hellork commited on
Commit
25182cf
1 Parent(s): a5a39fa

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM-1.7B-Instruct
3
+ datasets:
4
+ - Magpie-Align/Magpie-Pro-300K-Filtered
5
+ - bigcode/self-oss-instruct-sc2-exec-filter-50k
6
+ - teknium/OpenHermes-2.5
7
+ - HuggingFaceTB/everyday-conversations-llama3.1-2k
8
+ language:
9
+ - en
10
+ library_name: transformers
11
+ license: apache-2.0
12
+ tags:
13
+ - alignment-handbook
14
+ - trl
15
+ - sft
16
+ - llama-cpp
17
+ - gguf-my-repo
18
+ ---
19
+
20
+ # hellork/SmolLM-1.7B-Instruct-Q5_K_M-GGUF
21
+ This model was converted to GGUF format from [`HuggingFaceTB/SmolLM-1.7B-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
22
+ Refer to the [original model card](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct) for more details on the model.
23
+
24
+ ## Use with llama.cpp
25
+ Install llama.cpp through brew (works on Mac and Linux)
26
+
27
+ ```bash
28
+ brew install llama.cpp
29
+
30
+ ```
31
+ Invoke the llama.cpp server or the CLI.
32
+
33
+ ### CLI:
34
+ ```bash
35
+ llama-cli --hf-repo hellork/SmolLM-1.7B-Instruct-Q5_K_M-GGUF --hf-file smollm-1.7b-instruct-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
36
+ ```
37
+
38
+ ### Server:
39
+ ```bash
40
+ llama-server --hf-repo hellork/SmolLM-1.7B-Instruct-Q5_K_M-GGUF --hf-file smollm-1.7b-instruct-q5_k_m-imat.gguf -c 2048
41
+ ```
42
+
43
+ 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.
44
+
45
+ Step 1: Clone llama.cpp from GitHub.
46
+ ```
47
+ git clone https://github.com/ggerganov/llama.cpp
48
+ ```
49
+
50
+ 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).
51
+ ```
52
+ cd llama.cpp && LLAMA_CURL=1 make
53
+ ```
54
+
55
+ Step 3: Run inference through the main binary.
56
+ ```
57
+ ./llama-cli --hf-repo hellork/SmolLM-1.7B-Instruct-Q5_K_M-GGUF --hf-file smollm-1.7b-instruct-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
58
+ ```
59
+ or
60
+ ```
61
+ ./llama-server --hf-repo hellork/SmolLM-1.7B-Instruct-Q5_K_M-GGUF --hf-file smollm-1.7b-instruct-q5_k_m-imat.gguf -c 2048
62
+ ```