Usage
You can use this model with the following code:
First, download the model
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
model_id='lawrencewu/hc-mistral-7B-v0.3-alpaca-first-100'
model = AutoPeftModelForCausalLM.from_pretrained(model_id).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_id)
tokenizer.pad_token = tokenizer.eos_token
Then, construct the prompt template like so:
def prompt(nlq, cols):
return f"""Honeycomb is an observability platform that allows you to write queries to inspect trace data. You are an assistant that takes a natural language query (NLQ) and a list of valid columns and produce a Honeycomb query.
### Instruction:
NLQ: "{nlq}"
Columns: {cols}
### Response:
"""
def prompt_tok(nlq, cols):
_p = prompt(nlq, cols)
input_ids = tokenizer(_p, return_tensors="pt", truncation=True).input_ids.cuda()
out_ids = model.generate(input_ids=input_ids, max_new_tokens=5000,
do_sample=False)
return tokenizer.batch_decode(out_ids.detach().cpu().numpy(),
skip_special_tokens=True)[0][len(_p):]
Finally, you can get predictions like this:
# model inputs
nlq = "Exception count by exception and caller"
cols = ['error', 'exception.message', 'exception.type', 'exception.stacktrace', 'SampleRate', 'name', 'db.user', 'type', 'duration_ms', 'db.name', 'service.name', 'http.method', 'db.system', 'status_code', 'db.operation', 'library.name', 'process.pid', 'net.transport', 'messaging.system', 'rpc.system', 'http.target', 'db.statement', 'library.version', 'status_message', 'parent_name', 'aws.region', 'process.command', 'rpc.method', 'span.kind', 'serializer.name', 'net.peer.name', 'rpc.service', 'http.scheme', 'process.runtime.name', 'serializer.format', 'serializer.renderer', 'net.peer.port', 'process.runtime.version', 'http.status_code', 'telemetry.sdk.language', 'trace.parent_id', 'process.runtime.description', 'span.num_events', 'messaging.destination', 'net.peer.ip', 'trace.trace_id', 'telemetry.instrumentation_library', 'trace.span_id', 'span.num_links', 'meta.signal_type', 'http.route']
# print prediction
out = prompt_tok(nlq, cols)
print(nlq, '\n', out)
This will give you a prediction that looks like this:
"{'breakdowns': ['exception.message', 'exception.type'], 'calculations': [{'op': 'COUNT'}], 'filters': [{'column': 'exception.message', 'op': 'exists'}, {'column': 'exception.type', 'op': 'exists'}], 'orders': [{'op': 'COUNT', 'order': 'descending'}], 'time_range': 7200}"
See axolotl config
axolotl version: 0.4.0
base_model: mistralai/Mistral-7B-v0.3
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: true
strict: false
lora_fan_in_fan_out: false
data_seed: 49
seed: 49
datasets:
- path: data/output_first_100.jsonl
type: sharegpt
conversation: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./qlora-alpaca-out
hub_model_id: lawrencewu/hc-mistral-7B-v0.3-alpaca-first-100
adapter: qlora
lora_model_dir:
sequence_len: 896
sample_packing: false
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
wandb_project: hc-axolotl-mistral
wandb_entity: law
gradient_accumulation_steps: 4
micro_batch_size: 16
eval_batch_size: 16
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
max_grad_norm: 1.0
adam_beta2: 0.95
adam_epsilon: 0.00001
save_total_limit: 12
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_steps: 20
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 6
debug:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
save_safetensors: true
hc-mistral-7B-v0.3-alpaca-first-100
This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0883
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 49
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.2291 | 0.6667 | 1 | 1.1299 |
1.2111 | 1.3333 | 2 | 1.1216 |
1.2203 | 2.0 | 3 | 1.0883 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for lawrencewu/hc-mistral-7B-v0.3-alpaca-first-100
Base model
mistralai/Mistral-7B-v0.3