mannix

llama3.1-8b-abliterated

Ablitered v3 llama-3.1 8b with uncensored prompt

tools

12.2K Pulls 38 Tags Updated 3 months ago

llama3-uncensored

llama3-8b with uncensored GuruBot prompt

6,226 Pulls 1 Tag Updated 7 months ago

qwen2-57b

Mixture-of-Experts model 57b

3,662 Pulls 18 Tags Updated 3 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.

3,419 Pulls 16 Tags Updated 6 months ago

llama3.1-8b-lexi

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

tools

2,651 Pulls 45 Tags Updated 3 months ago

llava-phi3

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

vision

1,802 Pulls 4 Tags Updated 6 months ago

gemma2-9b-simpo

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

1,215 Pulls 24 Tags Updated 3 months ago

llama3-8b-ablitered-v3

Ablitered v3 llama-3 8b with uncensored prompt

1,061 Pulls 25 Tags Updated 5 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.

804 Pulls 24 Tags Updated 4 months ago

llamax3-8b-alpaca

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

749 Pulls 16 Tags Updated 4 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.

610 Pulls 23 Tags Updated 3 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.

609 Pulls 2 Tags Updated 7 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.

568 Pulls 20 Tags Updated 5 months ago

qwen2-math-7b

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

491 Pulls 21 Tags Updated 3 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

433 Pulls 13 Tags Updated 3 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

364 Pulls 24 Tags Updated 4 months ago

internlm2.5-20b

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

287 Pulls 14 Tags Updated 3 months ago

hermes-3-llama-3.1-8b

Hermes 3 Llama-3.1 8b Model by NousResearch

tools

280 Pulls 22 Tags Updated 3 months ago

llama3-12b

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

274 Pulls 22 Tags Updated 6 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

263 Pulls 18 Tags Updated 4 months ago

qwen2-7b

Qwen2 is the new series of Qwen large language models

262 Pulls 4 Tags Updated 5 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.

251 Pulls 2 Tags Updated 5 months ago

phi3-mini-4k

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

241 Pulls 19 Tags Updated 4 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.

214 Pulls 10 Tags Updated 5 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.

212 Pulls 22 Tags Updated 5 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

202 Pulls 9 Tags Updated 5 months ago

mixtral_7bx2_moe

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

197 Pulls 11 Tags Updated 7 months ago

llama3-sppo-iter3

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

187 Pulls 21 Tags Updated 5 months ago

llama3.1-70b

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

tools

174 Pulls 34 Tags Updated 3 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

160 Pulls 21 Tags Updated 4 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.

153 Pulls 17 Tags Updated 4 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

141 Pulls 11 Tags Updated 3 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

134 Pulls 4 Tags Updated 5 months ago

deepseek-v2-lite-instruct

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

120 Pulls 8 Tags Updated 5 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)

115 Pulls 13 Tags Updated 7 months ago

llama3-gradient

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

110 Pulls 4 Tags Updated 6 months ago

hermes-3-llama-3.1-70b

Hermes 3 Llama-3.1 70b Model by NousResearch

tools

105 Pulls 22 Tags Updated 3 months ago

smaug-qwen2-72b

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

102 Pulls 21 Tags Updated 4 months ago

qwen2-1.5b

Qwen2 is the new series of Qwen large language models

89 Pulls 4 Tags Updated 5 months ago

qwen2-math-1.5b

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

83 Pulls 7 Tags Updated 3 months ago

llama3.1-8b

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

tools

75 Pulls 41 Tags Updated 3 months ago

nous-hermes2-solar-10.7b

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

66 Pulls 7 Tags Updated 5 months ago

qwen2-0.5b

Qwen2 is the new series of Qwen large language models

59 Pulls 7 Tags Updated 5 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.

52 Pulls 2 Tags Updated 7 months ago

llamax3-8b

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

38 Pulls

phi3-mini-cpo-simpo

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

36 Pulls 16 Tags Updated 4 months ago

discopop-zephyr-7b-gemma

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

35 Pulls 5 Tags Updated 5 months ago

alchemistcoder-7b

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

19 Pulls 3 Tags Updated 5 months ago

llama3-8b-v0.9

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

3 Pulls 2 Tags Updated 5 months ago

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

llama3.1-8b-abliterated

llama3-uncensored

qwen2-57b

defog-llama3-sqlcoder-8b

llama3.1-8b-lexi

llava-phi3

gemma2-9b-simpo

llama3-8b-ablitered-v3

gemma2-9b-sppo-iter3

llamax3-8b-alpaca

deepseek-coder-v2-lite-instruct

dolphin-2.9-llama3-8b

dolphin-2.9.2-qwen2-72b

qwen2-math-7b

llama3.1-storm

gemma2-9b

internlm2.5-20b

hermes-3-llama-3.1-8b

llama3-12b

llama3-groq-tool-8b

qwen2-7b

dolphin-mixtral

phi3-mini-4k

replete-coder-llama3-8b

smaug-llama3-8b

smaug-llama3-70b

mixtral_7bx2_moe

llama3-sppo-iter3

llama3.1-70b

replete-coder-merged-8b

replete-adapted-llama3-8b

gemma2-2b

smaug-llama3-70b-32k

deepseek-v2-lite-instruct

starling-lm-10.7b

llama3-gradient

hermes-3-llama-3.1-70b

smaug-qwen2-72b

qwen2-1.5b

qwen2-math-1.5b

llama3.1-8b

nous-hermes2-solar-10.7b

qwen2-0.5b

wizardlm2

llamax3-8b

phi3-mini-cpo-simpo

discopop-zephyr-7b-gemma

alchemistcoder-7b

llama3-8b-v0.9