YorkieOH10 commited on
Commit
f65b673
1 Parent(s): 9d9c77d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +45 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - code
5
+ - llama-cpp
6
+ - gguf-my-repo
7
+ base_model: deepseek-ai/deepseek-coder-1.3b-base
8
+ datasets:
9
+ - JetBrains/KExercises
10
+ results:
11
+ - task:
12
+ type: text-generation
13
+ dataset:
14
+ name: MultiPL-HumanEval (Kotlin)
15
+ type: openai_humaneval
16
+ metrics:
17
+ - name: pass@1
18
+ type: pass@1
19
+ value: 36.65
20
+ ---
21
+
22
+ # YorkieOH10/deepseek-coder-1.3B-kexer-Q8_0-GGUF
23
+ This model was converted to GGUF format from [`JetBrains/deepseek-coder-1.3B-kexer`](https://huggingface.co/JetBrains/deepseek-coder-1.3B-kexer) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
24
+ Refer to the [original model card](https://huggingface.co/JetBrains/deepseek-coder-1.3B-kexer) for more details on the model.
25
+ ## Use with llama.cpp
26
+ Install llama.cpp through brew.
27
+ ```bash
28
+ brew install ggerganov/ggerganov/llama.cpp
29
+ ```
30
+ Invoke the llama.cpp server or the CLI.
31
+ CLI:
32
+ ```bash
33
+ llama-cli --hf-repo YorkieOH10/deepseek-coder-1.3B-kexer-Q8_0-GGUF --model deepseek-coder-1.3b-kexer-q8_0.gguf -p "The meaning to life and the universe is"
34
+ ```
35
+ Server:
36
+ ```bash
37
+ llama-server --hf-repo YorkieOH10/deepseek-coder-1.3B-kexer-Q8_0-GGUF --model deepseek-coder-1.3b-kexer-q8_0.gguf -c 2048
38
+ ```
39
+ 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.
40
+ ```
41
+ git clone https://github.com/ggerganov/llama.cpp && \
42
+ cd llama.cpp && \
43
+ make && \
44
+ ./main -m deepseek-coder-1.3b-kexer-q8_0.gguf -n 128
45
+ ```