ehristoforu commited on
Commit
8b347dc
·
verified ·
1 Parent(s): a07abd1

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - ru
5
+ - code
6
+ base_model: fluently/FluentlyQwen3-4B
7
+ inference: true
8
+ widget:
9
+ - example_title: FluentlyQwen3
10
+ messages:
11
+ - role: system
12
+ content: You are Fluently, a capable, neutrally-aligned assistant. Prefer concise,
13
+ correct answers.
14
+ - role: user
15
+ content: Explain the difference between BFS and DFS to a new CS student.
16
+ pipeline_tag: text-generation
17
+ library_name: transformers
18
+ license: apache-2.0
19
+ tags:
20
+ - fluently
21
+ - fluently-lm
22
+ - qwen3
23
+ - trained
24
+ - merged
25
+ - sft
26
+ - trl
27
+ - unsloth
28
+ - axolotl
29
+ - llama-cpp
30
+ - gguf-my-repo
31
+ ---
32
+
33
+ # ehristoforu/FluentlyQwen3-4B-Q4_K_M-GGUF
34
+ This model was converted to GGUF format from [`fluently/FluentlyQwen3-4B`](https://huggingface.co/fluently/FluentlyQwen3-4B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
35
+ Refer to the [original model card](https://huggingface.co/fluently/FluentlyQwen3-4B) for more details on the model.
36
+
37
+ ## Use with llama.cpp
38
+ Install llama.cpp through brew (works on Mac and Linux)
39
+
40
+ ```bash
41
+ brew install llama.cpp
42
+
43
+ ```
44
+ Invoke the llama.cpp server or the CLI.
45
+
46
+ ### CLI:
47
+ ```bash
48
+ llama-cli --hf-repo ehristoforu/FluentlyQwen3-4B-Q4_K_M-GGUF --hf-file fluentlyqwen3-4b-q4_k_m.gguf -p "The meaning to life and the universe is"
49
+ ```
50
+
51
+ ### Server:
52
+ ```bash
53
+ llama-server --hf-repo ehristoforu/FluentlyQwen3-4B-Q4_K_M-GGUF --hf-file fluentlyqwen3-4b-q4_k_m.gguf -c 2048
54
+ ```
55
+
56
+ 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.
57
+
58
+ Step 1: Clone llama.cpp from GitHub.
59
+ ```
60
+ git clone https://github.com/ggerganov/llama.cpp
61
+ ```
62
+
63
+ 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).
64
+ ```
65
+ cd llama.cpp && LLAMA_CURL=1 make
66
+ ```
67
+
68
+ Step 3: Run inference through the main binary.
69
+ ```
70
+ ./llama-cli --hf-repo ehristoforu/FluentlyQwen3-4B-Q4_K_M-GGUF --hf-file fluentlyqwen3-4b-q4_k_m.gguf -p "The meaning to life and the universe is"
71
+ ```
72
+ or
73
+ ```
74
+ ./llama-server --hf-repo ehristoforu/FluentlyQwen3-4B-Q4_K_M-GGUF --hf-file fluentlyqwen3-4b-q4_k_m.gguf -c 2048
75
+ ```