models(gallery): add llm-compiler (#2684)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-06-29 23:32:01 +02:00 committed by GitHub
parent 6a2a10603c
commit 6acba2bcbe
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -2689,6 +2689,69 @@
- filename: "Codestral-22B-v0.1-Q4_K_M.gguf"
uri: "huggingface://bartowski/Codestral-22B-v0.1-GGUF/Codestral-22B-v0.1-Q4_K_M.gguf"
sha256: 003e48ed892850b80994fcddca2bd6b833b092a4ef2db2853c33a3144245e06c
- &llm-compiler
url: "github:mudler/LocalAI/gallery/codellama.yaml@master"
name: "llm-compiler-13b-imat"
license: other
description: |
LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning.
LLM Compiler is free for both research and commercial use.
LLM Compiler is available in two flavors:
LLM Compiler, the foundational models, pretrained on over 500B tokens of LLVM-IR, x86_84, ARM, and CUDA assembly codes and trained to predict the effect of LLVM optimizations;
and LLM Compiler FTD, which is further fine-tuned to predict the best optimizations for code in LLVM assembly to reduce code size, and to disassemble assembly code to LLVM-IR.
urls:
- https://huggingface.co/legraphista/llm-compiler-13b-IMat-GGUF
- https://huggingface.co/facebook/llm-compiler-13b
tags:
- llm
- gguf
- gpu
- code
- cpu
overrides:
parameters:
model: llm-compiler-13b.Q4_K.gguf
files:
- filename: "llm-compiler-13b.Q4_K.gguf"
uri: "huggingface://legraphista/llm-compiler-13b-IMat-GGUF/llm-compiler-13b.Q4_K.gguf"
sha256: dad41a121d0d67432c289aba8ffffc93159e2b24ca3d1c62e118c9f4cbf0c890
- !!merge <<: *llm-compiler
name: "llm-compiler-13b-ftd"
urls:
- https://huggingface.co/QuantFactory/llm-compiler-13b-ftd-GGUF
- https://huggingface.co/facebook/llm-compiler-13b-ftd
overrides:
parameters:
model: llm-compiler-13b-ftd.Q4_K_M.gguf
files:
- filename: "llm-compiler-13b-ftd.Q4_K_M.gguf"
uri: "huggingface://QuantFactory/llm-compiler-13b-ftd-GGUF/llm-compiler-13b-ftd.Q4_K_M.gguf"
sha256: a5d19ae6b3fbe6724784363161b66cd2c8d8a3905761c0fb08245b3c03697db1
- !!merge <<: *llm-compiler
name: "llm-compiler-7b-imat-GGUF"
urls:
- https://huggingface.co/legraphista/llm-compiler-7b-IMat-GGUF
- https://huggingface.co/facebook/llm-compiler-7b
overrides:
parameters:
model: llm-compiler-7b.Q4_K.gguf
files:
- filename: "llm-compiler-7b.Q4_K.gguf"
uri: "huggingface://legraphista/llm-compiler-7b-IMat-GGUF/llm-compiler-7b.Q4_K.gguf"
sha256: 84926979701fa4591ff5ede94a6c5829a62efa620590e5815af984707d446926
- !!merge <<: *llm-compiler
name: "llm-compiler-7b-ftd-imat"
urls:
- https://huggingface.co/legraphista/llm-compiler-7b-ftd-IMat-GGUF
- https://huggingface.co/facebook/llm-compiler-7b-ftd
overrides:
parameters:
model: llm-compiler-7b-ftd.Q4_K.gguf
files:
- filename: "llm-compiler-7b-ftd.Q4_K.gguf"
uri: "huggingface://legraphista/llm-compiler-7b-ftd-IMat-GGUF/llm-compiler-7b-ftd.Q4_K.gguf"
sha256: d862dd18ed335413787d0ad196522a9902a3c10a6456afdab8721822cb0ddde8
- &openvino
### START OpenVINO
url: "github:mudler/LocalAI/gallery/openvino.yaml@master"