Felladrin commited on
Commit
93bb65c
1 Parent(s): a27aac3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +56 -2
README.md CHANGED
@@ -1,5 +1,59 @@
1
  ---
2
- base_model: Felladrin/gguf-Q5_K_M-Phi-1_5-Instruct-v0.1
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
 
5
- Sharded GGUF version of [Felladrin/gguf-Q5_K_M-Phi-1_5-Instruct-v0.1](https://huggingface.co/Felladrin/gguf-Q5_K_M-Phi-1_5-Instruct-v0.1).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: rasyosef/Phi-1_5-Instruct-v0.1
3
+ datasets:
4
+ - teknium/OpenHermes-2.5
5
+ - HuggingFaceH4/ultrafeedback_binarized
6
+ - argilla/distilabel-intel-orca-dpo-pairs
7
+ - jondurbin/py-dpo-v0.1
8
+ - argilla/distilabel-math-preference-dpo
9
+ library_name: transformers
10
+ license: mit
11
+ pipeline_tag: text-generation
12
+ tags:
13
+ - llama-cpp
14
+ - gguf-my-repo
15
  ---
16
 
17
+ # Felladrin/Phi-1_5-Instruct-v0.1-Q5_K_M-GGUF
18
+ This model was converted to GGUF format from [`rasyosef/Phi-1_5-Instruct-v0.1`](https://huggingface.co/rasyosef/Phi-1_5-Instruct-v0.1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
19
+ Refer to the [original model card](https://huggingface.co/rasyosef/Phi-1_5-Instruct-v0.1) for more details on the model.
20
+
21
+ ## Use with llama.cpp
22
+ Install llama.cpp through brew (works on Mac and Linux)
23
+
24
+ ```bash
25
+ brew install llama.cpp
26
+
27
+ ```
28
+ Invoke the llama.cpp server or the CLI.
29
+
30
+ ### CLI:
31
+ ```bash
32
+ llama-cli --hf-repo Felladrin/Phi-1_5-Instruct-v0.1-Q5_K_M-GGUF --hf-file phi-1_5-instruct-v0.1-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
33
+ ```
34
+
35
+ ### Server:
36
+ ```bash
37
+ llama-server --hf-repo Felladrin/Phi-1_5-Instruct-v0.1-Q5_K_M-GGUF --hf-file phi-1_5-instruct-v0.1-q5_k_m-imat.gguf -c 2048
38
+ ```
39
+
40
+ 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.
41
+
42
+ Step 1: Clone llama.cpp from GitHub.
43
+ ```
44
+ git clone https://github.com/ggerganov/llama.cpp
45
+ ```
46
+
47
+ 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).
48
+ ```
49
+ cd llama.cpp && LLAMA_CURL=1 make
50
+ ```
51
+
52
+ Step 3: Run inference through the main binary.
53
+ ```
54
+ ./llama-cli --hf-repo Felladrin/Phi-1_5-Instruct-v0.1-Q5_K_M-GGUF --hf-file phi-1_5-instruct-v0.1-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
55
+ ```
56
+ or
57
+ ```
58
+ ./llama-server --hf-repo Felladrin/Phi-1_5-Instruct-v0.1-Q5_K_M-GGUF --hf-file phi-1_5-instruct-v0.1-q5_k_m-imat.gguf -c 2048
59
+ ```