Update README.md
Browse files
README.md
CHANGED
@@ -12,6 +12,34 @@ base_model: DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B
|
|
12 |
This model was converted to GGUF format from [`DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B`](https://huggingface.co/DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
13 |
Refer to the [original model card](https://huggingface.co/DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B) for more details on the model.
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
## Use with llama.cpp
|
16 |
Install llama.cpp through brew (works on Mac and Linux)
|
17 |
|
|
|
12 |
This model was converted to GGUF format from [`DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B`](https://huggingface.co/DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
13 |
Refer to the [original model card](https://huggingface.co/DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B) for more details on the model.
|
14 |
|
15 |
+
---
|
16 |
+
DeepSeek Blackroot is a Deepseek model with "Distilled" components of "thinking/reasoning" fused into it.
|
17 |
+
|
18 |
+
|
19 |
+
This model is a Llama fine tune, has a dark bias, and can be used for creative and non-creative use.
|
20 |
+
|
21 |
+
|
22 |
+
This is a very stable model, which can operate at temps 1+ 2+ and
|
23 |
+
higher and generate coherent thought(s) and exceeds the original distill
|
24 |
+
model (by Deepseek) in terms of performance, coherence and depth of
|
25 |
+
thought.
|
26 |
+
|
27 |
+
|
28 |
+
This is Deepseek Distill version is based on this model by "Hastagaras":
|
29 |
+
|
30 |
+
|
31 |
+
[ https://huggingface.co/Hastagaras/Jamet-8B-L3-MK.V-Blackroot ]
|
32 |
+
|
33 |
+
|
34 |
+
with the actual "DeepSeek" thinking / reasoning tech built (grafted in directly, by DavidAU) into it.
|
35 |
+
|
36 |
+
|
37 |
+
The "thinking/reasoning" tech (for the model at this repo) is from the original Llama 3.1 "Distill" model from Deepseek:
|
38 |
+
|
39 |
+
|
40 |
+
[ https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B ]
|
41 |
+
|
42 |
+
---
|
43 |
## Use with llama.cpp
|
44 |
Install llama.cpp through brew (works on Mac and Linux)
|
45 |
|