fuzzy-mittenz
commited on
Commit
•
0333b05
1
Parent(s):
555ccf5
Update README.md
Browse files
README.md
CHANGED
@@ -10,47 +10,7 @@ tags:
|
|
10 |
- llama-cpp
|
11 |
- gguf-my-repo
|
12 |
---
|
13 |
-
|
14 |
-
# fuzzy-mittenz/
|
15 |
-
This model was converted to GGUF format from [`jeffmeloy/Qwen2.5-7B-olm-v1.0`](https://huggingface.co/jeffmeloy/Qwen2.5-7B-olm-v1.0)
|
16 |
-
Refer to the [original model card](https://huggingface.co/jeffmeloy/Qwen2.5-7B-olm-v1.0) for more details on the model.
|
17 |
-
|
18 |
## Use with llama.cpp
|
19 |
-
Install llama.cpp through brew (works on Mac and Linux)
|
20 |
-
|
21 |
-
```bash
|
22 |
-
brew install llama.cpp
|
23 |
-
|
24 |
-
```
|
25 |
-
Invoke the llama.cpp server or the CLI.
|
26 |
-
|
27 |
-
### CLI:
|
28 |
-
```bash
|
29 |
-
llama-cli --hf-repo fuzzy-mittenz/Qwen2.5-7B-olm-v1.0-IQ4_NL-GGUF --hf-file qwen2.5-7b-olm-v1.0-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
|
30 |
-
```
|
31 |
-
|
32 |
-
### Server:
|
33 |
-
```bash
|
34 |
-
llama-server --hf-repo fuzzy-mittenz/Qwen2.5-7B-olm-v1.0-IQ4_NL-GGUF --hf-file qwen2.5-7b-olm-v1.0-iq4_nl-imat.gguf -c 2048
|
35 |
-
```
|
36 |
-
|
37 |
-
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.
|
38 |
-
|
39 |
-
Step 1: Clone llama.cpp from GitHub.
|
40 |
-
```
|
41 |
-
git clone https://github.com/ggerganov/llama.cpp
|
42 |
-
```
|
43 |
-
|
44 |
-
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
|
45 |
-
```
|
46 |
-
cd llama.cpp && LLAMA_CURL=1 make
|
47 |
-
```
|
48 |
-
|
49 |
-
Step 3: Run inference through the main binary.
|
50 |
-
```
|
51 |
-
./llama-cli --hf-repo fuzzy-mittenz/Qwen2.5-7B-olm-v1.0-IQ4_NL-GGUF --hf-file qwen2.5-7b-olm-v1.0-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
|
52 |
-
```
|
53 |
-
or
|
54 |
-
```
|
55 |
-
./llama-server --hf-repo fuzzy-mittenz/Qwen2.5-7B-olm-v1.0-IQ4_NL-GGUF --hf-file qwen2.5-7b-olm-v1.0-iq4_nl-imat.gguf -c 2048
|
56 |
-
```
|
|
|
10 |
- llama-cpp
|
11 |
- gguf-my-repo
|
12 |
---
|
13 |
+
QAT model trained with THE KEY dataset not yet tested, 3rd times the charm. !!!TEST!!! please give input as I'm not sure if his model's function will transfer
|
14 |
+
# fuzzy-mittenz/OLM_Wareding-JMeloy-Mittens-Qwn-Q4_NL.GGUF
|
15 |
+
This model was converted to GGUF format from [`jeffmeloy/Qwen2.5-7B-olm-v1.0`](https://huggingface.co/jeffmeloy/Qwen2.5-7B-olm-v1.0)
|
|
|
|
|
16 |
## Use with llama.cpp
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|