win10

win10/aya-expanse-32b-Q5KM-GGUF This model was converted to GGUF format from `CohereForAI/aya-expanse-32b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/aya-expanse-32b-Q4KM-GGUF This model was converted to GGUF format from `CohereForAI/aya-expanse-32b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

This is an expanded version of unsloth/gpt-oss-20b-BF16 scaled up to 26B parameters and created with abliteration (see abliteration to know more about it). Usage You can use this model in your applications by loading it with Hugging Face's `transformers` library: - Risk of Sensitive or Controversial Outputs: This model's safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs. - Not Suitable for All Audiences: Due to limited content filtering, the model's outputs may be inappropriate for public settings, underage users, or applications requiring high security. - Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences. - Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications. - Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content. - No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. The author bears no responsibility for any consequences arising from its use. Donation Your donation helps us continue our further development and improvement, a cup of coffee can do it. - PayPal: Support via PayPal - Ko-fi: Support our work on Ko-fi

win10/openhands-Nemotron-32B-karcher-Q4KM-GGUF This model was converted to GGUF format from `mergekit-community/openhands-Nemotron-32B-karcher` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/MagiDevs-24B-2506-Vision-Q80-GGUF This model was converted to GGUF format from `win10/MagiDevs-24B-2506-Vision` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/Infinirc-ArliAI-RPMax-v1.3-merge-13.3B-Q80-GGUF This model was converted to GGUF format from `win10/Infinirc-ArliAI-RPMax-v1.3-merge-13.3B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/MagiDevs-24B-2506-Vision-Q6K-GGUF This model was converted to GGUF format from `win10/MagiDevs-24B-2506-Vision` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

This is a merge of pre-trained language models created using mergekit. This model was merged using the passthrough merge method. The following models were included in the merge: win10/Norns-Qwen2.5-7B The following YAML configuration was used to produce this model:

win10/EVA-Instruct-QwQ-32B-Preview-Q4KM-GGUF This model was converted to GGUF format from `win10/EVA-Instruct-QwQ-32B-Preview` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/shuttle-3-mini-Q80-GGUF This model was converted to GGUF format from `shuttleai/shuttle-3-mini` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/Mistral-RP-24b-karcher-pro-Q4KM-GGUF This model was converted to GGUF format from `win10/Mistral-RP-24b-karcher-pro` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/Lingshu-32B-Q4KM-GGUF This model was converted to GGUF format from `lingshu-medical-mllm/Lingshu-32B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

Please support my ko-fi. https://ko-fi.com/ogodwin10 my-paypal: https://www.paypal.com/ncp/payment/X7DMN9DUBH2X8 If you like this model, please give me some sponsorship and I will continue to create better merges. If there is a device that can fine-tune the model, there will be more new models fine-tuned after the merge (just like solar 10b). merge This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using Qwen/QwQ-32B-Preview as a base. The following models were included in the merge: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 The following YAML configuration was used to produce this model:

Your support = more models My Ko-fi page (Click here) This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using sthenno-com/miscii-14b-1225 as a base. The following models were included in the merge: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B sthenno/tempesthenno-ppo-ckpt40 The following YAML configuration was used to produce this model:

win10/SphinxMind-14B-Q80-GGUF This model was converted to GGUF format from `win10/SphinxMind-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/ArliAI-RPMax-v1.3-merge-13.3B-Q80-GGUF This model was converted to GGUF format from `win10/ArliAI-RPMax-v1.3-merge-13.3B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/EVA-Meissa-mini-pro-v2-Q80-GGUF This model was converted to GGUF format from `win10/EVA-Meissa-mini-pro-v2` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/openhands-Nemotron-32B-karcher-300-Q4KM-GGUF This model was converted to GGUF format from `mergekit-community/openhands-Nemotron-32B-karcher-300` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

Qwen2.5-2B-Instruct is a merge of the following models using LazyMergekit: Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct

win10/Norns-Qwen2.5-12B-Q80-GGUF This model was converted to GGUF format from `win10/Norns-Qwen2.5-12B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/EVA-Norns-Qwen2.5-v0.1-Q80-GGUF This model was converted to GGUF format from `win10/EVA-Norns-Qwen2.5-v0.1` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

This is a merge of pre-trained language models created using mergekit. This model was merged using the passthrough merge method. The following models were included in the merge: Qwen/Qwen2.5-Math-7B-Instruct The following YAML configuration was used to produce this model:

This is a merge of pre-trained language models created using mergekit. This model was merged using the passthrough merge method. The following models were included in the merge: win10/ArliAI-RPMax-v1.3-merge-8B The following YAML configuration was used to produce this model:

my kofi: https://ko-fi.com/ogodwin10 If you like this model, please give me some sponsorship and I will continue to create better merges. If there is a device that can fine-tune the model, there will be more new models fine-tuned after the merge (just like solar 10b). merge This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 as a base. The following models were included in the merge: Qwen/QwQ-32B-Preview Qwen/Qwen2.5-Coder-32B-Instruct The following YAML configuration was used to produce this model:

my kofi: https://ko-fi.com/ogodwin10 If you like this model, please give me some sponsorship and I will continue to create better merges. If there is a device that can fine-tune the model, there will be more new models fine-tuned after the merge (just like solar 10b). win10/EVA-QwQ-32B-Preview-Q4KM-GGUF This model was converted to GGUF format from `win10/EVA-QwQ-32B-Preview` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/EVA-Meissa-mini-pro-Q80-GGUF This model was converted to GGUF format from `win10/EVA-Meissa-mini-pro` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

win10/KwaiCoder-AutoThink-preview-Q4KM-GGUF This model was converted to GGUF format from `Kwaipilot/KwaiCoder-AutoThink-preview` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using sthenno-com/miscii-14b-1028 as a base. The following models were included in the merge: arcee-ai/Virtuoso-Small The following YAML configuration was used to produce this model:

This is a merge of pre-trained language models created using mergekit. This model was merged using the passthrough merge method. The following models were included in the merge: F:\text-generation-webui\models\meta-llamaMeta-Llama-3-8B-Instruct The following YAML configuration was used to produce this model:

Breeze-13B-32k-Instruct-v10 is a merge of the following models using mergekit: MediaTek-Research/Breeze-7B-32k-Instruct-v10 MediaTek-Research/Breeze-7B-32k-Instruct-v10 MediaTek-Research/Breeze-7B-32k-Instruct-v10 MediaTek-Research/Breeze-7B-32k-Instruct-v10 MediaTek-Research/Breeze-7B-32k-Instruct-v10 MediaTek-Research/Breeze-7B-32k-Instruct-v10 MediaTek-Research/Breeze-7B-32k-Instruct-v10

This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using E:\tabbyAPI\models\deepseek-aiDeepSeek-V2-Lite as a base. The following models were included in the merge: E:\tabbyAPI\models\deepseek-aiDeepSeek-Coder-V2-Lite-Instruct The following YAML configuration was used to produce this model:

This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1 as a base. The following models were included in the merge: win10/Urdandi-Qwen2.5-7B The following YAML configuration was used to produce this model: