mohanz commited on
Commit
f245569
·
verified ·
1 Parent(s): fa6b7f8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -45
README.md CHANGED
@@ -1,52 +1,8 @@
1
  ---
2
  license: mit
3
- library_name: transformers
4
- tags:
5
- - llama-cpp
6
- - gguf-my-repo
7
  base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
8
  ---
9
 
10
- # mohanz/DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL-GGUF
11
  This model was converted to GGUF format from [`deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
12
  Refer to the [original model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) for more details on the model.
13
-
14
- ## Use with llama.cpp
15
- Install llama.cpp through brew (works on Mac and Linux)
16
-
17
- ```bash
18
- brew install llama.cpp
19
-
20
- ```
21
- Invoke the llama.cpp server or the CLI.
22
-
23
- ### CLI:
24
- ```bash
25
- llama-cli --hf-repo mohanz/DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL-GGUF --hf-file deepseek-r1-distill-qwen-1.5b-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
26
- ```
27
-
28
- ### Server:
29
- ```bash
30
- llama-server --hf-repo mohanz/DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL-GGUF --hf-file deepseek-r1-distill-qwen-1.5b-iq4_nl-imat.gguf -c 2048
31
- ```
32
-
33
- 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.
34
-
35
- Step 1: Clone llama.cpp from GitHub.
36
- ```
37
- git clone https://github.com/ggerganov/llama.cpp
38
- ```
39
-
40
- 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).
41
- ```
42
- cd llama.cpp && LLAMA_CURL=1 make
43
- ```
44
-
45
- Step 3: Run inference through the main binary.
46
- ```
47
- ./llama-cli --hf-repo mohanz/DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL-GGUF --hf-file deepseek-r1-distill-qwen-1.5b-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
48
- ```
49
- or
50
- ```
51
- ./llama-server --hf-repo mohanz/DeepSeek-R1-Distill-Qwen-1.5B-IQ4_NL-GGUF --hf-file deepseek-r1-distill-qwen-1.5b-iq4_nl-imat.gguf -c 2048
52
- ```
 
1
  ---
2
  license: mit
 
 
 
 
3
  base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
4
  ---
5
 
6
+ # Antigma/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
7
  This model was converted to GGUF format from [`deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
8
  Refer to the [original model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) for more details on the model.