|
|
--- |
|
|
license: llama3.2 |
|
|
datasets: |
|
|
- teknium/OpenHermes-2.5 |
|
|
- NousResearch/hermes-function-calling-v1 |
|
|
base_model: |
|
|
- minpeter/QLoRA-Llama-3.2-1B-chatml-tool-v1 |
|
|
- minpeter/Llama-3.2-1B-AlternateTokenizer-tool-chatml |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-generation |
|
|
library_name: transformers |
|
|
tags: |
|
|
- axolotl |
|
|
- merge |
|
|
new_version: minpeter/Llama-3.2-1B-chatml-tool-v2 |
|
|
--- |
|
|
|
|
|
axolotl config |
|
|
```yaml |
|
|
base_model: minpeter/Llama-3.2-1B-AlternateTokenizer-chatml |
|
|
|
|
|
load_in_8bit: false |
|
|
load_in_4bit: true |
|
|
strict: false |
|
|
|
|
|
datasets: |
|
|
- path: teknium/OpenHermes-2.5 |
|
|
type: chat_template |
|
|
chat_template: chatml |
|
|
field_messages: conversations |
|
|
message_field_role: from |
|
|
message_field_content: value |
|
|
shards: 800 |
|
|
- path: func-calling-singleturn.jsonl |
|
|
type: chat_template |
|
|
chat_template: chatml |
|
|
field_messages: conversations |
|
|
message_field_role: from |
|
|
message_field_content: value |
|
|
shards: 2 |
|
|
|
|
|
save_safetensors: true |
|
|
auto_resume_from_checkpoints: false |
|
|
save_steps: 200 |
|
|
|
|
|
chat_template: chatml |
|
|
dataset_prepared_path: last_run_prepared |
|
|
val_set_size: 0.1 |
|
|
output_dir: ./output |
|
|
|
|
|
adapter: qlora |
|
|
lora_model_dir: |
|
|
|
|
|
sequence_len: 4096 |
|
|
sample_packing: true |
|
|
eval_sample_packing: true |
|
|
pad_to_sequence_len: true |
|
|
|
|
|
lora_r: 32 |
|
|
lora_alpha: 16 |
|
|
lora_dropout: 0.05 |
|
|
lora_fan_in_fan_out: |
|
|
lora_target_modules: |
|
|
- gate_proj |
|
|
- down_proj |
|
|
- up_proj |
|
|
- q_proj |
|
|
- v_proj |
|
|
- k_proj |
|
|
- o_proj |
|
|
|
|
|
wandb_project: "axolotl" |
|
|
wandb_entity: "kasfiekfs-e" |
|
|
wandb_watch: |
|
|
wandb_name: |
|
|
wandb_log_model: |
|
|
|
|
|
gradient_accumulation_steps: 4 |
|
|
micro_batch_size: 2 |
|
|
num_epochs: 2 |
|
|
optimizer: adamw_bnb_8bit |
|
|
lr_scheduler: cosine |
|
|
learning_rate: 0.0002 |
|
|
|
|
|
train_on_inputs: false |
|
|
group_by_length: false |
|
|
bf16: auto |
|
|
fp16: |
|
|
tf32: false |
|
|
|
|
|
gradient_checkpointing: true |
|
|
early_stopping_patience: |
|
|
resume_from_checkpoint: |
|
|
local_rank: |
|
|
logging_steps: 1 |
|
|
xformers_attention: |
|
|
# flash_attention: true |
|
|
|
|
|
loss_watchdog_threshold: 5.0 |
|
|
loss_watchdog_patience: 3 |
|
|
|
|
|
warmup_steps: 10 |
|
|
evals_per_epoch: 4 |
|
|
eval_table_size: |
|
|
eval_max_new_tokens: 128 |
|
|
debug: |
|
|
deepspeed: |
|
|
weight_decay: 0.0 |
|
|
fsdp: |
|
|
fsdp_config: |
|
|
|
|
|
special_tokens: |
|
|
bos_token: <|begin_of_text|> |
|
|
eos_token: <|im_end|> |
|
|
pad_token: <|end_of_text|> |
|
|
|
|
|
# <--- unsloth config ---> |
|
|
unsloth_lora_mlp: true |
|
|
unsloth_lora_qkv: true |
|
|
unsloth_lora_o: true |
|
|
``` |
|
|
|
|
|
function calling prompt |
|
|
|
|
|
```yaml |
|
|
tool_call_body_style: "arguments_name_object" |
|
|
system_prompt_template: | |
|
|
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools>{{tools}}</tools> Use the following pydantic model json schema for each tool call you will make: {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows: |
|
|
<tool_call> |
|
|
{'arguments': <args-dict>, 'name': <function-name>} |
|
|
</tool_call> |
|
|
``` |
