catbash commited on
Commit
1e6cc20
1 Parent(s): f2dfeff

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: timpal0l/Mistral-7B-v0.1-flashback-v2-instruct
3
+ datasets:
4
+ - timpal0l/OpenHermes-2.5-sv
5
+ - teknium/OpenHermes-2.5
6
+ language:
7
+ - sv
8
+ - en
9
+ license: mit
10
+ pipeline_tag: text-generation
11
+ tags:
12
+ - pretrained
13
+ - flashback
14
+ - web
15
+ - conversational
16
+ - chat
17
+ - llama-cpp
18
+ - gguf-my-repo
19
+ ---
20
+
21
+ # catbash/Mistral-7B-v0.1-flashback-v2-instruct-Q5_K_M-GGUF
22
+ This model was converted to GGUF format from [`timpal0l/Mistral-7B-v0.1-flashback-v2-instruct`](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
23
+ Refer to the [original model card](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2-instruct) for more details on the model.
24
+
25
+ ## Use with llama.cpp
26
+ Install llama.cpp through brew (works on Mac and Linux)
27
+
28
+ ```bash
29
+ brew install llama.cpp
30
+
31
+ ```
32
+ Invoke the llama.cpp server or the CLI.
33
+
34
+ ### CLI:
35
+ ```bash
36
+ llama-cli --hf-repo catbash/Mistral-7B-v0.1-flashback-v2-instruct-Q5_K_M-GGUF --hf-file mistral-7b-v0.1-flashback-v2-instruct-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
37
+ ```
38
+
39
+ ### Server:
40
+ ```bash
41
+ llama-server --hf-repo catbash/Mistral-7B-v0.1-flashback-v2-instruct-Q5_K_M-GGUF --hf-file mistral-7b-v0.1-flashback-v2-instruct-q5_k_m-imat.gguf -c 2048
42
+ ```
43
+
44
+ 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.
45
+
46
+ Step 1: Clone llama.cpp from GitHub.
47
+ ```
48
+ git clone https://github.com/ggerganov/llama.cpp
49
+ ```
50
+
51
+ 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).
52
+ ```
53
+ cd llama.cpp && LLAMA_CURL=1 make
54
+ ```
55
+
56
+ Step 3: Run inference through the main binary.
57
+ ```
58
+ ./llama-cli --hf-repo catbash/Mistral-7B-v0.1-flashback-v2-instruct-Q5_K_M-GGUF --hf-file mistral-7b-v0.1-flashback-v2-instruct-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
59
+ ```
60
+ or
61
+ ```
62
+ ./llama-server --hf-repo catbash/Mistral-7B-v0.1-flashback-v2-instruct-Q5_K_M-GGUF --hf-file mistral-7b-v0.1-flashback-v2-instruct-q5_k_m-imat.gguf -c 2048
63
+ ```