MotherEarth
commited on
Commit
•
b91abb7
1
Parent(s):
30437cc
Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model: MotherEarth/
|
3 |
library_name: transformers
|
4 |
tags:
|
5 |
- mergekit
|
@@ -20,9 +20,9 @@ tags:
|
|
20 |
- proverbs
|
21 |
---
|
22 |
|
23 |
-
# MotherEarth/
|
24 |
-
This model was converted to GGUF format from [`MotherEarth/MotherEarth_1.
|
25 |
-
Refer to the [original model card](https://huggingface.co/MotherEarth/MotherEarth_1.
|
26 |
|
27 |
|
28 |
NEEDS still a system prompt
|
@@ -124,12 +124,12 @@ Invoke the llama.cpp server or the CLI.
|
|
124 |
|
125 |
### CLI:
|
126 |
```bash
|
127 |
-
llama-cli --hf-repo MotherEarth/MotherEarth_1.
|
128 |
```
|
129 |
|
130 |
### Server:
|
131 |
```bash
|
132 |
-
llama-server --hf-repo MotherEarth/MotherEarth_1.
|
133 |
```
|
134 |
|
135 |
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
|
@@ -146,9 +146,9 @@ cd llama.cpp && LLAMA_CURL=1 make
|
|
146 |
|
147 |
Step 3: Run inference through the main binary.
|
148 |
```
|
149 |
-
./llama-cli --hf-repo MotherEarth/MotherEarth_1.
|
150 |
```
|
151 |
or
|
152 |
```
|
153 |
-
./llama-server --hf-repo MotherEarth/MotherEarth_1.
|
154 |
```
|
|
|
1 |
---
|
2 |
+
base_model: MotherEarth/MotherEarth-1.1-8B
|
3 |
library_name: transformers
|
4 |
tags:
|
5 |
- mergekit
|
|
|
20 |
- proverbs
|
21 |
---
|
22 |
|
23 |
+
# MotherEarth/MotherEarth-1.1-GGUF
|
24 |
+
This model was converted to GGUF format from [`MotherEarth/MotherEarth_1.1`](https://huggingface.co/MotherEarth/MotherEarth_1.1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
25 |
+
Refer to the [original model card](https://huggingface.co/MotherEarth/MotherEarth_1.1) for more details on the model.
|
26 |
|
27 |
|
28 |
NEEDS still a system prompt
|
|
|
124 |
|
125 |
### CLI:
|
126 |
```bash
|
127 |
+
llama-cli --hf-repo MotherEarth/MotherEarth_1.1-Q4_K_M-GGUF --hf-file motherearth_1.1-q4_k_m.gguf -p "The meaning to life and the universe is"
|
128 |
```
|
129 |
|
130 |
### Server:
|
131 |
```bash
|
132 |
+
llama-server --hf-repo MotherEarth/MotherEarth_1.1-Q4_K_M-GGUF --hf-file motherearth_1.1-q4_k_m.gguf -c 2048
|
133 |
```
|
134 |
|
135 |
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
|
|
|
146 |
|
147 |
Step 3: Run inference through the main binary.
|
148 |
```
|
149 |
+
./llama-cli --hf-repo MotherEarth/MotherEarth_1.1-Q4_K_M-GGUF --hf-file motherearth_1.1-q4_k_m.gguf -p "The meaning to life and the universe is"
|
150 |
```
|
151 |
or
|
152 |
```
|
153 |
+
./llama-server --hf-repo MotherEarth/MotherEarth_1.1-Q4_K_M-GGUF --hf-file motherearth_1.1-q4_k_m.gguf -c 2048
|
154 |
```
|