vanilj

Phi-4

Microsoft's Phi 4 model

84.2K Pulls 5 Tags Updated 1 year ago

mistral-nemo-12b-celeste-v1.9

10.6K Pulls 6 Tags Updated 2 years ago

phi-4-unsloth

The Phi 4 model with fixed tokenizer from Unsloth

7,123 Pulls 8 Tags Updated 1 year ago

palmyra-fin-70b-32k

Palmyra-Fin-70B-32K is a model built by Writer specifically to meet the needs of the financial industry. It is a leading LLM on financial benchmarks, outperforming other large language models in various financial tasks and evaluations.

2,951 Pulls 7 Tags Updated 2 years ago

midnight-miqu-70b-v1.5

Midnight-Miqu-70B-v1.5-GGUF Q4_K_S & Q4_K_M

2,752 Pulls 2 Tags Updated 2 years ago

supernova-medius

Arcee-SuperNova-Medius is a 14B parameter language model developed by Arcee.ai, built on the Qwen2.5-14B-Instruct architecture.

tools

2,546 Pulls 22 Tags Updated 2 years ago

hermes-3-llama-3.1-8b

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.

tools

1,263 Pulls 5 Tags Updated 2 years ago

gemma-2-ataraxy-9b

Made from Gemma 2 9B SPPO iter3 and SimPO

932 Pulls 19 Tags Updated 2 years ago

qwen2.5-coder-32b-instruct-iq4_xs

Perfect size for 24GB GPUs!

tools

639 Pulls 1 Tag Updated 1 year ago

llama-3.1-70b-instruct-lorablated-iq2_xs

tools

617 Pulls 1 Tag Updated 2 years ago

llama-3-8b-instruct-coder-v2

Llama-3-8B-Instruct-Coder-v2

604 Pulls 9 Tags Updated 2 years ago

smaug-llama-3-70b-instruct

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

589 Pulls 11 Tags Updated 2 years ago

mistral-nemo-gutenberg-12b-v2

axolotl-ai-co/romulus-mistral-nemo-12b-simpo finetuned on jondurbin/gutenberg-dpo-v0.1

tools

384 Pulls 1 Tag Updated 2 years ago

theia-21b-v1

An upscaled NeMo with half its layers trained

382 Pulls 7 Tags Updated 2 years ago

llama-3.1-instruct-bellman-8b-swedish

This version of bellman is finetuned from llama-3.1-instruct-8b. It's finetuned for prompt question answering, based on a dataset created from Swedish wikipedia, with a lot of Sweden-centric questions.

tools

355 Pulls 3 Tags Updated 2 years ago

reflection-70b-iq2_xxs

Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

353 Pulls 1 Tag Updated 2 years ago

calme-2.4-rys-78b

This model is a fine-tuned version of the dnhkng/RYS-XLarge, pushing the boundaries of natural language understanding and generation even further.

tools

335 Pulls 2 Tags Updated 2 years ago

llama-3-14b-instruct-v1

Self-merge Llama 3 14B Instruct

309 Pulls 2 Tags Updated 2 years ago

llama3.1-70b-iquants

Llama 3.1 70b IQs: IQ1_M, IQ2_M, IQ2_S, IQ2_XS, IQ2_XXS, IQ3_XS, IQ4_XS

tools

285 Pulls 8 Tags Updated 2 years ago

llama-3-8b-instruct-32k-v0.1

Llama 3 8b 32k

272 Pulls 11 Tags Updated 2 years ago

qwq-32b-iq4_xs

IQ4_XS quant of Qwen/QwQ-32B

tools

263 Pulls 4 Tags Updated 1 year ago

qwen2.5-14b-instruct-iq4_xs

Qwen2.5 14B Instruct IQ4_XS

tools

254 Pulls 1 Tag Updated 2 years ago

tess-v2.5-qwen2-72b

Tess-v2.5 (Qwen2-72B) was fine-tuned over the newly released Qwen2-72B base, using the Tess-v2.5 dataset that contain 300K samples spanning multiple topics.

224 Pulls 3 Tags Updated 2 years ago

qwen2.5-32b-instruct_iq4_xs

Qwen2.5 32B Instruct IQ4_XS

tools

220 Pulls 1 Tag Updated 2 years ago

einstein-v6.1-llama3-8b

Weyaxi/Einstein-v6.1-Llama3-8B

156 Pulls 11 Tags Updated 2 years ago

llama-3-peach-instruct-4x8b-moe

This is a experimental 4x8B Llama 3 MoE

147 Pulls 2 Tags Updated 2 years ago

command-r-08-2024-q4_k_m

Command R is a Large Language Model optimized for conversational interaction and long context tasks.

135 Pulls 1 Tag Updated 2 years ago

trinity-2-codestral-22b-v0.2

Trinity is a coding specific Large Language Model series created by Migel Tissera.

98 Pulls 2 Tags Updated 2 years ago

athene-v2-chat-iq3_xs

Athene-V2-Chat-IQ3_XS

tools

98 Pulls 1 Tag Updated 1 year ago

orca-llama-3-8b-instruct

Orca-Llama-3-8B-Instruct-DPO

90 Pulls 2 Tags Updated 2 years ago

mixtral_34bx2_moe_60b

Mixtral_34Bx2_MoE_60B GGUF Q4_K_M

83 Pulls 1 Tag Updated 2 years ago

una-simplesmaug-34b-v1beta

UNA SimpleSmaug 34b v1beta Q4_K_M GGUF

78 Pulls 1 Tag Updated 2 years ago

llama-3-magenta-instruct-4x8b-moe

This is a experimental 4x8B Llama 3 MoE

65 Pulls 1 Tag Updated 2 years ago

cathallama-70b-i1-iq2_s

Perfect for 24GB cards

tools

44 Pulls 1 Tag Updated 2 years ago

qwen2.5-72b-instruct-iq3_xxs

Qwen2.5 is the latest series of Qwen large language models.

tools

40 Pulls 1 Tag Updated 2 years ago

mistral-large-instruct-2407-iq3_xx

tools

37 Pulls 1 Tag Updated 2 years ago

rys-xlarge-iq3_xs

This is a new kind of model optimization. This model is based on MaziyarPanahi/calme-2.1-qwen2-72b, which was tuned from Qwen2-72B.

31 Pulls 1 Tag Updated 2 years ago

Hi. RDson@🤗

Phi-4

mistral-nemo-12b-celeste-v1.9

phi-4-unsloth

palmyra-fin-70b-32k

midnight-miqu-70b-v1.5

supernova-medius

hermes-3-llama-3.1-8b

gemma-2-ataraxy-9b

qwen2.5-coder-32b-instruct-iq4_xs

llama-3.1-70b-instruct-lorablated-iq2_xs

llama-3-8b-instruct-coder-v2

smaug-llama-3-70b-instruct

mistral-nemo-gutenberg-12b-v2

theia-21b-v1

llama-3.1-instruct-bellman-8b-swedish

reflection-70b-iq2_xxs

calme-2.4-rys-78b

llama-3-14b-instruct-v1

llama3.1-70b-iquants

llama-3-8b-instruct-32k-v0.1

qwq-32b-iq4_xs

qwen2.5-14b-instruct-iq4_xs

tess-v2.5-qwen2-72b

qwen2.5-32b-instruct_iq4_xs

einstein-v6.1-llama3-8b

llama-3-peach-instruct-4x8b-moe

command-r-08-2024-q4_k_m

trinity-2-codestral-22b-v0.2

athene-v2-chat-iq3_xs

orca-llama-3-8b-instruct

mixtral_34bx2_moe_60b

una-simplesmaug-34b-v1beta

llama-3-magenta-instruct-4x8b-moe

cathallama-70b-i1-iq2_s

qwen2.5-72b-instruct-iq3_xxs

mistral-large-instruct-2407-iq3_xx

rys-xlarge-iq3_xs