nnch
/

GGUF
Thai
English
llama-cpp
gguf-my-repo
Eval Results
Inference Endpoints
conversational
nnch commited on
Commit
e706f4c
1 Parent(s): 1424156

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +161 -0
README.md ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sambanovasystems/SambaLingo-Thai-Chat
3
+ datasets:
4
+ - HuggingFaceH4/ultrachat_200k
5
+ - HuggingFaceH4/ultrafeedback_binarized
6
+ - HuggingFaceH4/cai-conversation-harmless
7
+ language:
8
+ - th
9
+ - en
10
+ license: llama2
11
+ tags:
12
+ - llama-cpp
13
+ - gguf-my-repo
14
+ model-index:
15
+ - name: SambaLingo-Thai-Chat
16
+ results:
17
+ - task:
18
+ type: text-generation
19
+ name: Text Generation
20
+ dataset:
21
+ name: AI2 Reasoning Challenge (25-Shot)
22
+ type: ai2_arc
23
+ config: ARC-Challenge
24
+ split: test
25
+ args:
26
+ num_few_shot: 25
27
+ metrics:
28
+ - type: acc_norm
29
+ value: 52.73
30
+ name: normalized accuracy
31
+ source:
32
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
33
+ name: Open LLM Leaderboard
34
+ - task:
35
+ type: text-generation
36
+ name: Text Generation
37
+ dataset:
38
+ name: HellaSwag (10-Shot)
39
+ type: hellaswag
40
+ split: validation
41
+ args:
42
+ num_few_shot: 10
43
+ metrics:
44
+ - type: acc_norm
45
+ value: 78.42
46
+ name: normalized accuracy
47
+ source:
48
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
49
+ name: Open LLM Leaderboard
50
+ - task:
51
+ type: text-generation
52
+ name: Text Generation
53
+ dataset:
54
+ name: MMLU (5-Shot)
55
+ type: cais/mmlu
56
+ config: all
57
+ split: test
58
+ args:
59
+ num_few_shot: 5
60
+ metrics:
61
+ - type: acc
62
+ value: 43.95
63
+ name: accuracy
64
+ source:
65
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
66
+ name: Open LLM Leaderboard
67
+ - task:
68
+ type: text-generation
69
+ name: Text Generation
70
+ dataset:
71
+ name: TruthfulQA (0-shot)
72
+ type: truthful_qa
73
+ config: multiple_choice
74
+ split: validation
75
+ args:
76
+ num_few_shot: 0
77
+ metrics:
78
+ - type: mc2
79
+ value: 40.84
80
+ source:
81
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
82
+ name: Open LLM Leaderboard
83
+ - task:
84
+ type: text-generation
85
+ name: Text Generation
86
+ dataset:
87
+ name: Winogrande (5-shot)
88
+ type: winogrande
89
+ config: winogrande_xl
90
+ split: validation
91
+ args:
92
+ num_few_shot: 5
93
+ metrics:
94
+ - type: acc
95
+ value: 72.22
96
+ name: accuracy
97
+ source:
98
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
99
+ name: Open LLM Leaderboard
100
+ - task:
101
+ type: text-generation
102
+ name: Text Generation
103
+ dataset:
104
+ name: GSM8k (5-shot)
105
+ type: gsm8k
106
+ config: main
107
+ split: test
108
+ args:
109
+ num_few_shot: 5
110
+ metrics:
111
+ - type: acc
112
+ value: 8.57
113
+ name: accuracy
114
+ source:
115
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
116
+ name: Open LLM Leaderboard
117
+ ---
118
+
119
+ # nnch/SambaLingo-Thai-Chat-Q4_K_M-GGUF
120
+ This model was converted to GGUF format from [`sambanovasystems/SambaLingo-Thai-Chat`](https://huggingface.co/sambanovasystems/SambaLingo-Thai-Chat) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
121
+ Refer to the [original model card](https://huggingface.co/sambanovasystems/SambaLingo-Thai-Chat) for more details on the model.
122
+
123
+ ## Use with llama.cpp
124
+ Install llama.cpp through brew (works on Mac and Linux)
125
+
126
+ ```bash
127
+ brew install llama.cpp
128
+
129
+ ```
130
+ Invoke the llama.cpp server or the CLI.
131
+
132
+ ### CLI:
133
+ ```bash
134
+ llama-cli --hf-repo nnch/SambaLingo-Thai-Chat-Q4_K_M-GGUF --hf-file sambalingo-thai-chat-q4_k_m.gguf -p "The meaning to life and the universe is"
135
+ ```
136
+
137
+ ### Server:
138
+ ```bash
139
+ llama-server --hf-repo nnch/SambaLingo-Thai-Chat-Q4_K_M-GGUF --hf-file sambalingo-thai-chat-q4_k_m.gguf -c 2048
140
+ ```
141
+
142
+ 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.
143
+
144
+ Step 1: Clone llama.cpp from GitHub.
145
+ ```
146
+ git clone https://github.com/ggerganov/llama.cpp
147
+ ```
148
+
149
+ 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).
150
+ ```
151
+ cd llama.cpp && LLAMA_CURL=1 make
152
+ ```
153
+
154
+ Step 3: Run inference through the main binary.
155
+ ```
156
+ ./llama-cli --hf-repo nnch/SambaLingo-Thai-Chat-Q4_K_M-GGUF --hf-file sambalingo-thai-chat-q4_k_m.gguf -p "The meaning to life and the universe is"
157
+ ```
158
+ or
159
+ ```
160
+ ./llama-server --hf-repo nnch/SambaLingo-Thai-Chat-Q4_K_M-GGUF --hf-file sambalingo-thai-chat-q4_k_m.gguf -c 2048
161
+ ```