mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-28 09:08:54 -04:00
feat(gallery): add Hy-Memory 30B A3B variants
Add official Q4_K_M and Q8_0 builds for memory-writing workflows.
Use the embedded template with no-think mode and pinned downloads.
Document installation and variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit a1259642c5, mudler/LocalAI#12851)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
localai-org-maint-bot authored and Ettore Di Giacinto committed
1 parent
c08e37f55d
commit
d747cf0798
2 files changed
+184
No files matched your search
@@ -79941,3 +79941,87 @@
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
name: hy-memory-30b-a3b-q4
|
||||
description: |
|
||||
Tencent Hy-Memory is a 30B MoE model with about 3B active parameters
|
||||
for writing and updating long-term memory in external agent frameworks.
|
||||
This Q4_K_M build uses llama.cpp with the embedded chat template and
|
||||
no-think mode. It supports English and Chinese; the memory framework
|
||||
must supply the task prompts and persistent storage.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/tencent/Hy-Memory-30B-A3B
|
||||
- https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- memory
|
||||
- english
|
||||
- chinese
|
||||
files:
|
||||
- filename: Hy-Memory-30B-A3B-Q4_K_M.gguf
|
||||
sha256: e417fc86d0a2bb058ed253028f4617d144aa874b8af35711cca0c7009bd63446
|
||||
uri: https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF/resolve/38e10a37701e1caff4a6dc3831448aaf8c2e15d1/Hy-Memory-30B-A3B-Q4_K_M.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
chat_template_kwargs:
|
||||
reasoning_effort: no_think
|
||||
context_size: 8192
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: Hy-Memory-30B-A3B-Q4_K_M.gguf
|
||||
repeat_penalty: 1.0
|
||||
temperature: 0.7
|
||||
top_k: 0
|
||||
top_p: 1.0
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
variants:
|
||||
- model: hy-memory-30b-a3b-q8
|
||||
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
name: hy-memory-30b-a3b-q8
|
||||
description: |
|
||||
Tencent Hy-Memory is a 30B MoE model with about 3B active parameters
|
||||
for writing and updating long-term memory in external agent frameworks.
|
||||
This Q8_0 build uses llama.cpp with the embedded chat template and
|
||||
no-think mode. It supports English and Chinese; the memory framework
|
||||
must supply the task prompts and persistent storage.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/tencent/Hy-Memory-30B-A3B
|
||||
- https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- memory
|
||||
- english
|
||||
- chinese
|
||||
files:
|
||||
- filename: Hy-Memory-30B-A3B-Q8_0.gguf
|
||||
sha256: 3ba2897dbb7e21e618cb65cec4b31498e59eca2960b381c5e0a0590e7ce8526b
|
||||
uri: https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF/resolve/38e10a37701e1caff4a6dc3831448aaf8c2e15d1/Hy-Memory-30B-A3B-Q8_0.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
chat_template_kwargs:
|
||||
reasoning_effort: no_think
|
||||
context_size: 8192
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: Hy-Memory-30B-A3B-Q8_0.gguf
|
||||
repeat_penalty: 1.0
|
||||
temperature: 0.7
|
||||
top_k: 0
|
||||
top_p: 1.0
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
@@ -98170,3 +98170,103 @@
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
- kind: model
|
||||
id: hy-memory-30b-a3b-q4
|
||||
name: hy-memory-30b-a3b-q4
|
||||
version: 0.0.0-gallery.9e00023fd8c5
|
||||
description: |
|
||||
Tencent Hy-Memory is a 30B MoE model with about 3B active parameters
|
||||
for writing and updating long-term memory in external agent frameworks.
|
||||
This Q4_K_M build uses llama.cpp with the embedded chat template and
|
||||
no-think mode. It supports English and Chinese; the memory framework
|
||||
must supply the task prompts and persistent storage.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/tencent/Hy-Memory-30B-A3B
|
||||
- https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- memory
|
||||
- english
|
||||
- chinese
|
||||
channel: gallery
|
||||
policy:
|
||||
requireSignature: false
|
||||
schemaVersion: 1
|
||||
model:
|
||||
url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
files:
|
||||
- filename: Hy-Memory-30B-A3B-Q4_K_M.gguf
|
||||
sha256: e417fc86d0a2bb058ed253028f4617d144aa874b8af35711cca0c7009bd63446
|
||||
uri: https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF/resolve/38e10a37701e1caff4a6dc3831448aaf8c2e15d1/Hy-Memory-30B-A3B-Q4_K_M.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
chat_template_kwargs:
|
||||
reasoning_effort: no_think
|
||||
context_size: 8192
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: Hy-Memory-30B-A3B-Q4_K_M.gguf
|
||||
repeat_penalty: 1.0
|
||||
temperature: 0.7
|
||||
top_k: 0
|
||||
top_p: 1.0
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
variants:
|
||||
- model: hy-memory-30b-a3b-q8
|
||||
- kind: model
|
||||
id: hy-memory-30b-a3b-q8
|
||||
name: hy-memory-30b-a3b-q8
|
||||
version: 0.0.0-gallery.1da8190960d9
|
||||
description: |
|
||||
Tencent Hy-Memory is a 30B MoE model with about 3B active parameters
|
||||
for writing and updating long-term memory in external agent frameworks.
|
||||
This Q8_0 build uses llama.cpp with the embedded chat template and
|
||||
no-think mode. It supports English and Chinese; the memory framework
|
||||
must supply the task prompts and persistent storage.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/tencent/Hy-Memory-30B-A3B
|
||||
- https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- memory
|
||||
- english
|
||||
- chinese
|
||||
channel: gallery
|
||||
policy:
|
||||
requireSignature: false
|
||||
schemaVersion: 1
|
||||
model:
|
||||
url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
files:
|
||||
- filename: Hy-Memory-30B-A3B-Q8_0.gguf
|
||||
sha256: 3ba2897dbb7e21e618cb65cec4b31498e59eca2960b381c5e0a0590e7ce8526b
|
||||
uri: https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF/resolve/38e10a37701e1caff4a6dc3831448aaf8c2e15d1/Hy-Memory-30B-A3B-Q8_0.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
chat_template_kwargs:
|
||||
reasoning_effort: no_think
|
||||
context_size: 8192
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: Hy-Memory-30B-A3B-Q8_0.gguf
|
||||
repeat_penalty: 1.0
|
||||
temperature: 0.7
|
||||
top_k: 0
|
||||
top_p: 1.0
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
Reference in new issue
Block a user