Full-text search
+ 1,000 results
MildlyAggressiveGoose1 / ggml-oasst-sft-6-llama-30B-q4_0
README.md
model
2 matches
eachadea / ggml-gpt4-x-vicuna-13b
README.md
model
2 matches
nomic-ai / ggml-replit-code-v1-3b
README.md
model
2 matches
tags:
license:cc-by-sa-4.0, region:us
5
6
7
8
9
GGML (16bit float) version of Replit V1-3B Code Model.
Original model: https://huggingface.co/replit/replit-code-v1-3b
**Important**: This model binary was created with the original Replit model code before it was refactored to use [MPT configurations](https://huggingface.co/replit/replit-code-v1-3b/commit/e023a8461c7a2e2f2c85e52dbdd8d68b415f95eb).
kujirahand / ggml-gpt-neox-japanese-llm
README.md
model
11 matches
Crataco / AI-Dungeon-2-Classic-GGML
README.md
model
6 matches
nouamanetazi / bloomz-560m-ggml
model
1 matches
Drake-AI / GPT-J-6b-Skein-ggml-q4_1
README.md
model
2 matches
Arjay87 / bloomz_7b1.cpp
README.md
model
1 matches
tags:
ggml, bloom, region:us
6
This model contains a model based on the Bloom architecture with weights compatible with [bloomz.cpp](https://github.com/NouamaneTazi/bloomz.cpp). This model card has been automatically generated [by the bloomz.cpp converter Space](https://huggingface.co/spaces/Wauplin/bloomz.cpp-converter) and must be completed.
ravenscroftj / CodeGen-350M-multi-ggml-quant
README.md
model
3 matches
tags:
ggml, quantized, text-generation, en, license:bsd-3-clause, region:us
10
11
12
13
14
ulti GGML Quantized
This is Salesforce's Codegen 350M multi model ported to ggml and quantized to be executed via [turbopilot](https://github.com/ravenscroftj/turbopilot).
Please refer to the [turbopilot](https://github.com/ravenscroftj/turbopilot) project to learn more about this model.
ravenscroftj / CodeGen-2B-multi-ggml-quant
README.md
model
3 matches
tags:
ggml, quantized, text-generation, en, license:bsd-3-clause, region:us
10
11
12
13
14
ulti GGML Quantized
This is Salesforce's Codegen 2B multi model ported to ggml and quantized to be executed via [turbopilot](https://github.com/ravenscroftj/turbopilot).
Please refer to the [turbopilot](https://github.com/ravenscroftj/turbopilot) project to learn more about this model.
ravenscroftj / CodeGen-6B-multi-ggml-quant
README.md
model
3 matches
tags:
ggml, quantized, text-generation, en, license:bsd-3-clause, region:us
10
11
12
13
14
ulti GGML Quantized
This is Salesforce's Codegen 6B multi model ported to ggml and quantized to be executed via [turbopilot](https://github.com/ravenscroftj/turbopilot).
Please refer to the [turbopilot](https://github.com/ravenscroftj/turbopilot) project to learn more about this model.
mverrilli / dolly-v2-7b-ggml
README.md
model
6 matches
tags:
ggml, en, dataset:databricks/databricks-dolly-15k, license:mit, region:us
9
10
11
cial ggml Dolly-v2-3b models. These are intended to use with the ggml dolly-v2 example: https://github.com/ggerganov/ggml/tree/master/examples/dolly-v2
This requires more testing (both the ggml example and the ggml model conversions), use at your own risk.
mverrilli / dolly-v2-3b-ggml
README.md
model
6 matches
tags:
ggml, en, dataset:databricks/databricks-dolly-15k, license:mit, region:us
9
10
11
cial ggml Dolly-v2-3b models. These are intended to use with the ggml dolly-v2 example: https://github.com/ggerganov/ggml/tree/master/examples/dolly-v2
This requires more testing (both the ggml example and the ggml model conversions), use at your own risk.
mverrilli / dolly-v2-12b-ggml
README.md
model
6 matches
tags:
ggml, en, dataset:databricks/databricks-dolly-15k, license:mit, region:us
9
10
11
cial ggml Dolly-v2-12b models. These are intended to use with the ggml dolly-v2 example: https://github.com/ggerganov/ggml/tree/master/examples/dolly-v2
This requires more testing (both the ggml example and the ggml model conversions), use at your own risk.
rustformers / mpt-7b-ggml
README.md
model
20 matches
tags:
transformers, mpt, llm-rs, ggml, text-generation, en, dataset:mc4, dataset:c4, dataset:togethercomputer/RedPajama-Data-1T, dataset:bigcode/the-stack, dataset:allenai/s2orc, license:apache-2.0, text-generation-inference, region:us
17
18
19
20
21
# GGML converted versions of [Mosaic's](https://huggingface.co/mosaicml) MPT Models
MPT-7B is a decoder-style transformer pretrained from scratch on 1T tokens of English text and code.
This model was trained by [MosaicML](https://www.mosaicml.com).
Crataco / Pygmalion-1.3B-GGML
README.md
model
6 matches
tags:
ggml, text generation, conversational, en, license:agpl-3.0, region:us
16
17
18
19
20
1.3B GGML
### This repository contains quantized conversions of the Pygmalion 1.3B checkpoint.
*For use with frontends that support GGML quantized GPT-NeoX models, such as KoboldCpp and Oobabooga (with the CTransformers loader).*
*Last updated on 2023-09-23.*
Crataco / RWKV-4-PilePlus-Series-GGML
README.md
model
2 matches
tags:
ggml, text-generation, causal-lm, rwkv, en, dataset:EleutherAI/pile, dataset:togethercomputer/RedPajama-Data-1T, license:apache-2.0, region:us
17
18
19
20
21
d to GGML for use with rwkv.cpp and KoboldCpp. [rwkv.cpp's conversion instructions](https://github.com/saharNooby/rwkv.cpp#option-32-convert-and-quantize-pytorch-model) were followed.
### RAM USAGE (KoboldCpp)
Model | RAM usage (with OpenBLAS)
:--:|:--:
rustformers / redpajama-3b-ggml
README.md
model
12 matches
tags:
transformers, llm-rs, ggml, text-generation, en, license:apache-2.0, endpoints_compatible, region:us
10
11
12
13
14
# GGML converted versions of [Together](https://huggingface.co/togethercomputer)'s RedPajama models
## Description
RedPajama-INCITE-Base-3B-v1 was developed by Together and leaders from the open-source AI community including Ontocord.ai, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION.
The training was done on 3,072 V100 GPUs provided as part of the INCITE 2023 project on Scalable Foundation Models for Transferrable Generalist AI, awarded to MILA, LAION, and EleutherAI in fall 2022, with support from the Oak Ridge Leadership Computing Facility (OLCF) and INCITE program.
rustformers / pythia-ggml
README.md
model
21 matches
tags:
transformers, llm-rs, ggml, text-generation, en, license:apache-2.0, endpoints_compatible, region:us
11
12
13
14
15
# GGML converted versions of [EleutherAI](https://huggingface.co/EleutherAI)'s Pythia models
## Description:
The *Pythia Scaling Suite* is a collection of models developed to facilitate
interpretability research. It contains two sets of eight models of sizes