# BEGIN GENERAL GGUF METADATA
id: llama-nemotron
model: llama-nemotron
name: llama-nemotron
version: 1
# END GENERAL GGUF METADATA

# BEGIN INFERENCE PARAMETERS
# BEGIN REQUIRED
stop:
- <|end_header_id|>
# END REQUIRED

# BEGIN OPTIONAL
stream: true
top_p: 0.9
temperature: 0.7
frequency_penalty: 0
presence_penalty: 0
max_tokens: 4096
seed: -1
dynatemp_range: 0
dynatemp_exponent: 1
top_k: 40
min_p: 0.05
tfs_z: 1
typ_p: 1
repeat_last_n: 64
repeat_penalty: 1
mirostat: false
mirostat_tau: 5
mirostat_eta: 0.100000001
penalize_nl: false
ignore_eos: false
n_probs: 0
min_keep: 0
# END OPTIONAL
# END INFERENCE PARAMETERS

# BEGIN MODEL LOAD PARAMETERS
# BEGIN REQUIRED
engine: llama-cpp
ctx_len: 4096
ngl: 34
prompt_template: "<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>"
# END REQUIRED
# END MODEL LOAD PARAMETERS