Initial GGML model commit
Browse files
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
inference: false
|
3 |
license: other
|
4 |
-
model_creator:
|
5 |
model_link: https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
|
6 |
model_name: Chronos Beluga v2 13B
|
7 |
model_type: llama
|
@@ -23,12 +23,12 @@ quantized_by: TheBloke
|
|
23 |
<!-- header end -->
|
24 |
|
25 |
# Chronos Beluga v2 13B - GGML
|
26 |
-
- Model creator: [
|
27 |
- Original model: [Chronos Beluga v2 13B](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16)
|
28 |
|
29 |
## Description
|
30 |
|
31 |
-
This repo contains GGML format model files for [
|
32 |
|
33 |
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
|
34 |
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
|
@@ -42,7 +42,7 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
42 |
|
43 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GPTQ)
|
44 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML)
|
45 |
-
* [
|
46 |
|
47 |
## Prompt template: Alpaca
|
48 |
|
@@ -149,7 +149,7 @@ Thank you to all my generous patrons and donaters!
|
|
149 |
|
150 |
<!-- footer end -->
|
151 |
|
152 |
-
# Original model card:
|
153 |
|
154 |
merged 58% chronos v2 42% beluga 13b merge using LUNK(Large universal neural kombiner)
|
155 |
|
|
|
1 |
---
|
2 |
inference: false
|
3 |
license: other
|
4 |
+
model_creator: Caleb Morgan
|
5 |
model_link: https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
|
6 |
model_name: Chronos Beluga v2 13B
|
7 |
model_type: llama
|
|
|
23 |
<!-- header end -->
|
24 |
|
25 |
# Chronos Beluga v2 13B - GGML
|
26 |
+
- Model creator: [Caleb Morgan](https://huggingface.co/The-Face-Of-Goonery)
|
27 |
- Original model: [Chronos Beluga v2 13B](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16)
|
28 |
|
29 |
## Description
|
30 |
|
31 |
+
This repo contains GGML format model files for [Caleb Morgan's Chronos Beluga v2 13B](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16).
|
32 |
|
33 |
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
|
34 |
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
|
|
|
42 |
|
43 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GPTQ)
|
44 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML)
|
45 |
+
* [Caleb Morgan's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16)
|
46 |
|
47 |
## Prompt template: Alpaca
|
48 |
|
|
|
149 |
|
150 |
<!-- footer end -->
|
151 |
|
152 |
+
# Original model card: Caleb Morgan's Chronos Beluga v2 13B
|
153 |
|
154 |
merged 58% chronos v2 42% beluga 13b merge using LUNK(Large universal neural kombiner)
|
155 |
|