|
2696 | 2696 | - filename: Qwentile2.5-32B-Instruct-Q4_K_M.gguf
|
2697 | 2697 | sha256: e476d6e3c15c78fc3f986d7ae8fa35c16116843827f2e6243c05767cef2f3615
|
2698 | 2698 | uri: huggingface://bartowski/Qwentile2.5-32B-Instruct-GGUF/Qwentile2.5-32B-Instruct-Q4_K_M.gguf
|
2699 |
| -- !!merge <<: *qwen25 |
2700 |
| - name: "deepseek-r1-distill-qwen-1.5b" |
2701 |
| - icon: "https://avatars.githubusercontent.com/u/148330874" |
2702 |
| - urls: |
2703 |
| - - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5b |
2704 |
| - - https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF |
2705 |
| - description: | |
2706 |
| - DeepSeek-R1 is our advanced first-generation reasoning model designed to enhance performance in reasoning tasks. |
2707 |
| - Building on the foundation laid by its predecessor, DeepSeek-R1-Zero, which was trained using large-scale reinforcement learning (RL) without supervised fine-tuning, DeepSeek-R1 addresses the challenges faced by R1-Zero, such as endless repetition, poor readability, and language mixing. |
2708 |
| - By incorporating cold-start data prior to the RL phase,DeepSeek-R1 significantly improves reasoning capabilities and achieves performance levels comparable to OpenAI-o1 across a variety of domains, including mathematics, coding, and complex reasoning tasks. |
2709 |
| - overrides: |
2710 |
| - parameters: |
2711 |
| - model: deepseek-r1-distill-qwen-1.5b-Q4_K_M.gguf |
2712 |
| - files: |
2713 |
| - - filename: deepseek-r1-distill-qwen-1.5b-Q4_K_M.gguf |
2714 |
| - sha256: c2c43b6018cf7700ce0ddee8807deb1a9a26758ef878232f3a142d16df81f0fe |
2715 |
| - uri: huggingface://unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf |
2716 |
| -- !!merge <<: *qwen25 |
2717 |
| - name: "deepseek-r1-distill-qwen-7b" |
2718 |
| - urls: |
2719 |
| - - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B |
2720 |
| - - https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF |
2721 |
| - description: | |
2722 |
| - DeepSeek-R1 is our advanced first-generation reasoning model designed to enhance performance in reasoning tasks. |
2723 |
| - Building on the foundation laid by its predecessor, DeepSeek-R1-Zero, which was trained using large-scale reinforcement learning (RL) without supervised fine-tuning, DeepSeek-R1 addresses the challenges faced by R1-Zero, such as endless repetition, poor readability, and language mixing. |
2724 |
| - By incorporating cold-start data prior to the RL phase,DeepSeek-R1 significantly improves reasoning capabilities and achieves performance levels comparable to OpenAI-o1 across a variety of domains, including mathematics, coding, and complex reasoning tasks. |
2725 |
| - overrides: |
2726 |
| - parameters: |
2727 |
| - model: DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf |
2728 |
| - files: |
2729 |
| - - filename: DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf |
2730 |
| - sha256: 731ece8d06dc7eda6f6572997feb9ee1258db0784827e642909d9b565641937b |
2731 |
| - uri: huggingface://bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF/DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf |
2732 | 2699 | - &archfunct
|
2733 | 2700 | license: apache-2.0
|
2734 | 2701 | tags:
|
|
5334 | 5301 | - filename: archangel_sft_pythia2-8b.Q4_K_M.gguf
|
5335 | 5302 | sha256: a47782c55ef2b39b19644213720a599d9849511a73c9ebb0c1de749383c0a0f8
|
5336 | 5303 | uri: huggingface://RichardErkhov/ContextualAI_-_archangel_sft_pythia2-8b-gguf/archangel_sft_pythia2-8b.Q4_K_M.gguf
|
| 5304 | +- &deepseek-r1 ## Start DeepSeek-R1 |
| 5305 | + url: "github:mudler/LocalAI/gallery/chatml.yaml@master" |
| 5306 | + name: "deepseek-r1-distill-qwen-1.5b" |
| 5307 | + icon: "https://avatars.githubusercontent.com/u/148330874" |
| 5308 | + urls: |
| 5309 | + - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5b |
| 5310 | + - https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF |
| 5311 | + description: | |
| 5312 | + DeepSeek-R1 is our advanced first-generation reasoning model designed to enhance performance in reasoning tasks. |
| 5313 | + Building on the foundation laid by its predecessor, DeepSeek-R1-Zero, which was trained using large-scale reinforcement learning (RL) without supervised fine-tuning, DeepSeek-R1 addresses the challenges faced by R1-Zero, such as endless repetition, poor readability, and language mixing. |
| 5314 | + By incorporating cold-start data prior to the RL phase,DeepSeek-R1 significantly improves reasoning capabilities and achieves performance levels comparable to OpenAI-o1 across a variety of domains, including mathematics, coding, and complex reasoning tasks. |
| 5315 | + overrides: |
| 5316 | + parameters: |
| 5317 | + model: DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf |
| 5318 | + files: |
| 5319 | + - filename: DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf |
| 5320 | + sha256: 1741e5b2d062b07acf048bf0d2c514dadf2a48f94e2b4aa0cfe069af3838ee2f |
| 5321 | + uri: huggingface://bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf |
| 5322 | +- !!merge <<: *deepseek-r1 |
| 5323 | + name: "deepseek-r1-distill-qwen-7b" |
| 5324 | + urls: |
| 5325 | + - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B |
| 5326 | + - https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF |
| 5327 | + overrides: |
| 5328 | + parameters: |
| 5329 | + model: DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf |
| 5330 | + files: |
| 5331 | + - filename: DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf |
| 5332 | + sha256: 731ece8d06dc7eda6f6572997feb9ee1258db0784827e642909d9b565641937b |
| 5333 | + uri: huggingface://bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF/DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf |
| 5334 | +- !!merge <<: *deepseek-r1 |
| 5335 | + name: "deepseek-r1-distill-qwen-14b" |
| 5336 | + urls: |
| 5337 | + - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B |
| 5338 | + - https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF |
| 5339 | + overrides: |
| 5340 | + parameters: |
| 5341 | + model: DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf |
| 5342 | + files: |
| 5343 | + - filename: DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf |
| 5344 | + sha256: 0b319bd0572f2730bfe11cc751defe82045fad5085b4e60591ac2cd2d9633181 |
| 5345 | + uri: huggingface://bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF/DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf |
| 5346 | +- !!merge <<: *deepseek-r1 |
| 5347 | + name: "deepseek-r1-distill-qwen-32b" |
| 5348 | + urls: |
| 5349 | + - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B |
| 5350 | + - https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF |
| 5351 | + overrides: |
| 5352 | + parameters: |
| 5353 | + model: DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf |
| 5354 | + files: |
| 5355 | + - filename: DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf |
| 5356 | + sha256: bed9b0f551f5b95bf9da5888a48f0f87c37ad6b72519c4cbd775f54ac0b9fc62 |
| 5357 | + uri: huggingface://bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF/DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf |
| 5358 | +- !!merge <<: *deepseek-r1 |
| 5359 | + name: "deepseek-r1-distill-llama-8b" |
| 5360 | + icon: "https://avatars.githubusercontent.com/u/148330874" |
| 5361 | + urls: |
| 5362 | + - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B |
| 5363 | + - https://huggingface.co/bartowski/DeepSeek-R1-Distill-Llama-8B-GGUF |
| 5364 | + overrides: |
| 5365 | + parameters: |
| 5366 | + model: DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf |
| 5367 | + files: |
| 5368 | + - filename: DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf |
| 5369 | + sha256: 87bcba20b4846d8dadf753d3ff48f9285d131fc95e3e0e7e934d4f20bc896f5d |
| 5370 | + uri: huggingface://bartowski/DeepSeek-R1-Distill-Llama-8B-GGUF/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf |
| 5371 | +- !!merge <<: *deepseek-r1 |
| 5372 | + name: "deepseek-r1-distill-llama-70b" |
| 5373 | + icon: "https://avatars.githubusercontent.com/u/148330874" |
| 5374 | + urls: |
| 5375 | + - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
| 5376 | + - https://huggingface.co/bartowski/DeepSeek-R 1-Distill-Llama-70B-GGUF |
| 5377 | + overrides: |
| 5378 | + parameters: |
| 5379 | + model: DeepSeek-R1-Distill-Llama-70B-Q4_K_M.gguf |
| 5380 | + files: |
| 5381 | + - filename: DeepSeek-R1-Distill-Llama-70B-Q4_K_M.gguf |
| 5382 | + sha256: 181a82a1d6d2fa24fe4db83a68eee030384986bdbdd4773ba76424e3a6eb9fd8 |
| 5383 | + uri: huggingface://bartowski/DeepSeek-R1-Distill-Llama-70B-GGUF/DeepSeek-R1-Distill-Llama-70B-Q4_K_M.gguf |
5337 | 5384 | - &qwen2 ## Start QWEN2
|
5338 | 5385 | url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
|
5339 | 5386 | name: "qwen2-7b-instruct"
|
|
0 commit comments