File size: 2,351 Bytes
ecb2864 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | # Modelfile
models:
- name: llama
config:
model_path: llama.gguf
tokenizer_path: llama_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: starcoder2
config:
model_path: starcoder2.gguf
tokenizer_path: starcoder2_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: qwen2
config:
model_path: qwen2.gguf
tokenizer_path: qwen2_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: gemma2
config:
model_path: gemma2.gguf
tokenizer_path: gemma2_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: meta_llama_31
config:
model_path: meta_llama_31.gguf
tokenizer_path: meta_llama_31_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: gemma2_9b
config:
model_path: gemma2_9b.gguf
tokenizer_path: gemma2_9b_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: phi3
config:
model_path: phi3.gguf
tokenizer_path: phi3_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: meta_llama_31_instruct
config:
model_path: meta_llama_31_instruct.gguf
tokenizer_path: meta_llama_31_instruct_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: gpt2_xl
config:
model_path: gpt2_xl.gguf
tokenizer_path: gpt2_xl_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: qwen2_math_7b
config:
model_path: qwen2_math_7b.gguf
tokenizer_path: qwen2_math_7b_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: wizardlm_7b
config:
model_path: wizardlm_7b.gguf
tokenizer_path: wizardlm_7b_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
- name: wizardlm_13b
config:
model_path: wizardlm_13b.gguf
tokenizer_path: wizardlm_13b_tokenizer.model
max_length: 2048
temperature: 0.7
top_k: 40
top_p: 0.9
|