o1_t-lite-it-1.0_gguf

Name: o1_t-lite-it-1.0_gguf
Author: evilfreelancer

license:mit

evilfreelancer

Language Model

OTHER

New

71 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

LoRA-адаптер для модели T-lite-it-1.

Code Examples

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

yaml

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.