Hugging Face's logo

oncu
/
c4ai-command-r7b-12-2024-GGUF

Transformers
GGUF
llama-cpp
gguf-my-repo
conversational
Model card Files Community
oncu commited on
Commit
5e1a677
·
verified ·
1 Parent(s): 76e4b23

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +26 -4
README.md CHANGED
@@ -57,12 +57,12 @@ Invoke the llama.cpp server or the CLI.
57
 
58
  ### CLI:
59
  ```bash
60
- llama-cli --hf-repo oncu/c4ai-command-r7b-12-2024-GGUF --hf-file c4ai-command-r7b-12-2024-q4_0.gguf -p "The meaning to life and the universe is"
61
  ```
62
 
63
  ### Server:
64
  ```bash
65
- llama-server --hf-repo oncu/c4ai-command-r7b-12-2024-GGUF --hf-file c4ai-command-r7b-12-2024-q4_0.gguf -c 2048
66
  ```
67
 
68
  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.
@@ -79,9 +79,31 @@ cd llama.cpp && LLAMA_CURL=1 make
79
 
80
  Step 3: Run inference through the main binary.
81
  ```
82
- ./llama-cli --hf-repo oncu/c4ai-command-r7b-12-2024-GGUF --hf-file c4ai-command-r7b-12-2024-q4_0.gguf -p "The meaning to life and the universe is"
83
  ```
84
  or
85
  ```
86
- ./llama-server --hf-repo oncu/c4ai-command-r7b-12-2024-GGUF --hf-file c4ai-command-r7b-12-2024-q4_0.gguf -c 2048
87
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
  ### CLI:
59
  ```bash
60
+ llama-cli --hf-repo oncu/c4ai-command-r7b-12-2024-GGUF --hf-file c4ai-command-r7b-12-2024-q4_k_m.gguf -p "The meaning to life and the universe is"
61
  ```
62
 
63
  ### Server:
64
  ```bash
65
+ llama-server --hf-repo oncu/c4ai-command-r7b-12-2024-GGUF --hf-file c4ai-command-r7b-12-2024-q4_k_m.gguf -c 2048
66
  ```
67
 
68
  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.
 
79
 
80
  Step 3: Run inference through the main binary.
81
  ```
82
+ ./llama-cli --hf-repo oncu/c4ai-command-r7b-12-2024-GGUF --hf-file c4ai-command-r7b-12-2024-q4_k_m.gguf -p "The meaning to life and the universe is"
83
  ```
84
  or
85
  ```
86
+ ./llama-server --hf-repo oncu/c4ai-command-r7b-12-2024-GGUF --hf-file c4ai-command-r7b-12-2024-q4_k_m.gguf -c 2048
87
  ```
88
+
89
+
90
+
91
+ ## Quant List
92
+ You can download the desired quant version from the list here.
93
+
94
+ | Link | Type | Size/GB | Notes |
95
+ |:-----|:-----|--------:|:------|
96
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q2_k.gguf) | Q2_K | 3.44 | |
97
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q3_k_s.gguf) | Q3_K_S | 3.87 | |
98
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q3_k_m.gguf) | Q3_K_M | 4.22 | lower quality |
99
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q3_k_l.gguf) | Q3_K_L | 4.53 | |
100
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q4_0.gguf) | Q4_0 | 4.80 | Arm, fast |
101
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q4_k_s.gguf) | Q4_K_S | 4.83 | fast, recommended |
102
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q4_k_m.gguf) | Q4_K_M | 5.06 | fast, recommended |
103
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q5_0.gguf) | Q5_0 | 5.67 | |
104
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q5_k_s.gguf) | Q5_K_S | 5.67 | |
105
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q5_k_m.gguf) | Q5_K_M | 5.8 | |
106
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q6_k.gguf) | Q6_K | 6.60 | very good quality |
107
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-q8_0.gguf) | Q8_0 | 8.54 | fast, best quality |
108
+ | [Download here](https://huggingface.co/oncu/c4ai-command-r7b-12-2024-GGUF/resolve/main/c4ai-command-r7b-12-2024-f16.gguf) | f16 | 16.07 | 16 bpw, overkill |
109
+