mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-28 00:59:28 -04:00
feat(gallery): add Spark-X2.6 4B variants
Add the publisher Q4_K_M and Q8_0 builds with pinned downloads and
verified SHA256 hashes. Document installation and variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 64d0b3b094, mudler/LocalAI#12821)
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
baba351517
commit
8b0d6c0b4d
2 files changed
+172
No files matched your search
@@ -3,6 +3,84 @@
|
||||
# written by scripts/models/cmd/modelcatalog and stays only so releases before
|
||||
# the cutover keep working. CI fails when it differs from the generated copy:
|
||||
# go run ./scripts/models/cmd/modelcatalog --library gallery/models/index.yaml --out gallery/index.yaml
|
||||
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
name: spark-x2.6-4b-q4
|
||||
description: |
|
||||
Spark-X2.6-4B is XHToken's 4B text model for conversation, reasoning,
|
||||
coding, and multilingual tasks. This build uses Q4_K_M GGUF weights,
|
||||
the embedded Jinja chat template, and a 32K-token default context.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/XHToken/Spark-X2.6-4B
|
||||
- https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- reasoning
|
||||
- coding
|
||||
- multilingual
|
||||
files:
|
||||
- filename: llama-cpp/models/spark-x2.6-4b/Spark-X2.6-4B-Q4_K_M.gguf
|
||||
sha256: 91cb2811aebb47ac916aa619d27d4cdd7f4143106b7917accb8ead4cd7f5cbd9
|
||||
uri: https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF/resolve/fe31f8d64890302cc3a1d365d700357b4b75ba77/Spark-X2.6-4B-Q4_K_M.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/spark-x2.6-4b/Spark-X2.6-4B-Q4_K_M.gguf
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: -1
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
variants:
|
||||
- model: spark-x2.6-4b-q8
|
||||
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
name: spark-x2.6-4b-q8
|
||||
description: |
|
||||
Spark-X2.6-4B is XHToken's 4B text model for conversation, reasoning,
|
||||
coding, and multilingual tasks. This build uses Q8_0 GGUF weights,
|
||||
the embedded Jinja chat template, and a 32K-token default context.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/XHToken/Spark-X2.6-4B
|
||||
- https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- reasoning
|
||||
- coding
|
||||
- multilingual
|
||||
files:
|
||||
- filename: llama-cpp/models/spark-x2.6-4b/Spark-X2.6-4B-Q8_0.gguf
|
||||
sha256: 145c2aa606820663f26ad530b8fc141ed885e2e9ca29f9be7c3bfe8931d58b81
|
||||
uri: https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF/resolve/fe31f8d64890302cc3a1d365d700357b4b75ba77/Spark-X2.6-4B-Q8_0.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/spark-x2.6-4b/Spark-X2.6-4B-Q8_0.gguf
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: -1
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
- url: github:mudler/LocalAI/gallery/qwen3.yaml@master
|
||||
name: qwen3.8-27b-defiance-iq4
|
||||
description: |
|
||||
|
||||
@@ -4,6 +4,100 @@
|
||||
# changes and never edit it by hand. CI fails when it is stale. A build from
|
||||
# master reads it as the default model source; a tagged build reads the gallery
|
||||
# until the release cutover.
|
||||
- kind: model
|
||||
id: spark-x2.6-4b-q4
|
||||
name: spark-x2.6-4b-q4
|
||||
version: 0.0.0-gallery.893c50e4aba3
|
||||
description: |
|
||||
Spark-X2.6-4B is XHToken's 4B text model for conversation, reasoning,
|
||||
coding, and multilingual tasks. This build uses Q4_K_M GGUF weights,
|
||||
the embedded Jinja chat template, and a 32K-token default context.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/XHToken/Spark-X2.6-4B
|
||||
- https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- reasoning
|
||||
- coding
|
||||
- multilingual
|
||||
channel: gallery
|
||||
policy:
|
||||
requireSignature: false
|
||||
schemaVersion: 1
|
||||
model:
|
||||
url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
files:
|
||||
- filename: llama-cpp/models/spark-x2.6-4b/Spark-X2.6-4B-Q4_K_M.gguf
|
||||
sha256: 91cb2811aebb47ac916aa619d27d4cdd7f4143106b7917accb8ead4cd7f5cbd9
|
||||
uri: https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF/resolve/fe31f8d64890302cc3a1d365d700357b4b75ba77/Spark-X2.6-4B-Q4_K_M.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/spark-x2.6-4b/Spark-X2.6-4B-Q4_K_M.gguf
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: -1
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
variants:
|
||||
- model: spark-x2.6-4b-q8
|
||||
- kind: model
|
||||
id: spark-x2.6-4b-q8
|
||||
name: spark-x2.6-4b-q8
|
||||
version: 0.0.0-gallery.dc29344bd04b
|
||||
description: |
|
||||
Spark-X2.6-4B is XHToken's 4B text model for conversation, reasoning,
|
||||
coding, and multilingual tasks. This build uses Q8_0 GGUF weights,
|
||||
the embedded Jinja chat template, and a 32K-token default context.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/XHToken/Spark-X2.6-4B
|
||||
- https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- reasoning
|
||||
- coding
|
||||
- multilingual
|
||||
channel: gallery
|
||||
policy:
|
||||
requireSignature: false
|
||||
schemaVersion: 1
|
||||
model:
|
||||
url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
files:
|
||||
- filename: llama-cpp/models/spark-x2.6-4b/Spark-X2.6-4B-Q8_0.gguf
|
||||
sha256: 145c2aa606820663f26ad530b8fc141ed885e2e9ca29f9be7c3bfe8931d58b81
|
||||
uri: https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF/resolve/fe31f8d64890302cc3a1d365d700357b4b75ba77/Spark-X2.6-4B-Q8_0.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/spark-x2.6-4b/Spark-X2.6-4B-Q8_0.gguf
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: -1
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
- kind: model
|
||||
id: qwen3.8-27b-defiance-iq4
|
||||
name: qwen3.8-27b-defiance-iq4
|
||||
|
||||
Reference in new issue
Block a user