mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-24 13:37:01 +02:00
Compare commits
8
Commits
b4774
...
gguf-v0.16.0
| Author | SHA1 | Date | |
|---|---|---|---|
 Sigbjørn Skjæret
|
69050a11be | ||
 Aleksei Nikiforov
|
3567ee3a94 | ||
 Kante Yin
|
53e4db1012 | ||
 Olivier Chafik
|
d7cfe1ffe0 | ||
 Jeff Bolz
|
a82c9e7c23 | ||
 rhjdvsgsgks
|
401af80b54 | ||
  JuddandJudd
|
c132239bfb | ||
 Molly Sophia
|
393fca629e |
@@ -219,7 +219,7 @@ Instructions for adding support for new models: [HOWTO-add-model.md](docs/develo
|
||||
- [llama_cpp_canister](https://github.com/onicai/llama_cpp_canister) - llama.cpp as a smart contract on the Internet Computer, using WebAssembly
|
||||
- [llama-swap](https://github.com/mostlygeek/llama-swap) - transparent proxy that adds automatic model switching with llama-server
|
||||
- [Kalavai](https://github.com/kalavai-net/kalavai-client) - Crowdsource end to end LLM deployment at any scale
|
||||
|
||||
- [llmaz](https://github.com/InftyAI/llmaz) - ☸️ Easy, advanced inference platform for large language models on Kubernetes.
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
@@ -0,0 +1,390 @@
|
||||
# Function Calling
|
||||
|
||||
[chat.h](../common/chat.h) (https://github.com/ggml-org/llama.cpp/pull/9639) adds support for [OpenAI-style function calling](https://platform.openai.com/docs/guides/function-calling) and is used in:
|
||||
- `llama-server` when started w/ `--jinja` flag
|
||||
- `llama-cli` (WIP: https://github.com/ggml-org/llama.cpp/pull/11556)
|
||||
|
||||
## Universal support w/ Native & Generic handlers
|
||||
|
||||
Function calling is supported for all models (see https://github.com/ggml-org/llama.cpp/pull/9639):
|
||||
|
||||
- Native tool call formats supported:
|
||||
- Llama 3.1 / 3.3 (including builtin tools support - tool names for `wolfram_alpha`, `web_search` / `brave_search`, `code_interpreter`), Llama 3.2
|
||||
- Functionary v3.1 / v3.2
|
||||
- Hermes 2/3, Qwen 2.5
|
||||
- Qwen 2.5 Coder (WIP: https://github.com/ggml-org/llama.cpp/pull/12034)
|
||||
- Mistral Nemo
|
||||
- Firefunction v2
|
||||
- Command R7B
|
||||
- DeepSeek R1 (WIP / seems reluctant to call any tools?)
|
||||
|
||||
- Generic tool call is supported when the template isn't recognized by native format handlers (you'll see `Chat format: Generic` in the logs).
|
||||
- Use `--chat-template-file` to override the template when appropriate (see examples below)
|
||||
- Generic support may consume more tokens and be less efficient than a model's native format.
|
||||
|
||||
<details>
|
||||
<summary>Show some common templates and which format handler they use</summary>
|
||||
|
||||
| Template | Format |
|
||||
|----------|--------|
|
||||
| Almawave-Velvet-14B.jinja | Hermes 2 Pro |
|
||||
| AtlaAI-Selene-1-Mini-Llama-3.1-8B.jinja | Llama 3.x |
|
||||
| CohereForAI-aya-expanse-8b.jinja | Generic |
|
||||
| CohereForAI-c4ai-command-r-plus-default.jinja | Generic |
|
||||
| CohereForAI-c4ai-command-r-plus-rag.jinja | Generic |
|
||||
| CohereForAI-c4ai-command-r-plus-tool_use.jinja | Generic |
|
||||
| CohereForAI-c4ai-command-r7b-12-2024-default.jinja | Command R7B (extract reasoning) |
|
||||
| CohereForAI-c4ai-command-r7b-12-2024-rag.jinja | Command R7B (extract reasoning) |
|
||||
| CohereForAI-c4ai-command-r7b-12-2024-tool_use.jinja | Command R7B (extract reasoning) |
|
||||
| CohereForAI-c4ai-command-r7b-12-2024.jinja | Generic |
|
||||
| DavieLion-Llama-3.2-1B-SPIN-iter3.jinja | Generic |
|
||||
| Delta-Vector-Rei-12B.jinja | Mistral Nemo |
|
||||
| EpistemeAI-Mistral-Nemo-Instruct-12B-Philosophy-Math.jinja | Mistral Nemo |
|
||||
| FlofloB-83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit.jinja | Hermes 2 Pro |
|
||||
| FlofloB-test_continued_pretraining_Phi-3-mini-4k-instruct_Unsloth_merged_16bit.jinja | Generic |
|
||||
| HelpingAI-HAI-SER.jinja | Generic |
|
||||
| HuggingFaceTB-SmolLM2-1.7B-Instruct.jinja | Generic |
|
||||
| HuggingFaceTB-SmolLM2-135M-Instruct.jinja | Generic |
|
||||
| HuggingFaceTB-SmolLM2-360M-Instruct.jinja | Generic |
|
||||
| INSAIT-Institute-BgGPT-Gemma-2-27B-IT-v1.0.jinja | Generic |
|
||||
| Ihor-Text2Graph-R1-Qwen2.5-0.5b.jinja | Hermes 2 Pro |
|
||||
| Infinigence-Megrez-3B-Instruct.jinja | Generic |
|
||||
| Josephgflowers-TinyLlama_v1.1_math_code-world-test-1.jinja | Generic |
|
||||
| LGAI-EXAONE-EXAONE-3.5-2.4B-Instruct.jinja | Generic |
|
||||
| LGAI-EXAONE-EXAONE-3.5-7.8B-Instruct.jinja | Generic |
|
||||
| LatitudeGames-Wayfarer-12B.jinja | Generic |
|
||||
| Magpie-Align-Llama-3-8B-Magpie-Align-v0.1.jinja | Generic |
|
||||
| Magpie-Align-Llama-3.1-8B-Magpie-Align-v0.1.jinja | Generic |
|
||||
| MaziyarPanahi-calme-3.2-instruct-78b.jinja | Generic |
|
||||
| MiniMaxAI-MiniMax-Text-01.jinja | Generic |
|
||||
| MiniMaxAI-MiniMax-VL-01.jinja | Generic |
|
||||
| NaniDAO-deepseek-r1-qwen-2.5-32B-ablated.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| NexaAIDev-Octopus-v2.jinja | Generic |
|
||||
| NousResearch-Hermes-2-Pro-Llama-3-8B-default.jinja | Generic |
|
||||
| NousResearch-Hermes-2-Pro-Llama-3-8B-tool_use.jinja | Hermes 2 Pro |
|
||||
| NousResearch-Hermes-2-Pro-Mistral-7B-default.jinja | Generic |
|
||||
| NousResearch-Hermes-2-Pro-Mistral-7B-tool_use.jinja | Hermes 2 Pro |
|
||||
| NousResearch-Hermes-3-Llama-3.1-70B-default.jinja | Generic |
|
||||
| NousResearch-Hermes-3-Llama-3.1-70B-tool_use.jinja | Hermes 2 Pro |
|
||||
| NovaSky-AI-Sky-T1-32B-Flash.jinja | Hermes 2 Pro |
|
||||
| NovaSky-AI-Sky-T1-32B-Preview.jinja | Hermes 2 Pro |
|
||||
| OnlyCheeini-greesychat-turbo.jinja | Generic |
|
||||
| Orenguteng-Llama-3.1-8B-Lexi-Uncensored-V2.jinja | Llama 3.x |
|
||||
| OrionStarAI-Orion-14B-Chat.jinja | Generic |
|
||||
| PowerInfer-SmallThinker-3B-Preview.jinja | Generic |
|
||||
| PrimeIntellect-INTELLECT-1-Instruct.jinja | Generic |
|
||||
| Qwen-QVQ-72B-Preview.jinja | Generic |
|
||||
| Qwen-QwQ-32B-Preview.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen1.5-7B-Chat.jinja | Generic |
|
||||
| Qwen-Qwen2-7B-Instruct.jinja | Generic |
|
||||
| Qwen-Qwen2-VL-72B-Instruct.jinja | Generic |
|
||||
| Qwen-Qwen2-VL-7B-Instruct.jinja | Generic |
|
||||
| Qwen-Qwen2.5-0.5B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-1.5B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-14B-Instruct-1M.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-14B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-32B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-32B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-3B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-72B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-7B-Instruct-1M.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-7B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-7B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-Coder-32B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-Coder-7B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-Math-1.5B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-Math-7B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-VL-3B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-VL-72B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-VL-7B-Instruct.jinja | Hermes 2 Pro |
|
||||
| RWKV-Red-Team-ARWKV-7B-Preview-0.1.jinja | Hermes 2 Pro |
|
||||
| SakanaAI-TinySwallow-1.5B-Instruct.jinja | Hermes 2 Pro |
|
||||
| SakanaAI-TinySwallow-1.5B.jinja | Hermes 2 Pro |
|
||||
| Sao10K-70B-L3.3-Cirrus-x1.jinja | Llama 3.x |
|
||||
| SentientAGI-Dobby-Mini-Leashed-Llama-3.1-8B.jinja | Llama 3.x |
|
||||
| SentientAGI-Dobby-Mini-Unhinged-Llama-3.1-8B.jinja | Llama 3.x |
|
||||
| Steelskull-L3.3-Damascus-R1.jinja | Llama 3.x |
|
||||
| Steelskull-L3.3-MS-Nevoria-70b.jinja | Llama 3.x |
|
||||
| Steelskull-L3.3-Nevoria-R1-70b.jinja | Llama 3.x |
|
||||
| THUDM-glm-4-9b-chat.jinja | Generic |
|
||||
| THUDM-glm-edge-1.5b-chat.jinja | Generic |
|
||||
| Tarek07-Progenitor-V1.1-LLaMa-70B.jinja | Llama 3.x |
|
||||
| TheBloke-FusionNet_34Bx2_MoE-AWQ.jinja | Generic |
|
||||
| TinyLlama-TinyLlama-1.1B-Chat-v1.0.jinja | Generic |
|
||||
| UCLA-AGI-Mistral7B-PairRM-SPPO-Iter3.jinja | Generic |
|
||||
| ValiantLabs-Llama3.1-8B-Enigma.jinja | Llama 3.x |
|
||||
| abacusai-Fewshot-Metamath-OrcaVicuna-Mistral.jinja | Generic |
|
||||
| ai21labs-AI21-Jamba-1.5-Large.jinja | Generic |
|
||||
| allenai-Llama-3.1-Tulu-3-405B-SFT.jinja | Generic |
|
||||
| allenai-Llama-3.1-Tulu-3-405B.jinja | Generic |
|
||||
| allenai-Llama-3.1-Tulu-3-8B.jinja | Generic |
|
||||
| arcee-ai-Virtuoso-Lite.jinja | Hermes 2 Pro |
|
||||
| arcee-ai-Virtuoso-Medium-v2.jinja | Hermes 2 Pro |
|
||||
| arcee-ai-Virtuoso-Small-v2.jinja | Hermes 2 Pro |
|
||||
| avemio-GRAG-NEMO-12B-ORPO-HESSIAN-AI.jinja | Generic |
|
||||
| bespokelabs-Bespoke-Stratos-7B.jinja | Hermes 2 Pro |
|
||||
| bfuzzy1-acheron-m1a-llama.jinja | Generic |
|
||||
| bofenghuang-vigogne-2-70b-chat.jinja | Generic |
|
||||
| bytedance-research-UI-TARS-72B-DPO.jinja | Generic |
|
||||
| bytedance-research-UI-TARS-7B-DPO.jinja | Generic |
|
||||
| bytedance-research-UI-TARS-7B-SFT.jinja | Generic |
|
||||
| carsenk-phi3.5_mini_exp_825_uncensored.jinja | Generic |
|
||||
| cyberagent-DeepSeek-R1-Distill-Qwen-14B-Japanese.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| cyberagent-DeepSeek-R1-Distill-Qwen-32B-Japanese.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| databricks-dbrx-instruct.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-Coder-V2-Instruct.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-Coder-V2-Lite-Base.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-Coder-V2-Lite-Instruct.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Llama-70B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Llama-8B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Qwen-14B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Qwen-7B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Zero.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-V2-Lite.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-V2.5.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-V3.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-deepseek-coder-33b-instruct.jinja | Generic |
|
||||
| deepseek-ai-deepseek-coder-6.7b-instruct.jinja | Generic |
|
||||
| deepseek-ai-deepseek-coder-7b-instruct-v1.5.jinja | Generic |
|
||||
| deepseek-ai-deepseek-llm-67b-chat.jinja | Generic |
|
||||
| deepseek-ai-deepseek-llm-7b-chat.jinja | Generic |
|
||||
| dicta-il-dictalm2.0-instruct.jinja | Generic |
|
||||
| ehristoforu-Falcon3-8B-Franken-Basestruct.jinja | Hermes 2 Pro |
|
||||
| fireworks-ai-llama-3-firefunction-v2.jinja | FireFunction v2 |
|
||||
| godlikehhd-alpaca_data_sampled_ifd_new_5200.jinja | Hermes 2 Pro |
|
||||
| godlikehhd-alpaca_data_score_max_0.7_2600.jinja | Hermes 2 Pro |
|
||||
| google-gemma-2-27b-it.jinja | Generic |
|
||||
| google-gemma-2-2b-it.jinja | Generic |
|
||||
| google-gemma-2-2b-jpn-it.jinja | Generic |
|
||||
| google-gemma-7b-it.jinja | Generic |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Llama-70B-abliterated.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Llama-8B-abliterated.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Qwen-14B-abliterated-v2.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Qwen-32B-abliterated.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Qwen-7B-abliterated-v2.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-Qwen2.5-14B-Instruct-1M-abliterated.jinja | Hermes 2 Pro |
|
||||
| ibm-granite-granite-3.1-8b-instruct.jinja | Generic |
|
||||
| indischepartij-MiniCPM-3B-OpenHermes-2.5-v2.jinja | Generic |
|
||||
| inflatebot-MN-12B-Mag-Mell-R1.jinja | Generic |
|
||||
| jinaai-ReaderLM-v2.jinja | Generic |
|
||||
| kms7530-chemeng_qwen-math-7b_24_1_100_1_nonmath.jinja | Hermes 2 Pro |
|
||||
| knifeayumu-Cydonia-v1.3-Magnum-v4-22B.jinja | Mistral Nemo |
|
||||
| langgptai-qwen1.5-7b-chat-sa-v0.1.jinja | Generic |
|
||||
| lightblue-DeepSeek-R1-Distill-Qwen-7B-Japanese.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| mattshumer-Reflection-Llama-3.1-70B.jinja | Generic |
|
||||
| meetkai-functionary-medium-v3.1.jinja | Functionary v3.1 Llama 3.1 |
|
||||
| meetkai-functionary-medium-v3.2.jinja | Functionary v3.2 |
|
||||
| meta-llama-Llama-2-7b-chat-hf.jinja | Generic |
|
||||
| meta-llama-Llama-3.1-8B-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Llama-3.2-11B-Vision-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Llama-3.2-1B-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Llama-3.2-3B-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Llama-3.3-70B-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Meta-Llama-3-8B-Instruct.jinja | Generic |
|
||||
| meta-llama-Meta-Llama-3.1-8B-Instruct.jinja | Llama 3.x |
|
||||
| microsoft-Phi-3-medium-4k-instruct.jinja | Generic |
|
||||
| microsoft-Phi-3-mini-4k-instruct.jinja | Generic |
|
||||
| microsoft-Phi-3-small-8k-instruct.jinja | Generic |
|
||||
| microsoft-Phi-3.5-mini-instruct.jinja | Generic |
|
||||
| microsoft-Phi-3.5-vision-instruct.jinja | Generic |
|
||||
| microsoft-phi-4.jinja | Generic |
|
||||
| migtissera-Tess-3-Mistral-Nemo-12B.jinja | Generic |
|
||||
| ministral-Ministral-3b-instruct.jinja | Generic |
|
||||
| mistralai-Codestral-22B-v0.1.jinja | Generic |
|
||||
| mistralai-Mistral-7B-Instruct-v0.1.jinja | Generic |
|
||||
| mistralai-Mistral-7B-Instruct-v0.2.jinja | Generic |
|
||||
| mistralai-Mistral-7B-Instruct-v0.3.jinja | Mistral Nemo |
|
||||
| mistralai-Mistral-Large-Instruct-2407.jinja | Mistral Nemo |
|
||||
| mistralai-Mistral-Large-Instruct-2411.jinja | Generic |
|
||||
| mistralai-Mistral-Nemo-Instruct-2407.jinja | Mistral Nemo |
|
||||
| mistralai-Mistral-Small-24B-Instruct-2501.jinja | Generic |
|
||||
| mistralai-Mixtral-8x7B-Instruct-v0.1.jinja | Generic |
|
||||
| mkurman-Qwen2.5-14B-DeepSeek-R1-1M.jinja | Hermes 2 Pro |
|
||||
| mlabonne-AlphaMonarch-7B.jinja | Generic |
|
||||
| mlx-community-Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32.jinja | Hermes 2 Pro |
|
||||
| mlx-community-Qwen2.5-VL-7B-Instruct-8bit.jinja | Hermes 2 Pro |
|
||||
| mobiuslabsgmbh-DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| netcat420-MFANNv0.20.jinja | Generic |
|
||||
| netcat420-MFANNv0.24.jinja | Generic |
|
||||
| netease-youdao-Confucius-o1-14B.jinja | Hermes 2 Pro |
|
||||
| nvidia-AceMath-7B-RM.jinja | Hermes 2 Pro |
|
||||
| nvidia-Eagle2-1B.jinja | Hermes 2 Pro |
|
||||
| nvidia-Eagle2-9B.jinja | Hermes 2 Pro |
|
||||
| nvidia-Llama-3.1-Nemotron-70B-Instruct-HF.jinja | Llama 3.x |
|
||||
| onnx-community-DeepSeek-R1-Distill-Qwen-1.5B-ONNX.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| open-thoughts-OpenThinker-7B.jinja | Hermes 2 Pro |
|
||||
| openchat-openchat-3.5-0106.jinja | Generic |
|
||||
| pankajmathur-orca_mini_v6_8b.jinja | Generic |
|
||||
| princeton-nlp-Mistral-7B-Base-SFT-RDPO.jinja | Generic |
|
||||
| princeton-nlp-Mistral-7B-Instruct-DPO.jinja | Generic |
|
||||
| princeton-nlp-Mistral-7B-Instruct-RDPO.jinja | Generic |
|
||||
| prithivMLmods-Bellatrix-Tiny-1.5B-R1.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Bellatrix-Tiny-1B-R1.jinja | Llama 3.x |
|
||||
| prithivMLmods-Bellatrix-Tiny-1B-v3.jinja | Generic |
|
||||
| prithivMLmods-Bellatrix-Tiny-3B-R1.jinja | Llama 3.x |
|
||||
| prithivMLmods-Blaze-14B-xElite.jinja | Generic |
|
||||
| prithivMLmods-Calcium-Opus-14B-Elite2-R1.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Calme-Ties-78B.jinja | Generic |
|
||||
| prithivMLmods-Calme-Ties2-78B.jinja | Generic |
|
||||
| prithivMLmods-Calme-Ties3-78B.jinja | Generic |
|
||||
| prithivMLmods-ChemQwen2-vL.jinja | Generic |
|
||||
| prithivMLmods-GWQ2b.jinja | Generic |
|
||||
| prithivMLmods-LatexMind-2B-Codec.jinja | Generic |
|
||||
| prithivMLmods-Llama-3.2-6B-AlgoCode.jinja | Llama 3.x |
|
||||
| prithivMLmods-Megatron-Opus-14B-Exp.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Megatron-Opus-14B-Stock.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Megatron-Opus-7B-Exp.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Omni-Reasoner-Merged.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Omni-Reasoner4-Merged.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Primal-Opus-14B-Optimus-v1.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-QwQ-Math-IO-500M.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Qwen-7B-Distill-Reasoner.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| prithivMLmods-Qwen2.5-1.5B-DeepSeek-R1-Instruct.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Qwen2.5-14B-DeepSeek-R1-1M.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Qwen2.5-32B-DeepSeek-R1-Instruct.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Qwen2.5-7B-DeepSeek-R1-1M.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Triangulum-v2-10B.jinja | Hermes 2 Pro |
|
||||
| qingy2024-Falcon3-2x10B-MoE-Instruct.jinja | Hermes 2 Pro |
|
||||
| rubenroy-Zurich-14B-GCv2-5m.jinja | Hermes 2 Pro |
|
||||
| rubenroy-Zurich-7B-GCv2-5m.jinja | Hermes 2 Pro |
|
||||
| silma-ai-SILMA-Kashif-2B-Instruct-v1.0.jinja | Generic |
|
||||
| simplescaling-s1-32B.jinja | Hermes 2 Pro |
|
||||
| sometimesanotion-Lamarck-14B-v0.7.jinja | Hermes 2 Pro |
|
||||
| sonthenguyen-zephyr-sft-bnb-4bit-DPO-mtbr-180steps.jinja | Generic |
|
||||
| sthenno-tempesthenno-icy-0130.jinja | Generic |
|
||||
| sumink-qwft.jinja | Hermes 2 Pro |
|
||||
| teknium-OpenHermes-2.5-Mistral-7B.jinja | Generic |
|
||||
| thirdeyeai-elevate360m.jinja | Generic |
|
||||
| tiiuae-Falcon3-10B-Instruct.jinja | Hermes 2 Pro |
|
||||
| unsloth-DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| unsloth-DeepSeek-R1-Distill-Llama-8B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| unsloth-DeepSeek-R1.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| unsloth-Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit.jinja | Generic |
|
||||
| upstage-solar-pro-preview-instruct.jinja | Generic |
|
||||
| whyhow-ai-PatientSeek.jinja | Generic |
|
||||
| xwen-team-Xwen-72B-Chat.jinja | Hermes 2 Pro |
|
||||
| xwen-team-Xwen-7B-Chat.jinja | Hermes 2 Pro |
|
||||
|
||||
This table can be generated with:
|
||||
|
||||
```bash
|
||||
./build/bin/test-chat ../minja/build/tests/*.jinja 2>/dev/null
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
# Usage - need tool-aware Jinja template
|
||||
|
||||
First, start a server with any model, but make sure it has a tools-enabled template: you can verify this by inspecting the `chat_template` or `chat_template_tool_use` properties in `http://localhost:8080/props`).
|
||||
|
||||
Here are some models known to work (w/ chat template override when needed):
|
||||
|
||||
```shell
|
||||
# Native support:
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M
|
||||
llama-server --jinja -fa -hf bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q6_K_L
|
||||
llama-server --jinja -fa -hf bartowski/functionary-small-v3.2-GGUF:Q4_K_M
|
||||
llama-server --jinja -fa -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_M
|
||||
|
||||
# Native support for DeepSeek R1 works best w/ our own template (official template buggy)
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q6_K_L \
|
||||
--chat-template-file models/templates/llama-cpp-deepseek-r1.jinja
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M \
|
||||
--chat-template-file models/templates/llama-cpp-deepseek-r1.jinja
|
||||
|
||||
# Native support requires the right template for these GGUFs:
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M \
|
||||
--chat-template-file <( python scripts/get_chat_template.py NousResearch/Hermes-2-Pro-Llama-3-8B tool_use )
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M \
|
||||
--chat-template-file <( python scripts/get_chat_template.py NousResearch/Hermes-3-Llama-3.1-8B tool_use )
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/firefunction-v2-GGUF -hff firefunction-v2-IQ1_M.gguf \
|
||||
--chat-template-file <( python scripts/get_chat_template.py fireworks-ai/llama-3-firefunction-v2 tool_use )
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/c4ai-command-r7b-12-2024-GGUF:Q6_K_L \
|
||||
--chat-template-file <( python scripts/get_chat_template.py CohereForAI/c4ai-command-r7b-12-2024 tool_use )
|
||||
|
||||
# Generic format support
|
||||
llama-server --jinja -fa -hf bartowski/phi-4-GGUF:Q4_0
|
||||
llama-server --jinja -fa -hf bartowski/gemma-2-2b-it-GGUF:Q8_0
|
||||
llama-server --jinja -fa -hf bartowski/c4ai-command-r-v01-GGUF:Q2_K
|
||||
```
|
||||
|
||||
> [!TIP]
|
||||
> If there is no official `tool_use` Jinja template, you may want to set `--chat-template chatml` to use a default that works with many models (YMMV!), or write your own (e.g. we provide a custom [llama-cpp-deepseek-r1.jinja](../models/templates/llama-cpp-deepseek-r1.jinja) for DeepSeek R1 distills)
|
||||
|
||||
Test in CLI (or with any library / software that can use OpenAI-compatible API backends):
|
||||
|
||||
```bash
|
||||
curl http://localhost:8080/v1/chat/completions -d '{
|
||||
"model": "gpt-3.5-turbo",
|
||||
"tools": [
|
||||
{
|
||||
"type":"function",
|
||||
"function":{
|
||||
"name":"python",
|
||||
"description":"Runs code in an ipython interpreter and returns the result of the execution after 60 seconds.",
|
||||
"parameters":{
|
||||
"type":"object",
|
||||
"properties":{
|
||||
"code":{
|
||||
"type":"string",
|
||||
"description":"The code to run in the ipython interpreter."
|
||||
}
|
||||
},
|
||||
"required":["code"]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Print a hello world message with python."
|
||||
}
|
||||
]
|
||||
}'
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>Show output</summary>
|
||||
|
||||
```json
|
||||
{
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "tool",
|
||||
"index": 0,
|
||||
"message": {
|
||||
"content": null,
|
||||
"tool_calls": [
|
||||
{
|
||||
"name": "python",
|
||||
"arguments": "{\"code\":\" \\nprint(\\\"Hello, World!\\\")\"}"
|
||||
}
|
||||
],
|
||||
"role": "assistant"
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1727287211,
|
||||
"model": "gpt-3.5-turbo",
|
||||
"object": "chat.completion",
|
||||
"usage": {
|
||||
"completion_tokens": 16,
|
||||
"prompt_tokens": 44,
|
||||
"total_tokens": 60
|
||||
},
|
||||
"id": "chatcmpl-Htbgh9feMmGM0LEH2hmQvwsCxq3c6Ni8"
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
+3
-374
@@ -13,6 +13,7 @@ Set of LLM REST APIs and a simple web front end to interact with llama.cpp.
|
||||
* Multimodal (wip)
|
||||
* Monitoring endpoints
|
||||
* Schema-constrained JSON response format
|
||||
* [Function calling](../../docs/function-calling.md) / tool use for ~any model
|
||||
|
||||
The project is under active development, and we are [looking for feedback and contributors](https://github.com/ggml-org/llama.cpp/issues/4216).
|
||||
|
||||
@@ -1120,381 +1121,9 @@ curl http://localhost:8080/v1/chat/completions \
|
||||
|
||||
*Tool call support*
|
||||
|
||||
[Function calling](https://platform.openai.com/docs/guides/function-calling) is supported for all models (see https://github.com/ggml-org/llama.cpp/pull/9639):
|
||||
[OpenAI-style function calling](https://platform.openai.com/docs/guides/function-calling) is supported with the `--jinja` flag (and may require a `--chat-template-file` override to get the right tool-use compatible Jinja template; worst case, `--chat-template chatml` may also work).
|
||||
|
||||
- Requires `--jinja` flag
|
||||
- Native tool call formats supported:
|
||||
- Llama 3.1 / 3.3 (including builtin tools support - tool names for `wolfram_alpha`, `web_search` / `brave_search`, `code_interpreter`), Llama 3.2
|
||||
- Functionary v3.1 / v3.2
|
||||
- Hermes 2/3, Qwen 2.5
|
||||
- Mistral Nemo
|
||||
- Firefunction v2
|
||||
- Command R7B
|
||||
- DeepSeek R1 (WIP / seems reluctant to call any tools?)
|
||||
|
||||
<details>
|
||||
<summary>Show some common templates and which format handler they use</summary>
|
||||
|
||||
| Template | Format |
|
||||
|----------|--------|
|
||||
| Almawave-Velvet-14B.jinja | Hermes 2 Pro |
|
||||
| AtlaAI-Selene-1-Mini-Llama-3.1-8B.jinja | Llama 3.x |
|
||||
| CohereForAI-aya-expanse-8b.jinja | Generic |
|
||||
| CohereForAI-c4ai-command-r-plus-default.jinja | Generic |
|
||||
| CohereForAI-c4ai-command-r-plus-rag.jinja | Generic |
|
||||
| CohereForAI-c4ai-command-r-plus-tool_use.jinja | Generic |
|
||||
| CohereForAI-c4ai-command-r7b-12-2024-default.jinja | Command R7B (extract reasoning) |
|
||||
| CohereForAI-c4ai-command-r7b-12-2024-rag.jinja | Command R7B (extract reasoning) |
|
||||
| CohereForAI-c4ai-command-r7b-12-2024-tool_use.jinja | Command R7B (extract reasoning) |
|
||||
| CohereForAI-c4ai-command-r7b-12-2024.jinja | Generic |
|
||||
| DavieLion-Llama-3.2-1B-SPIN-iter3.jinja | Generic |
|
||||
| Delta-Vector-Rei-12B.jinja | Mistral Nemo |
|
||||
| EpistemeAI-Mistral-Nemo-Instruct-12B-Philosophy-Math.jinja | Mistral Nemo |
|
||||
| FlofloB-83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit.jinja | Hermes 2 Pro |
|
||||
| FlofloB-test_continued_pretraining_Phi-3-mini-4k-instruct_Unsloth_merged_16bit.jinja | Generic |
|
||||
| HelpingAI-HAI-SER.jinja | Generic |
|
||||
| HuggingFaceTB-SmolLM2-1.7B-Instruct.jinja | Generic |
|
||||
| HuggingFaceTB-SmolLM2-135M-Instruct.jinja | Generic |
|
||||
| HuggingFaceTB-SmolLM2-360M-Instruct.jinja | Generic |
|
||||
| INSAIT-Institute-BgGPT-Gemma-2-27B-IT-v1.0.jinja | Generic |
|
||||
| Ihor-Text2Graph-R1-Qwen2.5-0.5b.jinja | Hermes 2 Pro |
|
||||
| Infinigence-Megrez-3B-Instruct.jinja | Generic |
|
||||
| Josephgflowers-TinyLlama_v1.1_math_code-world-test-1.jinja | Generic |
|
||||
| LGAI-EXAONE-EXAONE-3.5-2.4B-Instruct.jinja | Generic |
|
||||
| LGAI-EXAONE-EXAONE-3.5-7.8B-Instruct.jinja | Generic |
|
||||
| LatitudeGames-Wayfarer-12B.jinja | Generic |
|
||||
| Magpie-Align-Llama-3-8B-Magpie-Align-v0.1.jinja | Generic |
|
||||
| Magpie-Align-Llama-3.1-8B-Magpie-Align-v0.1.jinja | Generic |
|
||||
| MaziyarPanahi-calme-3.2-instruct-78b.jinja | Generic |
|
||||
| MiniMaxAI-MiniMax-Text-01.jinja | Generic |
|
||||
| MiniMaxAI-MiniMax-VL-01.jinja | Generic |
|
||||
| NaniDAO-deepseek-r1-qwen-2.5-32B-ablated.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| NexaAIDev-Octopus-v2.jinja | Generic |
|
||||
| NousResearch-Hermes-2-Pro-Llama-3-8B-default.jinja | Generic |
|
||||
| NousResearch-Hermes-2-Pro-Llama-3-8B-tool_use.jinja | Hermes 2 Pro |
|
||||
| NousResearch-Hermes-2-Pro-Mistral-7B-default.jinja | Generic |
|
||||
| NousResearch-Hermes-2-Pro-Mistral-7B-tool_use.jinja | Hermes 2 Pro |
|
||||
| NousResearch-Hermes-3-Llama-3.1-70B-default.jinja | Generic |
|
||||
| NousResearch-Hermes-3-Llama-3.1-70B-tool_use.jinja | Hermes 2 Pro |
|
||||
| NovaSky-AI-Sky-T1-32B-Flash.jinja | Hermes 2 Pro |
|
||||
| NovaSky-AI-Sky-T1-32B-Preview.jinja | Hermes 2 Pro |
|
||||
| OnlyCheeini-greesychat-turbo.jinja | Generic |
|
||||
| Orenguteng-Llama-3.1-8B-Lexi-Uncensored-V2.jinja | Llama 3.x |
|
||||
| OrionStarAI-Orion-14B-Chat.jinja | Generic |
|
||||
| PowerInfer-SmallThinker-3B-Preview.jinja | Generic |
|
||||
| PrimeIntellect-INTELLECT-1-Instruct.jinja | Generic |
|
||||
| Qwen-QVQ-72B-Preview.jinja | Generic |
|
||||
| Qwen-QwQ-32B-Preview.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen1.5-7B-Chat.jinja | Generic |
|
||||
| Qwen-Qwen2-7B-Instruct.jinja | Generic |
|
||||
| Qwen-Qwen2-VL-72B-Instruct.jinja | Generic |
|
||||
| Qwen-Qwen2-VL-7B-Instruct.jinja | Generic |
|
||||
| Qwen-Qwen2.5-0.5B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-1.5B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-14B-Instruct-1M.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-14B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-32B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-32B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-3B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-72B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-7B-Instruct-1M.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-7B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-7B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-Coder-32B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-Coder-7B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-Math-1.5B.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-Math-7B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-VL-3B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-VL-72B-Instruct.jinja | Hermes 2 Pro |
|
||||
| Qwen-Qwen2.5-VL-7B-Instruct.jinja | Hermes 2 Pro |
|
||||
| RWKV-Red-Team-ARWKV-7B-Preview-0.1.jinja | Hermes 2 Pro |
|
||||
| SakanaAI-TinySwallow-1.5B-Instruct.jinja | Hermes 2 Pro |
|
||||
| SakanaAI-TinySwallow-1.5B.jinja | Hermes 2 Pro |
|
||||
| Sao10K-70B-L3.3-Cirrus-x1.jinja | Llama 3.x |
|
||||
| SentientAGI-Dobby-Mini-Leashed-Llama-3.1-8B.jinja | Llama 3.x |
|
||||
| SentientAGI-Dobby-Mini-Unhinged-Llama-3.1-8B.jinja | Llama 3.x |
|
||||
| Steelskull-L3.3-Damascus-R1.jinja | Llama 3.x |
|
||||
| Steelskull-L3.3-MS-Nevoria-70b.jinja | Llama 3.x |
|
||||
| Steelskull-L3.3-Nevoria-R1-70b.jinja | Llama 3.x |
|
||||
| THUDM-glm-4-9b-chat.jinja | Generic |
|
||||
| THUDM-glm-edge-1.5b-chat.jinja | Generic |
|
||||
| Tarek07-Progenitor-V1.1-LLaMa-70B.jinja | Llama 3.x |
|
||||
| TheBloke-FusionNet_34Bx2_MoE-AWQ.jinja | Generic |
|
||||
| TinyLlama-TinyLlama-1.1B-Chat-v1.0.jinja | Generic |
|
||||
| UCLA-AGI-Mistral7B-PairRM-SPPO-Iter3.jinja | Generic |
|
||||
| ValiantLabs-Llama3.1-8B-Enigma.jinja | Llama 3.x |
|
||||
| abacusai-Fewshot-Metamath-OrcaVicuna-Mistral.jinja | Generic |
|
||||
| ai21labs-AI21-Jamba-1.5-Large.jinja | Generic |
|
||||
| allenai-Llama-3.1-Tulu-3-405B-SFT.jinja | Generic |
|
||||
| allenai-Llama-3.1-Tulu-3-405B.jinja | Generic |
|
||||
| allenai-Llama-3.1-Tulu-3-8B.jinja | Generic |
|
||||
| arcee-ai-Virtuoso-Lite.jinja | Hermes 2 Pro |
|
||||
| arcee-ai-Virtuoso-Medium-v2.jinja | Hermes 2 Pro |
|
||||
| arcee-ai-Virtuoso-Small-v2.jinja | Hermes 2 Pro |
|
||||
| avemio-GRAG-NEMO-12B-ORPO-HESSIAN-AI.jinja | Generic |
|
||||
| bespokelabs-Bespoke-Stratos-7B.jinja | Hermes 2 Pro |
|
||||
| bfuzzy1-acheron-m1a-llama.jinja | Generic |
|
||||
| bofenghuang-vigogne-2-70b-chat.jinja | Generic |
|
||||
| bytedance-research-UI-TARS-72B-DPO.jinja | Generic |
|
||||
| bytedance-research-UI-TARS-7B-DPO.jinja | Generic |
|
||||
| bytedance-research-UI-TARS-7B-SFT.jinja | Generic |
|
||||
| carsenk-phi3.5_mini_exp_825_uncensored.jinja | Generic |
|
||||
| cyberagent-DeepSeek-R1-Distill-Qwen-14B-Japanese.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| cyberagent-DeepSeek-R1-Distill-Qwen-32B-Japanese.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| databricks-dbrx-instruct.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-Coder-V2-Instruct.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-Coder-V2-Lite-Base.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-Coder-V2-Lite-Instruct.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Llama-70B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Llama-8B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Qwen-14B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Distill-Qwen-7B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1-Zero.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-R1.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-V2-Lite.jinja | Generic |
|
||||
| deepseek-ai-DeepSeek-V2.5.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-DeepSeek-V3.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| deepseek-ai-deepseek-coder-33b-instruct.jinja | Generic |
|
||||
| deepseek-ai-deepseek-coder-6.7b-instruct.jinja | Generic |
|
||||
| deepseek-ai-deepseek-coder-7b-instruct-v1.5.jinja | Generic |
|
||||
| deepseek-ai-deepseek-llm-67b-chat.jinja | Generic |
|
||||
| deepseek-ai-deepseek-llm-7b-chat.jinja | Generic |
|
||||
| dicta-il-dictalm2.0-instruct.jinja | Generic |
|
||||
| ehristoforu-Falcon3-8B-Franken-Basestruct.jinja | Hermes 2 Pro |
|
||||
| fireworks-ai-llama-3-firefunction-v2.jinja | FireFunction v2 |
|
||||
| godlikehhd-alpaca_data_sampled_ifd_new_5200.jinja | Hermes 2 Pro |
|
||||
| godlikehhd-alpaca_data_score_max_0.7_2600.jinja | Hermes 2 Pro |
|
||||
| google-gemma-2-27b-it.jinja | Generic |
|
||||
| google-gemma-2-2b-it.jinja | Generic |
|
||||
| google-gemma-2-2b-jpn-it.jinja | Generic |
|
||||
| google-gemma-7b-it.jinja | Generic |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Llama-70B-abliterated.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Llama-8B-abliterated.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Qwen-14B-abliterated-v2.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Qwen-32B-abliterated.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-DeepSeek-R1-Distill-Qwen-7B-abliterated-v2.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| huihui-ai-Qwen2.5-14B-Instruct-1M-abliterated.jinja | Hermes 2 Pro |
|
||||
| ibm-granite-granite-3.1-8b-instruct.jinja | Generic |
|
||||
| indischepartij-MiniCPM-3B-OpenHermes-2.5-v2.jinja | Generic |
|
||||
| inflatebot-MN-12B-Mag-Mell-R1.jinja | Generic |
|
||||
| jinaai-ReaderLM-v2.jinja | Generic |
|
||||
| kms7530-chemeng_qwen-math-7b_24_1_100_1_nonmath.jinja | Hermes 2 Pro |
|
||||
| knifeayumu-Cydonia-v1.3-Magnum-v4-22B.jinja | Mistral Nemo |
|
||||
| langgptai-qwen1.5-7b-chat-sa-v0.1.jinja | Generic |
|
||||
| lightblue-DeepSeek-R1-Distill-Qwen-7B-Japanese.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| mattshumer-Reflection-Llama-3.1-70B.jinja | Generic |
|
||||
| meetkai-functionary-medium-v3.1.jinja | Functionary v3.1 Llama 3.1 |
|
||||
| meetkai-functionary-medium-v3.2.jinja | Functionary v3.2 |
|
||||
| meta-llama-Llama-2-7b-chat-hf.jinja | Generic |
|
||||
| meta-llama-Llama-3.1-8B-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Llama-3.2-11B-Vision-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Llama-3.2-1B-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Llama-3.2-3B-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Llama-3.3-70B-Instruct.jinja | Llama 3.x |
|
||||
| meta-llama-Meta-Llama-3-8B-Instruct.jinja | Generic |
|
||||
| meta-llama-Meta-Llama-3.1-8B-Instruct.jinja | Llama 3.x |
|
||||
| microsoft-Phi-3-medium-4k-instruct.jinja | Generic |
|
||||
| microsoft-Phi-3-mini-4k-instruct.jinja | Generic |
|
||||
| microsoft-Phi-3-small-8k-instruct.jinja | Generic |
|
||||
| microsoft-Phi-3.5-mini-instruct.jinja | Generic |
|
||||
| microsoft-Phi-3.5-vision-instruct.jinja | Generic |
|
||||
| microsoft-phi-4.jinja | Generic |
|
||||
| migtissera-Tess-3-Mistral-Nemo-12B.jinja | Generic |
|
||||
| ministral-Ministral-3b-instruct.jinja | Generic |
|
||||
| mistralai-Codestral-22B-v0.1.jinja | Generic |
|
||||
| mistralai-Mistral-7B-Instruct-v0.1.jinja | Generic |
|
||||
| mistralai-Mistral-7B-Instruct-v0.2.jinja | Generic |
|
||||
| mistralai-Mistral-7B-Instruct-v0.3.jinja | Mistral Nemo |
|
||||
| mistralai-Mistral-Large-Instruct-2407.jinja | Mistral Nemo |
|
||||
| mistralai-Mistral-Large-Instruct-2411.jinja | Generic |
|
||||
| mistralai-Mistral-Nemo-Instruct-2407.jinja | Mistral Nemo |
|
||||
| mistralai-Mistral-Small-24B-Instruct-2501.jinja | Generic |
|
||||
| mistralai-Mixtral-8x7B-Instruct-v0.1.jinja | Generic |
|
||||
| mkurman-Qwen2.5-14B-DeepSeek-R1-1M.jinja | Hermes 2 Pro |
|
||||
| mlabonne-AlphaMonarch-7B.jinja | Generic |
|
||||
| mlx-community-Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32.jinja | Hermes 2 Pro |
|
||||
| mlx-community-Qwen2.5-VL-7B-Instruct-8bit.jinja | Hermes 2 Pro |
|
||||
| mobiuslabsgmbh-DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| netcat420-MFANNv0.20.jinja | Generic |
|
||||
| netcat420-MFANNv0.24.jinja | Generic |
|
||||
| netease-youdao-Confucius-o1-14B.jinja | Hermes 2 Pro |
|
||||
| nvidia-AceMath-7B-RM.jinja | Hermes 2 Pro |
|
||||
| nvidia-Eagle2-1B.jinja | Hermes 2 Pro |
|
||||
| nvidia-Eagle2-9B.jinja | Hermes 2 Pro |
|
||||
| nvidia-Llama-3.1-Nemotron-70B-Instruct-HF.jinja | Llama 3.x |
|
||||
| onnx-community-DeepSeek-R1-Distill-Qwen-1.5B-ONNX.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| open-thoughts-OpenThinker-7B.jinja | Hermes 2 Pro |
|
||||
| openchat-openchat-3.5-0106.jinja | Generic |
|
||||
| pankajmathur-orca_mini_v6_8b.jinja | Generic |
|
||||
| princeton-nlp-Mistral-7B-Base-SFT-RDPO.jinja | Generic |
|
||||
| princeton-nlp-Mistral-7B-Instruct-DPO.jinja | Generic |
|
||||
| princeton-nlp-Mistral-7B-Instruct-RDPO.jinja | Generic |
|
||||
| prithivMLmods-Bellatrix-Tiny-1.5B-R1.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Bellatrix-Tiny-1B-R1.jinja | Llama 3.x |
|
||||
| prithivMLmods-Bellatrix-Tiny-1B-v3.jinja | Generic |
|
||||
| prithivMLmods-Bellatrix-Tiny-3B-R1.jinja | Llama 3.x |
|
||||
| prithivMLmods-Blaze-14B-xElite.jinja | Generic |
|
||||
| prithivMLmods-Calcium-Opus-14B-Elite2-R1.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Calme-Ties-78B.jinja | Generic |
|
||||
| prithivMLmods-Calme-Ties2-78B.jinja | Generic |
|
||||
| prithivMLmods-Calme-Ties3-78B.jinja | Generic |
|
||||
| prithivMLmods-ChemQwen2-vL.jinja | Generic |
|
||||
| prithivMLmods-GWQ2b.jinja | Generic |
|
||||
| prithivMLmods-LatexMind-2B-Codec.jinja | Generic |
|
||||
| prithivMLmods-Llama-3.2-6B-AlgoCode.jinja | Llama 3.x |
|
||||
| prithivMLmods-Megatron-Opus-14B-Exp.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Megatron-Opus-14B-Stock.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Megatron-Opus-7B-Exp.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Omni-Reasoner-Merged.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Omni-Reasoner4-Merged.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Primal-Opus-14B-Optimus-v1.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-QwQ-Math-IO-500M.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Qwen-7B-Distill-Reasoner.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| prithivMLmods-Qwen2.5-1.5B-DeepSeek-R1-Instruct.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Qwen2.5-14B-DeepSeek-R1-1M.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Qwen2.5-32B-DeepSeek-R1-Instruct.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Qwen2.5-7B-DeepSeek-R1-1M.jinja | Hermes 2 Pro |
|
||||
| prithivMLmods-Triangulum-v2-10B.jinja | Hermes 2 Pro |
|
||||
| qingy2024-Falcon3-2x10B-MoE-Instruct.jinja | Hermes 2 Pro |
|
||||
| rubenroy-Zurich-14B-GCv2-5m.jinja | Hermes 2 Pro |
|
||||
| rubenroy-Zurich-7B-GCv2-5m.jinja | Hermes 2 Pro |
|
||||
| silma-ai-SILMA-Kashif-2B-Instruct-v1.0.jinja | Generic |
|
||||
| simplescaling-s1-32B.jinja | Hermes 2 Pro |
|
||||
| sometimesanotion-Lamarck-14B-v0.7.jinja | Hermes 2 Pro |
|
||||
| sonthenguyen-zephyr-sft-bnb-4bit-DPO-mtbr-180steps.jinja | Generic |
|
||||
| sthenno-tempesthenno-icy-0130.jinja | Generic |
|
||||
| sumink-qwft.jinja | Hermes 2 Pro |
|
||||
| teknium-OpenHermes-2.5-Mistral-7B.jinja | Generic |
|
||||
| thirdeyeai-elevate360m.jinja | Generic |
|
||||
| tiiuae-Falcon3-10B-Instruct.jinja | Hermes 2 Pro |
|
||||
| unsloth-DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| unsloth-DeepSeek-R1-Distill-Llama-8B.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| unsloth-DeepSeek-R1.jinja | DeepSeek R1 (extract reasoning) |
|
||||
| unsloth-Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit.jinja | Generic |
|
||||
| upstage-solar-pro-preview-instruct.jinja | Generic |
|
||||
| whyhow-ai-PatientSeek.jinja | Generic |
|
||||
| xwen-team-Xwen-72B-Chat.jinja | Hermes 2 Pro |
|
||||
| xwen-team-Xwen-7B-Chat.jinja | Hermes 2 Pro |
|
||||
|
||||
This table can be generated with:
|
||||
|
||||
```bash
|
||||
./build/bin/test-chat ../minja/build/tests/*.jinja 2>/dev/null
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
- Generic tool call is supported when the template isn't recognized by native format handlers (you'll see `Chat format: Generic` in the logs).
|
||||
- Use `--chat-template-file` to override the template when appropriate (see examples below)
|
||||
- Generic support may consume more tokens and be less efficient than a model's native format.
|
||||
|
||||
- Run with:
|
||||
|
||||
```shell
|
||||
# Native support:
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M
|
||||
llama-server --jinja -fa -hf bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q6_K_L
|
||||
llama-server --jinja -fa -hf bartowski/functionary-small-v3.2-GGUF:Q4_K_M
|
||||
llama-server --jinja -fa -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_M
|
||||
|
||||
# Native support for DeepSeek R1 works best w/ our own template (official template buggy)
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q6_K_L \
|
||||
--chat-template-file models/templates/llama-cpp-deepseek-r1.jinja
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M \
|
||||
--chat-template-file models/templates/llama-cpp-deepseek-r1.jinja
|
||||
|
||||
# Native support requires the right template for these GGUFs:
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M \
|
||||
--chat-template-file <( python scripts/get_chat_template.py NousResearch/Hermes-2-Pro-Llama-3-8B tool_use )
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M \
|
||||
--chat-template-file <( python scripts/get_chat_template.py NousResearch/Hermes-3-Llama-3.1-8B tool_use )
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/firefunction-v2-GGUF -hff firefunction-v2-IQ1_M.gguf \
|
||||
--chat-template-file <( python scripts/get_chat_template.py fireworks-ai/llama-3-firefunction-v2 tool_use )
|
||||
|
||||
llama-server --jinja -fa -hf bartowski/c4ai-command-r7b-12-2024-GGUF:Q6_K_L \
|
||||
--chat-template-file <( python scripts/get_chat_template.py CohereForAI/c4ai-command-r7b-12-2024 tool_use )
|
||||
|
||||
# Generic format support
|
||||
llama-server --jinja -fa -hf bartowski/phi-4-GGUF:Q4_0
|
||||
llama-server --jinja -fa -hf bartowski/gemma-2-2b-it-GGUF:Q8_0
|
||||
llama-server --jinja -fa -hf bartowski/c4ai-command-r-v01-GGUF:Q2_K
|
||||
```
|
||||
|
||||
- Test in CLI:
|
||||
|
||||
```bash
|
||||
curl http://localhost:8080/v1/chat/completions -d '{
|
||||
"model": "gpt-3.5-turbo",
|
||||
"tools": [
|
||||
{
|
||||
"type":"function",
|
||||
"function":{
|
||||
"name":"python",
|
||||
"description":"Runs code in an ipython interpreter and returns the result of the execution after 60 seconds.",
|
||||
"parameters":{
|
||||
"type":"object",
|
||||
"properties":{
|
||||
"code":{
|
||||
"type":"string",
|
||||
"description":"The code to run in the ipython interpreter."
|
||||
}
|
||||
},
|
||||
"required":["code"]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Print a hello world message with python."
|
||||
}
|
||||
]
|
||||
}'
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>Show output</summary>
|
||||
|
||||
```json
|
||||
{
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "tool",
|
||||
"index": 0,
|
||||
"message": {
|
||||
"content": null,
|
||||
"tool_calls": [
|
||||
{
|
||||
"name": "python",
|
||||
"arguments": "{\"code\":\" \\nprint(\\\"Hello, World!\\\")\"}"
|
||||
}
|
||||
],
|
||||
"role": "assistant"
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1727287211,
|
||||
"model": "gpt-3.5-turbo",
|
||||
"object": "chat.completion",
|
||||
"usage": {
|
||||
"completion_tokens": 16,
|
||||
"prompt_tokens": 44,
|
||||
"total_tokens": 60
|
||||
},
|
||||
"id": "chatcmpl-Htbgh9feMmGM0LEH2hmQvwsCxq3c6Ni8"
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
**See our [Function calling](../../docs/function-calling.md) docs** for more details, supported native tool call styles (generic tool call style is used as fallback) / examples of use.
|
||||
|
||||
### POST `/v1/embeddings`: OpenAI-compatible embeddings API
|
||||
|
||||
|
||||
@@ -521,8 +521,13 @@ static json oaicompat_completion_params_parse(const json & body) {
|
||||
throw std::runtime_error("Only one completion choice is allowed");
|
||||
}
|
||||
|
||||
// Handle "echo" field
|
||||
if (json_value(body, "echo", false)) {
|
||||
throw std::runtime_error("Only no echo is supported");
|
||||
}
|
||||
|
||||
// Params supported by OAI but unsupported by llama.cpp
|
||||
static const std::vector<std::string> unsupported_params { "best_of", "echo", "suffix" };
|
||||
static const std::vector<std::string> unsupported_params { "best_of", "suffix" };
|
||||
for (const auto & param : unsupported_params) {
|
||||
if (body.contains(param)) {
|
||||
throw std::runtime_error("Unsupported param: " + param);
|
||||
|
||||
@@ -5265,6 +5265,7 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * restrict s, size_t bs, const void * r
|
||||
|
||||
#if defined(__ARM_FEATURE_SVE)
|
||||
|
||||
uint32_t aux[3];
|
||||
uint32_t utmp[4];
|
||||
|
||||
const int8_t m32 = 32;
|
||||
@@ -5276,7 +5277,6 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * restrict s, size_t bs, const void * r
|
||||
const svuint8_t m1_sv = svlsl_n_u8_x(svptrue_b8(), m0_sv, 1);
|
||||
const svuint8_t m2_sv = svlsl_n_u8_x(svptrue_b8(), m0_sv, 2);
|
||||
const svuint8_t m3_sv = svlsl_n_u8_x(svptrue_b8(), m0_sv, 3);
|
||||
svbool_t pred_s32 = svnot_b_z (svptrue_b32(), svptrue_pat_b32(SV_VL4));
|
||||
|
||||
float sum = 0;
|
||||
|
||||
@@ -5289,7 +5289,7 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * restrict s, size_t bs, const void * r
|
||||
const int8_t * restrict q8_sv = y[i].qs;
|
||||
|
||||
// Set up scales
|
||||
uint32_t * aux = &x[i].scales;
|
||||
memcpy(aux, x[i].scales, 12);
|
||||
utmp[3] = ((aux[1] >> 4) & kmask2) | (((aux[2] >> 6) & kmask1) << 4);
|
||||
utmp[2] = ((aux[0] >> 4) & kmask2) | (((aux[2] >> 4) & kmask1) << 4);
|
||||
utmp[1] = (aux[1] & kmask2) | (((aux[2] >> 2) & kmask1) << 4);
|
||||
|
||||
@@ -249,6 +249,7 @@ struct vk_device_struct {
|
||||
vk_pipeline pipeline_relu_f32;
|
||||
vk_pipeline pipeline_leaky_relu_f32;
|
||||
vk_pipeline pipeline_tanh_f32;
|
||||
vk_pipeline pipeline_sigmoid_f32;
|
||||
vk_pipeline pipeline_diag_mask_inf_f32;
|
||||
vk_pipeline pipeline_soft_max_f32, pipeline_soft_max_f32_f16;
|
||||
vk_pipeline pipeline_soft_max_f32_wg512, pipeline_soft_max_f32_f16_wg512;
|
||||
@@ -2189,6 +2190,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
|
||||
ggml_vk_create_pipeline(device, device->pipeline_relu_f32, "relu_f32", relu_f32_len, relu_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
|
||||
ggml_vk_create_pipeline(device, device->pipeline_leaky_relu_f32, "leaky_relu_f32", leaky_relu_f32_len, leaky_relu_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
|
||||
ggml_vk_create_pipeline(device, device->pipeline_tanh_f32, "tanh_f32", tanh_f32_len, tanh_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
|
||||
ggml_vk_create_pipeline(device, device->pipeline_sigmoid_f32, "sigmoid_f32", sigmoid_f32_len, sigmoid_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
|
||||
|
||||
ggml_vk_create_pipeline(device, device->pipeline_diag_mask_inf_f32, "diag_mask_inf_f32", diag_mask_inf_f32_len, diag_mask_inf_f32_data, "main", 2, sizeof(vk_op_diag_mask_push_constants), {1, 512, 1}, {}, 1, true);
|
||||
|
||||
@@ -4190,7 +4192,7 @@ static void ggml_vk_mul_mat_q_f16(ggml_backend_vk_context * ctx, vk_context& sub
|
||||
}
|
||||
if (qy_needs_dequant) {
|
||||
d_Y = ctx->prealloc_y;
|
||||
GGML_ASSERT(d_Y->size >= y_sz * ne02 * ne03);
|
||||
GGML_ASSERT(d_Y->size >= y_sz * ne12 * ne13);
|
||||
} else {
|
||||
d_Y = d_Qy;
|
||||
y_buf_offset = qy_buf_offset;
|
||||
@@ -4767,7 +4769,7 @@ static void ggml_vk_mul_mat_id_q_f16(ggml_backend_vk_context * ctx, vk_context&
|
||||
}
|
||||
if (qy_needs_dequant) {
|
||||
d_Y = ctx->prealloc_y;
|
||||
GGML_ASSERT(d_Y->size >= y_sz * ne02 * ne03);
|
||||
GGML_ASSERT(d_Y->size >= y_sz * ne12 * ne13);
|
||||
} else {
|
||||
d_Y = d_Qy;
|
||||
y_buf_offset = qy_buf_offset;
|
||||
@@ -5342,6 +5344,11 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
|
||||
return ctx->device->pipeline_tanh_f32;
|
||||
}
|
||||
break;
|
||||
case GGML_UNARY_OP_SIGMOID:
|
||||
if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) {
|
||||
return ctx->device->pipeline_sigmoid_f32;
|
||||
}
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
@@ -7335,6 +7342,7 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_tensor * nod
|
||||
case GGML_UNARY_OP_GELU_QUICK:
|
||||
case GGML_UNARY_OP_RELU:
|
||||
case GGML_UNARY_OP_TANH:
|
||||
case GGML_UNARY_OP_SIGMOID:
|
||||
break;
|
||||
default:
|
||||
return false;
|
||||
@@ -7551,6 +7559,7 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_tensor * nod
|
||||
case GGML_UNARY_OP_GELU_QUICK:
|
||||
case GGML_UNARY_OP_RELU:
|
||||
case GGML_UNARY_OP_TANH:
|
||||
case GGML_UNARY_OP_SIGMOID:
|
||||
ggml_vk_unary(ctx, compute_ctx, src0, node, dryrun);
|
||||
break;
|
||||
default:
|
||||
@@ -7738,6 +7747,7 @@ static bool ggml_vk_compute_forward(ggml_backend_vk_context * ctx, ggml_tensor *
|
||||
case GGML_UNARY_OP_GELU_QUICK:
|
||||
case GGML_UNARY_OP_RELU:
|
||||
case GGML_UNARY_OP_TANH:
|
||||
case GGML_UNARY_OP_SIGMOID:
|
||||
buf = tensor->buffer;
|
||||
break;
|
||||
default:
|
||||
@@ -8439,6 +8449,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
|
||||
case GGML_UNARY_OP_SILU:
|
||||
case GGML_UNARY_OP_RELU:
|
||||
case GGML_UNARY_OP_TANH:
|
||||
case GGML_UNARY_OP_SIGMOID:
|
||||
return ggml_is_contiguous(op->src[0]);
|
||||
default:
|
||||
return false;
|
||||
@@ -9105,6 +9116,9 @@ static void ggml_vk_check_results_0(ggml_tensor * tensor) {
|
||||
case GGML_UNARY_OP_TANH:
|
||||
tensor_clone = ggml_tanh(ggml_ctx, src_clone[0]);
|
||||
break;
|
||||
case GGML_UNARY_OP_SIGMOID:
|
||||
tensor_clone = ggml_sigmoid(ggml_ctx, src_clone[0]);
|
||||
break;
|
||||
default:
|
||||
std::cerr << "Missing vk_check_results OP: " << ggml_op_name(tensor->op) << std::endl;
|
||||
GGML_ABORT("fatal error");
|
||||
|
||||
@@ -0,0 +1,20 @@
|
||||
#version 450
|
||||
|
||||
#include "generic_head.comp"
|
||||
#include "types.comp"
|
||||
|
||||
#extension GL_EXT_control_flow_attributes : enable
|
||||
|
||||
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
|
||||
|
||||
layout (binding = 0) readonly buffer X {A_TYPE data_a[];};
|
||||
layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};
|
||||
|
||||
void main() {
|
||||
const uint i = gl_GlobalInvocationID.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
|
||||
|
||||
if (i >= p.KX) {
|
||||
return;
|
||||
}
|
||||
data_d[i] = D_TYPE(1. / (1 + exp(-1. *data_a[i])));
|
||||
}
|
||||
@@ -482,6 +482,7 @@ void process_shaders() {
|
||||
string_to_spv("relu_f32", "relu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
|
||||
string_to_spv("leaky_relu_f32", "leaky_relu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
|
||||
string_to_spv("tanh_f32", "tanh.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
|
||||
string_to_spv("sigmoid_f32", "sigmoid.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
|
||||
|
||||
string_to_spv("diag_mask_inf_f32", "diag_mask_inf.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
|
||||
|
||||
|
||||
@@ -2,12 +2,14 @@
|
||||
import logging
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from gguf.gguf_reader import GGUFReader
|
||||
|
||||
logger = logging.getLogger("reader")
|
||||
|
||||
# Necessary to load the local gguf package
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent))
|
||||
|
||||
from gguf.gguf_reader import GGUFReader
|
||||
|
||||
|
||||
def read_gguf_file(gguf_file_path):
|
||||
"""
|
||||
|
||||
@@ -6,6 +6,7 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
from collections import OrderedDict
|
||||
from typing import Any, Literal, NamedTuple, TypeVar, Union
|
||||
|
||||
@@ -15,7 +16,6 @@ import numpy.typing as npt
|
||||
from .quants import quant_shape_to_byte_shape
|
||||
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
# Allow running file in package as a script.
|
||||
@@ -28,6 +28,7 @@ from gguf.constants import (
|
||||
GGUF_VERSION,
|
||||
GGMLQuantizationType,
|
||||
GGUFValueType,
|
||||
GGUFEndian,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -53,6 +54,48 @@ class ReaderField(NamedTuple):
|
||||
|
||||
types: list[GGUFValueType] = []
|
||||
|
||||
def contents(self, index_or_slice: int | slice = slice(None)) -> Any:
|
||||
if self.types:
|
||||
to_string = lambda x: str(x.tobytes(), encoding='utf-8') # noqa: E731
|
||||
main_type = self.types[0]
|
||||
|
||||
if main_type == GGUFValueType.ARRAY:
|
||||
sub_type = self.types[-1]
|
||||
|
||||
if sub_type == GGUFValueType.STRING:
|
||||
indices = self.data[index_or_slice]
|
||||
|
||||
if isinstance(index_or_slice, int):
|
||||
return to_string(self.parts[indices]) # type: ignore
|
||||
else:
|
||||
return [to_string(self.parts[idx]) for idx in indices] # type: ignore
|
||||
else:
|
||||
# FIXME: When/if _get_field_parts() support multi-dimensional arrays, this must do so too
|
||||
|
||||
# Check if it's unsafe to perform slice optimization on data
|
||||
# if any(True for idx in self.data if len(self.parts[idx]) != 1):
|
||||
# optim_slice = slice(None)
|
||||
# else:
|
||||
# optim_slice = index_or_slice
|
||||
# index_or_slice = slice(None)
|
||||
|
||||
# if isinstance(optim_slice, int):
|
||||
# return self.parts[self.data[optim_slice]].tolist()[0]
|
||||
# else:
|
||||
# return [pv for idx in self.data[optim_slice] for pv in self.parts[idx].tolist()][index_or_slice]
|
||||
|
||||
if isinstance(index_or_slice, int):
|
||||
return self.parts[self.data[index_or_slice]].tolist()[0]
|
||||
else:
|
||||
return [pv for idx in self.data[index_or_slice] for pv in self.parts[idx].tolist()]
|
||||
|
||||
if main_type == GGUFValueType.STRING:
|
||||
return to_string(self.parts[-1])
|
||||
else:
|
||||
return self.parts[-1].tolist()[0]
|
||||
|
||||
return None
|
||||
|
||||
|
||||
class ReaderTensor(NamedTuple):
|
||||
name: str
|
||||
@@ -101,10 +144,19 @@ class GGUFReader:
|
||||
# If we get 0 here that means it's (probably) a GGUF file created for
|
||||
# the opposite byte order of the machine this script is running on.
|
||||
self.byte_order = 'S'
|
||||
temp_version = temp_version.newbyteorder(self.byte_order)
|
||||
temp_version = temp_version.view(temp_version.dtype.newbyteorder(self.byte_order))
|
||||
version = temp_version[0]
|
||||
if version not in READER_SUPPORTED_VERSIONS:
|
||||
raise ValueError(f'Sorry, file appears to be version {version} which we cannot handle')
|
||||
if sys.byteorder == "little":
|
||||
# Host is little endian
|
||||
host_endian = GGUFEndian.LITTLE
|
||||
swapped_endian = GGUFEndian.BIG
|
||||
else:
|
||||
# Sorry PDP or other weird systems that don't use BE or LE.
|
||||
host_endian = GGUFEndian.BIG
|
||||
swapped_endian = GGUFEndian.LITTLE
|
||||
self.endianess = swapped_endian if self.byte_order == "S" else host_endian
|
||||
self.fields: OrderedDict[str, ReaderField] = OrderedDict()
|
||||
self.tensors: list[ReaderTensor] = []
|
||||
offs += self._push_field(ReaderField(offs, 'GGUF.version', [temp_version], [0], [GGUFValueType.UINT32]))
|
||||
@@ -146,9 +198,7 @@ class GGUFReader:
|
||||
itemsize = int(np.empty([], dtype = dtype).itemsize)
|
||||
end_offs = offset + itemsize * count
|
||||
arr = self.data[offset:end_offs].view(dtype=dtype)[:count]
|
||||
if override_order is None:
|
||||
return arr
|
||||
return arr.view(arr.dtype.newbyteorder(override_order))
|
||||
return arr.view(arr.dtype.newbyteorder(self.byte_order if override_order is None else override_order))
|
||||
|
||||
def _push_field(self, field: ReaderField, skip_sum: bool = False) -> int:
|
||||
if field.name in self.fields:
|
||||
@@ -190,6 +240,7 @@ class GGUFReader:
|
||||
offs += int(alen.nbytes)
|
||||
aparts: list[npt.NDArray[Any]] = [raw_itype, alen]
|
||||
data_idxs: list[int] = []
|
||||
# FIXME: Handle multi-dimensional arrays properly instead of flattening
|
||||
for idx in range(alen[0]):
|
||||
curr_size, curr_parts, curr_idxs, curr_types = self._get_field_parts(offs, raw_itype[0])
|
||||
if idx == 0:
|
||||
|
||||
@@ -20,22 +20,15 @@ logger = logging.getLogger("gguf-convert-endian")
|
||||
|
||||
|
||||
def convert_byteorder(reader: gguf.GGUFReader, args: argparse.Namespace) -> None:
|
||||
if np.uint32(1) == np.uint32(1).newbyteorder("<"):
|
||||
# Host is little endian
|
||||
host_endian = "little"
|
||||
swapped_endian = "big"
|
||||
file_endian = reader.endianess.name
|
||||
if reader.byte_order == 'S':
|
||||
host_endian = 'BIG' if file_endian == 'LITTLE' else 'LITTLE'
|
||||
else:
|
||||
# Sorry PDP or other weird systems that don't use BE or LE.
|
||||
host_endian = "big"
|
||||
swapped_endian = "little"
|
||||
if reader.byte_order == "S":
|
||||
file_endian = swapped_endian
|
||||
else:
|
||||
file_endian = host_endian
|
||||
order = host_endian if args.order == "native" else args.order
|
||||
logger.info(f"* Host is {host_endian.upper()} endian, GGUF file seems to be {file_endian.upper()} endian")
|
||||
host_endian = file_endian
|
||||
order = host_endian if args.order == "native" else args.order.upper()
|
||||
logger.info(f"* Host is {host_endian} endian, GGUF file seems to be {file_endian} endian")
|
||||
if file_endian == order:
|
||||
logger.info(f"* File is already {order.upper()} endian. Nothing to do.")
|
||||
logger.info(f"* File is already {order} endian. Nothing to do.")
|
||||
sys.exit(0)
|
||||
logger.info("* Checking tensors for conversion compatibility")
|
||||
for tensor in reader.tensors:
|
||||
@@ -47,7 +40,7 @@ def convert_byteorder(reader: gguf.GGUFReader, args: argparse.Namespace) -> None
|
||||
gguf.GGMLQuantizationType.Q6_K,
|
||||
):
|
||||
raise ValueError(f"Cannot handle type {tensor.tensor_type.name} for tensor {repr(tensor.name)}")
|
||||
logger.info(f"* Preparing to convert from {file_endian.upper()} to {order.upper()}")
|
||||
logger.info(f"* Preparing to convert from {file_endian} to {order}")
|
||||
if args.dry_run:
|
||||
return
|
||||
logger.warning("*** Warning *** Warning *** Warning **")
|
||||
|
||||
@@ -9,8 +9,6 @@ import sys
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import numpy as np
|
||||
|
||||
# Necessary to load the local gguf package
|
||||
if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent.parent / 'gguf-py').exists():
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
|
||||
@@ -21,11 +19,11 @@ logger = logging.getLogger("gguf-dump")
|
||||
|
||||
|
||||
def get_file_host_endian(reader: GGUFReader) -> tuple[str, str]:
|
||||
host_endian = 'LITTLE' if np.uint32(1) == np.uint32(1).newbyteorder("<") else 'BIG'
|
||||
file_endian = reader.endianess.name
|
||||
if reader.byte_order == 'S':
|
||||
file_endian = 'BIG' if host_endian == 'LITTLE' else 'LITTLE'
|
||||
host_endian = 'BIG' if file_endian == 'LITTLE' else 'LITTLE'
|
||||
else:
|
||||
file_endian = host_endian
|
||||
host_endian = file_endian
|
||||
return (host_endian, file_endian)
|
||||
|
||||
|
||||
@@ -45,12 +43,20 @@ def dump_metadata(reader: GGUFReader, args: argparse.Namespace) -> None:
|
||||
pretty_type = str(field.types[-1].name)
|
||||
|
||||
log_message = f' {n:5}: {pretty_type:10} | {len(field.data):8} | {field.name}'
|
||||
if len(field.types) == 1:
|
||||
if field.types:
|
||||
curr_type = field.types[0]
|
||||
if curr_type == GGUFValueType.STRING:
|
||||
log_message += ' = {0}'.format(repr(str(bytes(field.parts[-1]), encoding='utf-8')[:60]))
|
||||
elif field.types[0] in reader.gguf_scalar_to_np:
|
||||
log_message += ' = {0}'.format(field.parts[-1][0])
|
||||
content = field.contents()
|
||||
if len(content) > 60:
|
||||
content = content[:57] + '...'
|
||||
log_message += ' = {0}'.format(repr(content))
|
||||
elif curr_type in reader.gguf_scalar_to_np:
|
||||
log_message += ' = {0}'.format(field.contents())
|
||||
else:
|
||||
content = repr(field.contents(slice(6)))
|
||||
if len(field.data) > 6:
|
||||
content = content[:-1] + ', ...]'
|
||||
log_message += ' = {0}'.format(content)
|
||||
print(log_message) # noqa: NP100
|
||||
if args.no_tensors:
|
||||
return
|
||||
@@ -82,15 +88,9 @@ def dump_metadata_json(reader: GGUFReader, args: argparse.Namespace) -> None:
|
||||
curr["array_types"] = [t.name for t in field.types][1:]
|
||||
if not args.json_array:
|
||||
continue
|
||||
itype = field.types[-1]
|
||||
if itype == GGUFValueType.STRING:
|
||||
curr["value"] = [str(bytes(field.parts[idx]), encoding="utf-8") for idx in field.data]
|
||||
else:
|
||||
curr["value"] = [pv for idx in field.data for pv in field.parts[idx].tolist()]
|
||||
elif field.types[0] == GGUFValueType.STRING:
|
||||
curr["value"] = str(bytes(field.parts[-1]), encoding="utf-8")
|
||||
curr["value"] = field.contents()
|
||||
else:
|
||||
curr["value"] = field.parts[-1].tolist()[0]
|
||||
curr["value"] = field.contents()
|
||||
if not args.no_tensors:
|
||||
for idx, tensor in enumerate(reader.tensors):
|
||||
tensors[tensor.name] = {
|
||||
|
||||
@@ -8,7 +8,6 @@ import sys
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from typing import Any, Sequence, NamedTuple
|
||||
|
||||
@@ -27,45 +26,10 @@ class MetadataDetails(NamedTuple):
|
||||
description: str = ''
|
||||
|
||||
|
||||
def get_byteorder(reader: gguf.GGUFReader) -> gguf.GGUFEndian:
|
||||
if np.uint32(1) == np.uint32(1).newbyteorder("<"):
|
||||
# Host is little endian
|
||||
host_endian = gguf.GGUFEndian.LITTLE
|
||||
swapped_endian = gguf.GGUFEndian.BIG
|
||||
else:
|
||||
# Sorry PDP or other weird systems that don't use BE or LE.
|
||||
host_endian = gguf.GGUFEndian.BIG
|
||||
swapped_endian = gguf.GGUFEndian.LITTLE
|
||||
|
||||
if reader.byte_order == "S":
|
||||
return swapped_endian
|
||||
else:
|
||||
return host_endian
|
||||
|
||||
|
||||
def decode_field(field: gguf.ReaderField | None) -> Any:
|
||||
if field and field.types:
|
||||
main_type = field.types[0]
|
||||
|
||||
if main_type == gguf.GGUFValueType.ARRAY:
|
||||
sub_type = field.types[-1]
|
||||
|
||||
if sub_type == gguf.GGUFValueType.STRING:
|
||||
return [str(bytes(field.parts[idx]), encoding='utf-8') for idx in field.data]
|
||||
else:
|
||||
return [pv for idx in field.data for pv in field.parts[idx].tolist()]
|
||||
if main_type == gguf.GGUFValueType.STRING:
|
||||
return str(bytes(field.parts[-1]), encoding='utf-8')
|
||||
else:
|
||||
return field.parts[-1][0]
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def get_field_data(reader: gguf.GGUFReader, key: str) -> Any:
|
||||
field = reader.get_field(key)
|
||||
|
||||
return decode_field(field)
|
||||
return field.contents() if field else None
|
||||
|
||||
|
||||
def find_token(token_list: Sequence[int], token: str) -> Sequence[int]:
|
||||
@@ -93,7 +57,7 @@ def copy_with_new_metadata(reader: gguf.GGUFReader, writer: gguf.GGUFWriter, new
|
||||
logger.debug(f'Removing {field.name}')
|
||||
continue
|
||||
|
||||
old_val = MetadataDetails(field.types[0], decode_field(field))
|
||||
old_val = MetadataDetails(field.types[0], field.contents())
|
||||
val = new_metadata.get(field.name, old_val)
|
||||
|
||||
if field.name in new_metadata:
|
||||
@@ -192,7 +156,6 @@ def main() -> None:
|
||||
reader = gguf.GGUFReader(args.input, 'r')
|
||||
|
||||
arch = get_field_data(reader, gguf.Keys.General.ARCHITECTURE)
|
||||
endianess = get_byteorder(reader)
|
||||
|
||||
token_list = get_field_data(reader, gguf.Keys.Tokenizer.LIST) or []
|
||||
|
||||
@@ -230,7 +193,7 @@ def main() -> None:
|
||||
sys.exit(0)
|
||||
|
||||
logger.info(f'* Writing: {args.output}')
|
||||
writer = gguf.GGUFWriter(args.output, arch=arch, endianess=endianess)
|
||||
writer = gguf.GGUFWriter(args.output, arch=arch, endianess=reader.endianess)
|
||||
|
||||
alignment = get_field_data(reader, gguf.Keys.General.ALIGNMENT)
|
||||
if alignment is not None:
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[tool.poetry]
|
||||
name = "gguf"
|
||||
version = "0.15.0"
|
||||
version = "0.16.0"
|
||||
description = "Read and write ML models in GGUF for GGML"
|
||||
authors = ["GGML <[email protected]>"]
|
||||
packages = [
|
||||
|
||||
Reference in New Issue
Block a user