mannix

llama3.1-8b-abliterated

Ablitered v3 llama-3.1 8b with uncensored prompt

21.7K Pulls 38 Tags Updated 8 months ago

llama3-uncensored

llama3-8b with uncensored GuruBot prompt

7,339 Pulls 1 Tag Updated 11 months ago

defog-llama3-sqlcoder-8b

A capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models.

4,340 Pulls 16 Tags Updated 11 months ago

llama3.1-8b-lexi

This is an uncensored version of Llama 3.1 8B Instruct with an uncensored prompt.

tools

3,815 Pulls 45 Tags Updated 8 months ago

qwen2-57b

Mixture-of-Experts model 57b

3,792 Pulls 18 Tags Updated 8 months ago

gemma2-9b-simpo

Fine-tuned google/gemma-2-9b-it on princeton-nlp/gemma2-ultrafeedback-armorm with the SimPO objective.

3,332 Pulls 24 Tags Updated 8 months ago

hermes-3-llama-3.1-8b

Hermes 3 Llama-3.1 8b Model by NousResearch

tools

2,451 Pulls 22 Tags Updated 7 months ago

deepseek-coder-v2-lite-instruct

An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

1,929 Pulls 23 Tags Updated 7 months ago

llava-phi3

A new small LLaVA model fine-tuned from Phi 3 Mini [I-Quants]

vision

1,881 Pulls 4 Tags Updated 10 months ago

llama3-8b-ablitered-v3

Ablitered v3 llama-3 8b with uncensored prompt

1,807 Pulls 25 Tags Updated 9 months ago

llamax3-8b-alpaca

LLaMAX is a multilingual language model, developed through continued pre-training on Llama3, and supports over 100 languages

1,425 Pulls 16 Tags Updated 8 months ago

dolphin-2.9-llama3-8b

The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.9 with llama 3.

1,066 Pulls 2 Tags Updated 11 months ago

qwq-32b-abilterated

QwQ is an experimental research model focused on advancing AI reasoning capabilities. Abliterated with uncensored prompt, i-matrix quants.

tools

1,021 Pulls 17 Tags Updated 3 months ago

dolphin-2.9.2-qwen2-72b

This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling. Dolphin is uncensored.

953 Pulls 20 Tags Updated 9 months ago

gemma2-9b-sppo-iter3

This model was developed using Self-Play Preference Optimization at iteration 3, based on the google/gemma-2-9b-it architecture as starting point.

928 Pulls 24 Tags Updated 8 months ago

qwen2.5-coder

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. I-Quant models.

tools

568 Pulls 47 Tags Updated 3 months ago

qwen2-math-7b

Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs

544 Pulls 21 Tags Updated 8 months ago

llama3.1-storm

Llama-3.1-Storm-8B outperforms both Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B!

tools

508 Pulls 13 Tags Updated 7 months ago

gemma2-9b

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models

488 Pulls 24 Tags Updated 8 months ago

phi3-mini-4k

Phi-3 Mini is a lightweight 3B state-of-the-art open models by Microsoft. Updated in July 2024.

447 Pulls 19 Tags Updated 9 months ago

llama3-groq-tool-8b

A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.

tools

405 Pulls 18 Tags Updated 8 months ago

internlm2.5-20b

InternLM2.5 has open-sourced a 20 billion parameter base model and a chat model tailored for practical scenarios.

399 Pulls 14 Tags Updated 8 months ago

qwq-32b

QwQ is an experimental research model focused on advancing AI reasoning capabilities. i-matrix quantizations.

tools

330 Pulls 23 Tags Updated 3 months ago

llama3-12b

Meta-Llama-3-12B-Instruct is a depth upscaling merge of llama3-8b from M. Labonne

330 Pulls 22 Tags Updated 10 months ago

smallthinker-abliterated

A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model. I-Quants models, abliterated with uncensored prompt.

309 Pulls 15 Tags Updated 3 months ago

dolphin-mixtral

Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.

298 Pulls 2 Tags Updated 10 months ago

smaug-llama3-8b

This model was built using the Smaug recipe for improving performance on real world multi-turn conversations applied to meta-llama/Meta-Llama-3-8B-Instruct.

289 Pulls 22 Tags Updated 9 months ago

qwen2-7b

Qwen2 is the new series of Qwen large language models

272 Pulls 4 Tags Updated 10 months ago

replete-coder-llama3-8b

Replete-Coder-llama3-8b is a general purpose model that is specially trained in coding in over 100 coding languages.

265 Pulls 10 Tags Updated 9 months ago

mixtral_7bx2_moe

A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI.

261 Pulls 11 Tags Updated 12 months ago

smaug-llama3-70b

This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to Meta-Llama-3-70B-Instruct

243 Pulls 9 Tags Updated 10 months ago

llama3-sppo-iter3

Meta Llama-3-8b with Self-Play Preference Optimization for Language Model Alignment at iteration 3

231 Pulls 21 Tags Updated 9 months ago

smaug-llama3-70b-32k

This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to Meta-Llama-3-70B-Instruct, 32k context length

217 Pulls 4 Tags Updated 9 months ago

llama3.1-70b

New state-of-the-art model from Meta available in 8B, 70B and 405B sizes

tools

211 Pulls 34 Tags Updated 8 months ago

deepseek-v2-lite-instruct

A strong, economical, and efficient Mixture-of-Experts language model.

201 Pulls 8 Tags Updated 9 months ago

replete-coder-merged-8b

Replete-Coder-Merged-8b is a general purpose model that is specially trained in coding in over 100 coding languages

183 Pulls 21 Tags Updated 9 months ago

gemma2-2b

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models

179 Pulls 11 Tags Updated 8 months ago

replete-adapted-llama3-8b

Replete-Adapted-llama3-8b is a general purpose model that is specially trained in coding in over 100 coding languages.

171 Pulls 17 Tags Updated 9 months ago

starling-lm-10.7b

Starling-LM-10.7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF)

151 Pulls 13 Tags Updated 12 months ago

smaug-qwen2-72b

The latest in the Smaug series - a finetune of Qwen2-72B-Instruct

151 Pulls 21 Tags Updated 9 months ago

llama3-gradient

This model extends LLama-3 70B's context length from 8k to over 1m tokens. [I-Quants]

151 Pulls 4 Tags Updated 10 months ago

hermes-3-llama-3.1-70b

Hermes 3 Llama-3.1 70b Model by NousResearch

tools

129 Pulls 22 Tags Updated 7 months ago

llama-3.3

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model. I-Quants models.

tools

123 Pulls 9 Tags Updated 3 months ago

qwen2-1.5b

Qwen2 is the new series of Qwen large language models

112 Pulls 4 Tags Updated 10 months ago

eurus-2-7b-prime

Eurus-2-7B-PRIME is trained using PRIME (Process Reinforcement through IMplicit rEward) method, an open-source solution for online reinforcement learning (RL) with process rewards, to advance reasoning abilities of language models.

110 Pulls 23 Tags Updated 3 months ago

llama3.1-8b

New state-of-the-art model from Meta available in 8B, 70B and 405B sizes.

tools

108 Pulls 41 Tags Updated 8 months ago

qwen2-math-1.5b

Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs

92 Pulls 7 Tags Updated 8 months ago

nous-hermes2-solar-10.7b

The powerful Solar based model by Nous Research that excels at scientific discussion and coding tasks.

75 Pulls 7 Tags Updated 10 months ago

smallthinker

A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model. I-Quants models.

75 Pulls 14 Tags Updated 3 months ago

wizardlm2

State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases. More quantizations.

74 Pulls 2 Tags Updated 11 months ago

qwen2-0.5b

Qwen2 is the new series of Qwen large language models

72 Pulls 7 Tags Updated 10 months ago

phi3-mini-cpo-simpo

Phi-3-mini-4K-instruct with CPO-SimPO

56 Pulls 16 Tags Updated 9 months ago

discopop-zephyr-7b-gemma

A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets using DiscoPOP

45 Pulls 5 Tags Updated 10 months ago

llamax3-8b

LLaMAX is a multilingual language model, developed through continued pre-training on Llama3, and supports over 100 languages.

38 Pulls

alchemistcoder-7b

AlchemistCoder is a series of coding models by InternLM. Tuned from Llama 2.

21 Pulls 3 Tags Updated 10 months ago

llama3-8b-v0.9

MaziyarPanahi/Llama-3-8B-Instruct-v0.9

3 Pulls 2 Tags Updated 10 months ago

Crazy Overclocker, Amateur Coder, AI Pragmatist, Non-sense Lover

llama3.1-8b-abliterated

llama3-uncensored

defog-llama3-sqlcoder-8b

llama3.1-8b-lexi

qwen2-57b

gemma2-9b-simpo

hermes-3-llama-3.1-8b

deepseek-coder-v2-lite-instruct

llava-phi3

llama3-8b-ablitered-v3

llamax3-8b-alpaca

dolphin-2.9-llama3-8b

qwq-32b-abilterated

dolphin-2.9.2-qwen2-72b

gemma2-9b-sppo-iter3

qwen2.5-coder

qwen2-math-7b

llama3.1-storm

gemma2-9b

phi3-mini-4k

llama3-groq-tool-8b

internlm2.5-20b

qwq-32b

llama3-12b

smallthinker-abliterated

dolphin-mixtral

smaug-llama3-8b

qwen2-7b

replete-coder-llama3-8b

mixtral_7bx2_moe

smaug-llama3-70b

llama3-sppo-iter3

smaug-llama3-70b-32k

llama3.1-70b

deepseek-v2-lite-instruct

replete-coder-merged-8b

gemma2-2b

replete-adapted-llama3-8b

starling-lm-10.7b

smaug-qwen2-72b

llama3-gradient

hermes-3-llama-3.1-70b

llama-3.3

qwen2-1.5b

eurus-2-7b-prime

llama3.1-8b

qwen2-math-1.5b

nous-hermes2-solar-10.7b

smallthinker

wizardlm2

qwen2-0.5b

phi3-mini-cpo-simpo

discopop-zephyr-7b-gemma

llamax3-8b

alchemistcoder-7b

llama3-8b-v0.9