Transfer owner
Browse files
README.md
CHANGED
|
@@ -5952,7 +5952,7 @@ model-index:
|
|
| 5952 |
value: 78.62997658079624
|
| 5953 |
---
|
| 5954 |
|
| 5955 |
-
#
|
| 5956 |
This model was converted to GGUF format from [`intfloat/multilingual-e5-large`](https://huggingface.co/intfloat/multilingual-e5-large) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 5957 |
Refer to the [original model card](https://huggingface.co/intfloat/multilingual-e5-large) for more details on the model.
|
| 5958 |
|
|
@@ -5967,12 +5967,12 @@ Invoke the llama.cpp server or the CLI.
|
|
| 5967 |
|
| 5968 |
### CLI:
|
| 5969 |
```bash
|
| 5970 |
-
llama-cli --hf-repo
|
| 5971 |
```
|
| 5972 |
|
| 5973 |
### Server:
|
| 5974 |
```bash
|
| 5975 |
-
llama-server --hf-repo
|
| 5976 |
```
|
| 5977 |
|
| 5978 |
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.
|
|
@@ -5989,9 +5989,9 @@ cd llama.cpp && LLAMA_CURL=1 make
|
|
| 5989 |
|
| 5990 |
Step 3: Run inference through the main binary.
|
| 5991 |
```
|
| 5992 |
-
./llama-cli --hf-repo
|
| 5993 |
```
|
| 5994 |
or
|
| 5995 |
```
|
| 5996 |
-
./llama-server --hf-repo
|
| 5997 |
```
|
|
|
|
| 5952 |
value: 78.62997658079624
|
| 5953 |
---
|
| 5954 |
|
| 5955 |
+
# groonga/multilingual-e5-large-Q4_K_M-GGUF
|
| 5956 |
This model was converted to GGUF format from [`intfloat/multilingual-e5-large`](https://huggingface.co/intfloat/multilingual-e5-large) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 5957 |
Refer to the [original model card](https://huggingface.co/intfloat/multilingual-e5-large) for more details on the model.
|
| 5958 |
|
|
|
|
| 5967 |
|
| 5968 |
### CLI:
|
| 5969 |
```bash
|
| 5970 |
+
llama-cli --hf-repo groonga/multilingual-e5-large-Q4_K_M-GGUF --hf-file multilingual-e5-large-q4_k_m.gguf -p "The meaning to life and the universe is"
|
| 5971 |
```
|
| 5972 |
|
| 5973 |
### Server:
|
| 5974 |
```bash
|
| 5975 |
+
llama-server --hf-repo groonga/multilingual-e5-large-Q4_K_M-GGUF --hf-file multilingual-e5-large-q4_k_m.gguf -c 2048
|
| 5976 |
```
|
| 5977 |
|
| 5978 |
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.
|
|
|
|
| 5989 |
|
| 5990 |
Step 3: Run inference through the main binary.
|
| 5991 |
```
|
| 5992 |
+
./llama-cli --hf-repo groonga/multilingual-e5-large-Q4_K_M-GGUF --hf-file multilingual-e5-large-q4_k_m.gguf -p "The meaning to life and the universe is"
|
| 5993 |
```
|
| 5994 |
or
|
| 5995 |
```
|
| 5996 |
+
./llama-server --hf-repo groonga/multilingual-e5-large-Q4_K_M-GGUF --hf-file multilingual-e5-large-q4_k_m.gguf -c 2048
|
| 5997 |
```
|