only
     model built by TII and trained over 5T tokens.
-  * New model: Yi 1.5: A new high-performing version of Yi, now
+  * New model: Yi 1.5: A new high-performing version of Yi, now 
     licensed as Apache 2.0. Available in 6B, 9B and 34B sizes.
   * Added ollama ps command
   * Added /clear command
@@ -780,7 +345,7 @@ Sun May 12 19:05:53 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 Sun May 12 15:20:28 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
 
 - Use obs_scm service instead of the deprecated tar_scm
-- Use zstd for vendor tarball compression
+- Use zstd for vendor tarball compression 
 
 -------------------------------------------------------------------
 Sun May 12 01:39:26 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
@@ -818,11 +383,11 @@ Sun May 12 01:39:26 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
   * New model: CodeGemma 1.1
   * New model: StableLM2 12B
   * New model: Moondream 2
-  * Fixed issues with LLaVa models where they would respond
+  * Fixed issues with LLaVa models where they would respond 
     incorrectly after the first request
-  * Fixed out of memory errors when running large models such as
+  * Fixed out of memory errors when running large models such as 
     Llama 3 70B
-  * Fixed various issues with Nvidia GPU discovery on Linux and
+  * Fixed various issues with Nvidia GPU discovery on Linux and 
     Windows
   * Fixed a series of Modelfile errors when running ollama create
   * Fixed no slots available error that occurred when cancelling a
@@ -840,13 +405,13 @@ Sun May 12 01:39:26 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
   * New model: Llama 3 Gradient 1048K
   * New model: Dolphin Llama 3
   * New model: Qwen 110B
-  * Fixed issues where the model would not terminate, causing the
+  * Fixed issues where the model would not terminate, causing the 
     API to hang.
   * Fixed a series of out of memory errors on Apple Silicon Macs
-  * Fixed out of memory errors when running Mixtral architecture
+  * Fixed out of memory errors when running Mixtral architecture 
     models
   * Aded experimental concurrency features:
-    ~ OLLAMA_NUM_PARALLEL: Handle multiple requests simultaneously
+    ~ OLLAMA_NUM_PARALLEL: Handle multiple requests simultaneously 
       for a single model
     ~ OLLAMA_MAX_LOADED_MODELS: Load multiple models simultaneously
 

ollama.obsinfo

@@ -1,4 +1,4 @@
 name: ollama
-version: 0.5.7
+version: 0.3.6
-mtime: 1737018844
+mtime: 1723575229
-commit: a420a453b4783841e3e79c248ef0fe9548df6914
+commit: 4c4fe3f87fe1858b35bd0d41e093a0039ec4cee4

ollama.service

@@ -8,7 +8,6 @@ User=ollama
 Group=ollama
 Restart=always
 RestartSec=3
-EnvironmentFile=-/etc/sysconfig/ollama
 
 [Install]
 WantedBy=default.target

ollama.spec

@@ -1,7 +1,7 @@
 #
 # spec file for package ollama
 #
-# Copyright (c) 2025 SUSE LLC
+# Copyright (c) 2024 SUSE LLC
 #
 # All modifications and additions to the file contributed by third parties
 # remain the property of their copyright owners, unless otherwise agreed
@@ -17,7 +17,7 @@
 
 
 Name:           ollama
-Version:        0.5.7
+Version:        0.3.6
 Release:        0
 Summary:        Tool for running AI models on-premise
 License:        MIT
@@ -26,14 +26,12 @@ Source:         %{name}-%{version}.tar
 Source1:        vendor.tar.zstd
 Source2:        ollama.service
 Source3:        %{name}-user.conf
-Source4:        sysconfig.ollama
+Patch0:         enable-lto.patch
 BuildRequires:  cmake >= 3.24
 BuildRequires:  git
 BuildRequires:  sysuser-tools
 BuildRequires:  zstd
 BuildRequires:  golang(API) >= 1.22
-# 32bit seems not to be supported anymore
-ExcludeArch:    %{ix86} %{arm}
 %sysusers_requires
 %if 0%{?sle_version} == 150600
 BuildRequires:  gcc12-c++
@@ -41,7 +39,8 @@ BuildRequires:  libstdc++6-gcc12
 %else
 BuildRequires:  gcc-c++ >= 11.4.0
 %endif
-Requires(pre):  %{fillup_prereq}
+# 32bit seems not to be supported anymore
+ExcludeArch:    %ix86 %arm
 
 %description
 Ollama is a tool for running AI models on one's own hardware.
@@ -67,16 +66,15 @@ export CC=gcc-12
 export GOFLAGS="-mod=vendor"
 %endif
 
-export GOFLAGS="${GOFLAGS} -v"
+export OLLAMA_SKIP_PATCHING=1
 
-%make_build
+go generate ./...
+go build -v .
 
 %install
 install -D -m 0755 %{name} %{buildroot}/%{_bindir}/%{name}
-
 install -D -m 0644 %{SOURCE2} %{buildroot}%{_unitdir}/%{name}.service
 install -D -m 0644 %{SOURCE3} %{buildroot}%{_sysusersdir}/%{name}-user.conf
-install -D -m 0644 %{SOURCE4} %{buildroot}%{_fillupdir}/sysconfig.%name
 install -d %{buildroot}%{_localstatedir}/lib/%{name}
 
 mkdir -p "%{buildroot}/%{_docdir}/%{name}"
@@ -89,14 +87,13 @@ export CC=gcc-12
 # pie doesn't work with gcc12 on leap
 export GOFLAGS="-mod=vendor"
 %endif
-go test -v ./...
+go test ./...
 
 %pre -f %{name}.pre
 %service_add_pre %{name}.service
 
 %post
 %service_add_post %{name}.service
-%fillup_only
 
 %preun
 %service_del_preun %{name}.service
@@ -111,7 +108,6 @@ go test -v ./...
 %{_bindir}/%{name}
 %{_unitdir}/%{name}.service
 %{_sysusersdir}/%{name}-user.conf
-%{_fillupdir}/sysconfig.%name
 %attr(-, ollama, ollama) %{_localstatedir}/lib/%{name}
 
 %changelog

sysconfig.ollama

@@ -1,58 +0,0 @@
-## Path:           Network/Ollama
-## Description:    Ollama server access
-## Type:           string
-## Default:        "http://127.0.0.1:11434"
-## ServiceRestart: ollama
-#
-# set it to 0.0.0.0 for global network access
-#
-OLLAMA_HOST="http://127.0.0.1:11434"
-
-## Type:           string
-## Description:    Ollama default quantization type for the K/V cache
-## Default:        "f16"
-## ServiceRestart: ollama
-OLLAMA_KV_CACHE_TYPE=f16
-
-## Type:           string
-## Description:    Ollama default quantization type for the K/V cache
-## Default:        "f16"
-## ServiceRestart: ollama
-OLLAMA_KEEP_ALIVE=
-
-## Type:           string
-## Description:    Parallel processes
-## Default:        ""
-## ServiceRestart: ollama
-OLLAMA_NUM_PARALLEL=
-
-## Type:           string
-## Description:    Maxmimal memory to be used
-## Default:        ""
-## ServiceRestart: ollama
-OLLAMA_MAX_VRAM=
-
-## Type:           string
-## Description:    Ollama runner directory
-## Default:        ""
-## ServiceRestart: ollama
-OLLAMA_RUNNERS_DIR=
-
-## Type:           string
-## Description:    Ollama temporary directory
-## Default:        ""
-## ServiceRestart: ollama
-OLLAMA_TMPDIR=
-
-## Type:           string
-## Description:    Models to be loaded by default
-## Default:        ""
-## ServiceRestart: ollama
-OLLAMA_MODELS=
-
-## Type:           string
-## Description:    List of allowed remote hosts
-## Default:        ""
-## ServiceRestart: ollama
-OLLAMA_ORIGINS=
-