Text Generation
GGUF
cortex.cpp
conversational
jan-hq commited on
Commit
7e59e04
·
verified ·
1 Parent(s): 5bb58f2

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. model.yml +4 -3
model.yml CHANGED
@@ -1,4 +1,4 @@
1
- name: tinyllama 1B
2
  model: tinyllama:1B
3
  version: 1
4
 
@@ -15,5 +15,6 @@ stream: true # true | false
15
  # Engine / Model Settings
16
  ngl: 33 # Infer from base config.json -> num_attention_heads
17
  ctx_len: 4096 # Infer from base config.json -> max_position_embeddings
18
- engine: cortex.llamacpp
19
- prompt_template: "\n\n<|system|>\n{system_message}</s>\n\n\n\n\n<|user|>\n{prompt}</s>\n\n\n<|assistant|>\n\n"
 
 
1
+ name: tinyllama:1b-gguf-q5-km
2
  model: tinyllama:1B
3
  version: 1
4
 
 
15
  # Engine / Model Settings
16
  ngl: 33 # Infer from base config.json -> num_attention_heads
17
  ctx_len: 4096 # Infer from base config.json -> max_position_embeddings
18
+ engine: llama-cpp
19
+ prompt_template: "\n\n<|system|>\n{system_message}</s>\n\n\n\n\n<|user|>\n{prompt}</s>\n\
20
+ \n\n<|assistant|>\n\n"