Hugging Face's logo

second-state
/
gemma-3-1b-it-GGUF

Text Generation
Transformers
GGUF
gemma3_text
conversational
Model card Files Community
apepkuss79 commited on
Commit
0688ddf
·
verified ·
1 Parent(s): a5abecb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -25,11 +25,11 @@ pipeline_tag: text-generation
25
 
26
  ## Run with LlamaEdge
27
 
28
- - LlamaEdge version: [v0.16.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.1) and above
29
 
30
  - Prompt template
31
 
32
- - Prompt type: `gemma-instruct`
33
 
34
  - Prompt string
35
 
@@ -47,7 +47,7 @@ pipeline_tag: text-generation
47
  ```bash
48
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-3-1b-it-Q5_K_M.gguf \
49
  llama-api-server.wasm \
50
- --prompt-template gemma-instruct \
51
  --ctx-size 128000 \
52
  --model-name gemma-3-1b
53
  ```
@@ -58,7 +58,7 @@ pipeline_tag: text-generation
58
  wasmedge --dir .:. \
59
  --nn-preload default:GGML:AUTO:gemma-3-1b-it-Q5_K_M.gguf \
60
  llama-chat.wasm \
61
- --prompt-template gemma-instruct \
62
  --ctx-size 128000
63
  ```
64
 
 
25
 
26
  ## Run with LlamaEdge
27
 
28
+ - LlamaEdge version: [v0.18.5](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.18.5) and above
29
 
30
  - Prompt template
31
 
32
+ - Prompt type: `gemma-3`
33
 
34
  - Prompt string
35
 
 
47
  ```bash
48
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-3-1b-it-Q5_K_M.gguf \
49
  llama-api-server.wasm \
50
+ --prompt-template gemma-3 \
51
  --ctx-size 128000 \
52
  --model-name gemma-3-1b
53
  ```
 
58
  wasmedge --dir .:. \
59
  --nn-preload default:GGML:AUTO:gemma-3-1b-it-Q5_K_M.gguf \
60
  llama-chat.wasm \
61
+ --prompt-template gemma-3 \
62
  --ctx-size 128000
63
  ```
64