Upload model

README.md

@@ -0,0 +1,131 @@
+---
+license: other
+base_model: Qwen/Qwen1.5-0.5B
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: Qwen/Qwen1.5-0.5B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: silk-road/ChatHaruhi-RolePlaying
+    type: "completion"
+dataset_prepared_path: 
+val_set_size: 0.00
+output_dir: ./outputs/out
+
+sequence_len: 250
+sample_packing: true
+pad_to_sequence_len: true
+save_safetensors: true
+gpu_memory_limit: 80GiB
+
+adapter:
+lora_model_dir:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_linear:
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00005
+
+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: false   #toggle
+
+warmup_steps: 100
+evals_per_epoch: 4
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed: #deepspeed_configs/zero2.json # multi-gpu only
+weight_decay: 0.01
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# outputs/out
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B) on the None dataset.
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c48e9edbee5da314efafc9ed3ba0f9989ef433d7b72f6419f8334da717e4031
+size 1239273520

model.safetensors.index.json

@@ -0,0 +1 @@
+{"weight_map": {"pytorch_model-00001-of-340.safetensors": ["model.embed_tokens.weight", "model.layers.0.self_attn.q_proj.weight", "model.layers.0.self_attn.q_proj.bias", "model.layers.0.self_attn.k_proj.weight", "model.layers.0.self_attn.k_proj.bias", "model.layers.0.self_attn.v_proj.weight", "model.layers.0.self_attn.v_proj.bias", "model.layers.0.self_attn.o_proj.weight", "model.layers.0.mlp.gate_proj.weight", "model.layers.0.mlp.up_proj.weight", "model.layers.0.mlp.down_proj.weight", "model.layers.0.input_layernorm.weight", "model.layers.0.input_layernorm.bias", "model.layers.0.post_attention_layernorm.weight", "model.layers.0.post_attention_layernorm.bias", "model.layers.1.self_attn.q_proj.weight", "model.layers.1.self_attn.q_proj.bias", "model.layers.1.self_attn.k_proj.weight", "model.layers.1.self_attn.k_proj.bias", "model.layers.1.self_attn.v_proj.weight", "model.layers.1.self_attn.v_proj.bias", "model.layers.1.self_attn.o_proj.weight", "model.layers.1.mlp.gate_proj.weight", "model.layers.1.mlp.up_proj.weight", "model.layers.1.mlp.down_proj.weight", "model.layers.1.input_layernorm.weight", "model.layers.1.input_layernorm.bias", "model.layers.1.post_attention_layernorm.weight", "model.layers.1.post_attention_layernorm.bias", "model.layers.2.self_attn.q_proj.weight", "model.layers.2.self_attn.q_proj.bias", "model.layers.2.self_attn.k_proj.weight", "model.layers.2.self_attn.k_proj.bias", "model.layers.2.self_attn.v_proj.weight", "model.layers.2.self_attn.v_proj.bias", "model.layers.2.self_attn.o_proj.weight", "model.layers.2.mlp.gate_proj.weight", "model.layers.2.mlp.up_proj.weight", "model.layers.2.mlp.down_proj.weight", "model.layers.2.input_layernorm.weight", "model.layers.2.input_layernorm.bias", "model.layers.2.post_attention_layernorm.weight", "model.layers.2.post_attention_layernorm.bias", "model.layers.3.self_attn.q_proj.weight", "model.layers.3.self_attn.q_proj.bias", "model.layers.3.self_attn.k_proj.weight", "model.layers.3.self_attn.k_proj.bias", "model.layers.3.self_attn.v_proj.weight", "model.layers.3.self_attn.v_proj.bias", "model.layers.3.self_attn.o_proj.weight", "model.layers.3.mlp.gate_proj.weight", "model.layers.3.mlp.up_proj.weight", "model.layers.3.mlp.down_proj.weight", "model.layers.3.input_layernorm.weight", "model.layers.3.input_layernorm.bias", "model.layers.3.post_attention_layernorm.weight", "model.layers.3.post_attention_layernorm.bias", "model.layers.4.self_attn.q_proj.weight", "model.layers.4.self_attn.q_proj.bias", "model.layers.4.self_attn.k_proj.weight", "model.layers.4.self_attn.k_proj.bias", "model.layers.4.self_attn.v_proj.weight", "model.layers.4.self_attn.v_proj.bias", "model.layers.4.self_attn.o_proj.weight", "model.layers.4.mlp.gate_proj.weight", "model.layers.4.mlp.up_proj.weight", "model.layers.4.mlp.down_proj.weight", "model.layers.4.input_layernorm.weight", "model.layers.4.input_layernorm.bias", "model.layers.4.post_attention_layernorm.weight", "model.layers.4.post_attention_layernorm.bias", "model.layers.5.self_attn.q_proj.weight", "model.layers.5.self_attn.q_proj.bias", "model.layers.5.self_attn.k_proj.weight", "model.layers.5.self_attn.k_proj.bias", "model.layers.5.self_attn.v_proj.weight", "model.layers.5.self_attn.v_proj.bias", "model.layers.5.self_attn.o_proj.weight", "model.layers.5.mlp.gate_proj.weight", "model.layers.5.mlp.up_proj.weight", "model.layers.5.mlp.down_proj.weight", "model.layers.5.input_layernorm.weight", "model.layers.5.input_layernorm.bias", "model.layers.5.post_attention_layernorm.weight", "model.layers.5.post_attention_layernorm.bias", "model.layers.6.self_attn.q_proj.weight", "model.layers.6.self_attn.q_proj.bias", "model.layers.6.self_attn.k_proj.weight", "model.layers.6.self_attn.k_proj.bias", "model.layers.6.self_attn.v_proj.weight", "model.layers.6.self_attn.v_proj.bias", "model.layers.6.self_attn.o_proj.weight", "model.layers.6.mlp.gate_proj.weight", "model.layers.6.mlp.up_proj.weight", "model.layers.6.mlp.down_proj.weight", "model.layers.6.input_layernorm.weight", "model.layers.6.input_layernorm.bias", "model.layers.6.post_attention_layernorm.weight", "model.layers.6.post_attention_layernorm.bias", "model.layers.7.self_attn.q_proj.weight", "model.layers.7.self_attn.q_proj.bias", "model.layers.7.self_attn.k_proj.weight", "model.layers.7.self_attn.k_proj.bias", "model.layers.7.self_attn.v_proj.weight", "model.layers.7.self_attn.v_proj.bias", "model.layers.7.self_attn.o_proj.weight", "model.layers.7.mlp.gate_proj.weight", "model.layers.7.mlp.up_proj.weight", "model.layers.7.mlp.down_proj.weight", "model.layers.7.input_layernorm.weight", "model.layers.7.input_layernorm.bias", "model.layers.7.post_attention_layernorm.weight", "model.layers.7.post_attention_layernorm.bias", "model.layers.8.self_attn.q_proj.weight", "model.layers.8.self_attn.q_proj.bias", "model.layers.8.self_attn.k_proj.weight", "model.layers.8.self_attn.k_proj.bias", "model.layers.8.self_attn.v_proj.weight", "model.layers.8.self_attn.v_proj.bias", "model.layers.8.self_attn.o_proj.weight", "model.layers.8.mlp.gate_proj.weight", "model.layers.8.mlp.up_proj.weight", "model.layers.8.mlp.down_proj.weight", "model.layers.8.input_layernorm.weight", "model.layers.8.input_layernorm.bias", "model.layers.8.post_attention_layernorm.weight", "model.layers.8.post_attention_layernorm.bias", "model.layers.9.self_attn.q_proj.weight", "model.layers.9.self_attn.q_proj.bias", "model.layers.9.self_attn.k_proj.weight", "model.layers.9.self_attn.k_proj.bias", "model.layers.9.self_attn.v_proj.weight", "model.layers.9.self_attn.v_proj.bias", "model.layers.9.self_attn.o_proj.weight", "model.layers.9.mlp.gate_proj.weight", "model.layers.9.mlp.up_proj.weight", "model.layers.9.mlp.down_proj.weight", "model.layers.9.input_layernorm.weight", "model.layers.9.input_layernorm.bias", "model.layers.9.post_attention_layernorm.weight", "model.layers.9.post_attention_layernorm.bias", "model.layers.10.self_attn.q_proj.weight", "model.layers.10.self_attn.q_proj.bias", "model.layers.10.self_attn.k_proj.weight", "model.layers.10.self_attn.k_proj.bias", "model.layers.10.self_attn.v_proj.weight", "model.layers.10.self_attn.v_proj.bias", "model.layers.10.self_attn.o_proj.weight", "model.layers.10.mlp.gate_proj.weight", "model.layers.10.mlp.up_proj.weight", "model.layers.10.mlp.down_proj.weight", "model.layers.10.input_layernorm.weight", "model.layers.10.input_layernorm.bias", "model.layers.10.post_attention_layernorm.weight", "model.layers.10.post_attention_layernorm.bias", "model.layers.11.self_attn.q_proj.weight", "model.layers.11.self_attn.q_proj.bias", "model.layers.11.self_attn.k_proj.weight", "model.layers.11.self_attn.k_proj.bias", "model.layers.11.self_attn.v_proj.weight", "model.layers.11.self_attn.v_proj.bias", "model.layers.11.self_attn.o_proj.weight", "model.layers.11.mlp.gate_proj.weight", "model.layers.11.mlp.up_proj.weight", "model.layers.11.mlp.down_proj.weight", "model.layers.11.input_layernorm.weight", "model.layers.11.input_layernorm.bias", "model.layers.11.post_attention_layernorm.weight", "model.layers.11.post_attention_layernorm.bias", "model.layers.12.self_attn.q_proj.weight", "model.layers.12.self_attn.q_proj.bias", "model.layers.12.self_attn.k_proj.weight", "model.layers.12.self_attn.k_proj.bias", "model.layers.12.self_attn.v_proj.weight", "model.layers.12.self_attn.v_proj.bias", "model.layers.12.self_attn.o_proj.weight", "model.layers.12.mlp.gate_proj.weight", "model.layers.12.mlp.up_proj.weight", "model.layers.12.mlp.down_proj.weight", "model.layers.12.input_layernorm.weight", "model.layers.12.input_layernorm.bias", "model.layers.12.post_attention_layernorm.weight", "model.layers.12.post_attention_layernorm.bias", "model.layers.13.self_attn.q_proj.weight", "model.layers.13.self_attn.q_proj.bias", "model.layers.13.self_attn.k_proj.weight", "model.layers.13.self_attn.k_proj.bias", "model.layers.13.self_attn.v_proj.weight", "model.layers.13.self_attn.v_proj.bias", "model.layers.13.self_attn.o_proj.weight", "model.layers.13.mlp.gate_proj.weight", "model.layers.13.mlp.up_proj.weight", "model.layers.13.mlp.down_proj.weight", "model.layers.13.input_layernorm.weight", "model.layers.13.input_layernorm.bias", "model.layers.13.post_attention_layernorm.weight", "model.layers.13.post_attention_layernorm.bias", "model.layers.14.self_attn.q_proj.weight", "model.layers.14.self_attn.q_proj.bias", "model.layers.14.self_attn.k_proj.weight", "model.layers.14.self_attn.k_proj.bias", "model.layers.14.self_attn.v_proj.weight", "model.layers.14.self_attn.v_proj.bias", "model.layers.14.self_attn.o_proj.weight", "model.layers.14.mlp.gate_proj.weight", "model.layers.14.mlp.up_proj.weight", "model.layers.14.mlp.down_proj.weight", "model.layers.14.input_layernorm.weight", "model.layers.14.input_layernorm.bias", "model.layers.14.post_attention_layernorm.weight", "model.layers.14.post_attention_layernorm.bias", "model.layers.15.self_attn.q_proj.weight", "model.layers.15.self_attn.q_proj.bias", "model.layers.15.self_attn.k_proj.weight", "model.layers.15.self_attn.k_proj.bias", "model.layers.15.self_attn.v_proj.weight", "model.layers.15.self_attn.v_proj.bias", "model.layers.15.self_attn.o_proj.weight", "model.layers.15.mlp.gate_proj.weight", "model.layers.15.mlp.up_proj.weight", "model.layers.15.mlp.down_proj.weight", "model.layers.15.input_layernorm.weight", "model.layers.15.input_layernorm.bias", "model.layers.15.post_attention_layernorm.weight", "model.layers.15.post_attention_layernorm.bias", "model.layers.16.self_attn.q_proj.weight", "model.layers.16.self_attn.q_proj.bias", "model.layers.16.self_attn.k_proj.weight", "model.layers.16.self_attn.k_proj.bias", "model.layers.16.self_attn.v_proj.weight", "model.layers.16.self_attn.v_proj.bias", "model.layers.16.self_attn.o_proj.weight", "model.layers.16.mlp.gate_proj.weight", "model.layers.16.mlp.up_proj.weight", "model.layers.16.mlp.down_proj.weight", "model.layers.16.input_layernorm.weight", "model.layers.16.input_layernorm.bias", "model.layers.16.post_attention_layernorm.weight", "model.layers.16.post_attention_layernorm.bias", "model.layers.17.self_attn.q_proj.weight", "model.layers.17.self_attn.q_proj.bias", "model.layers.17.self_attn.k_proj.weight", "model.layers.17.self_attn.k_proj.bias", "model.layers.17.self_attn.v_proj.weight", "model.layers.17.self_attn.v_proj.bias", "model.layers.17.self_attn.o_proj.weight", "model.layers.17.mlp.gate_proj.weight", "model.layers.17.mlp.up_proj.weight", "model.layers.17.mlp.down_proj.weight", "model.layers.17.input_layernorm.weight", "model.layers.17.input_layernorm.bias", "model.layers.17.post_attention_layernorm.weight", "model.layers.17.post_attention_layernorm.bias", "model.layers.18.self_attn.q_proj.weight", "model.layers.18.self_attn.q_proj.bias", "model.layers.18.self_attn.k_proj.weight", "model.layers.18.self_attn.k_proj.bias", "model.layers.18.self_attn.v_proj.weight", "model.layers.18.self_attn.v_proj.bias", "model.layers.18.self_attn.o_proj.weight", "model.layers.18.mlp.gate_proj.weight", "model.layers.18.mlp.up_proj.weight", "model.layers.18.mlp.down_proj.weight", "model.layers.18.input_layernorm.weight", "model.layers.18.input_layernorm.bias", "model.layers.18.post_attention_layernorm.weight", "model.layers.18.post_attention_layernorm.bias", "model.layers.19.self_attn.q_proj.weight", "model.layers.19.self_attn.q_proj.bias", "model.layers.19.self_attn.k_proj.weight", "model.layers.19.self_attn.k_proj.bias", "model.layers.19.self_attn.v_proj.weight", "model.layers.19.self_attn.v_proj.bias", "model.layers.19.self_attn.o_proj.weight", "model.layers.19.mlp.gate_proj.weight", "model.layers.19.mlp.up_proj.weight", "model.layers.19.mlp.down_proj.weight", "model.layers.19.input_layernorm.weight", "model.layers.19.input_layernorm.bias", "model.layers.19.post_attention_layernorm.weight", "model.layers.19.post_attention_layernorm.bias", "model.layers.20.self_attn.q_proj.weight", "model.layers.20.self_attn.q_proj.bias", "model.layers.20.self_attn.k_proj.weight", "model.layers.20.self_attn.k_proj.bias", "model.layers.20.self_attn.v_proj.weight", "model.layers.20.self_attn.v_proj.bias", "model.layers.20.self_attn.o_proj.weight", "model.layers.20.mlp.gate_proj.weight", "model.layers.20.mlp.up_proj.weight", "model.layers.20.mlp.down_proj.weight", "model.layers.20.input_layernorm.weight", "model.layers.20.input_layernorm.bias", "model.layers.20.post_attention_layernorm.weight", "model.layers.20.post_attention_layernorm.bias", "model.layers.21.self_attn.q_proj.weight", "model.layers.21.self_attn.q_proj.bias", "model.layers.21.self_attn.k_proj.weight", "model.layers.21.self_attn.k_proj.bias", "model.layers.21.self_attn.v_proj.weight", "model.layers.21.self_attn.v_proj.bias", "model.layers.21.self_attn.o_proj.weight", "model.layers.21.mlp.gate_proj.weight", "model.layers.21.mlp.up_proj.weight", "model.layers.21.mlp.down_proj.weight", "model.layers.21.input_layernorm.weight", "model.layers.21.input_layernorm.bias", "model.layers.21.post_attention_layernorm.weight", "model.layers.21.post_attention_layernorm.bias", "model.layers.22.self_attn.q_proj.weight", "model.layers.22.self_attn.q_proj.bias", "model.layers.22.self_attn.k_proj.weight", "model.layers.22.self_attn.k_proj.bias", "model.layers.22.self_attn.v_proj.weight", "model.layers.22.self_attn.v_proj.bias", "model.layers.22.self_attn.o_proj.weight", "model.layers.22.mlp.gate_proj.weight", "model.layers.22.mlp.up_proj.weight", "model.layers.22.mlp.down_proj.weight", "model.layers.22.input_layernorm.weight", "model.layers.22.input_layernorm.bias", "model.layers.22.post_attention_layernorm.weight", "model.layers.22.post_attention_layernorm.bias", "model.layers.23.self_attn.q_proj.weight", "model.layers.23.self_attn.q_proj.bias", "model.layers.23.self_attn.k_proj.weight", "model.layers.23.self_attn.k_proj.bias", "model.layers.23.self_attn.v_proj.weight", "model.layers.23.self_attn.v_proj.bias", "model.layers.23.self_attn.o_proj.weight", "model.layers.23.mlp.gate_proj.weight", "model.layers.23.mlp.up_proj.weight", "model.layers.23.mlp.down_proj.weight", "model.layers.23.input_layernorm.weight", "model.layers.23.input_layernorm.bias", "model.layers.23.post_attention_layernorm.weight", "model.layers.23.post_attention_layernorm.bias", "model.norm.weight", "model.norm.bias", "lm_head.weight"]}, "metadata": {"total_size": 3289030656}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}