初始化项目,由ModelHub XC社区提供模型

Model: saketh1201/Qwen3-4B-Inventory-SFT
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 12:05:07 +08:00
commit 3800042b5c
21 changed files with 2076 additions and 0 deletions

View File

@@ -0,0 +1,52 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "Qwen3ForCausalLM",
"parent_library": "transformers.models.qwen3.modeling_qwen3",
"unsloth_fixed": true
},
"base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 32,
"lora_bias": false,
"lora_dropout": 0.0,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"k_proj",
"v_proj",
"gate_proj",
"o_proj",
"down_proj",
"q_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
size 11423114

View File

@@ -0,0 +1,233 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": false,
"model_max_length": 262144,
"pad_token": "<|PAD_TOKEN|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151667": {
"content": "<think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151668": {
"content": "</think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151669": {
"content": "<|PAD_TOKEN|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
}
}

View File

@@ -0,0 +1,118 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 64,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15625,
"grad_norm": 1.1824947595596313,
"learning_rate": 8e-05,
"loss": 2.1224836349487304,
"step": 5
},
{
"epoch": 0.3125,
"grad_norm": 0.45979633927345276,
"learning_rate": 9.952402219937816e-05,
"loss": 1.7379152297973632,
"step": 10
},
{
"epoch": 0.46875,
"grad_norm": 0.5583250522613525,
"learning_rate": 9.760588329553571e-05,
"loss": 1.5223669052124023,
"step": 15
},
{
"epoch": 0.625,
"grad_norm": 0.4054713845252991,
"learning_rate": 9.42728012826605e-05,
"loss": 1.2529266357421875,
"step": 20
},
{
"epoch": 0.78125,
"grad_norm": 0.41235220432281494,
"learning_rate": 8.962384209755452e-05,
"loss": 1.0075555801391602,
"step": 25
},
{
"epoch": 0.9375,
"grad_norm": 0.4131007790565491,
"learning_rate": 8.379718220723773e-05,
"loss": 0.7767543792724609,
"step": 30
},
{
"epoch": 1.09375,
"grad_norm": 0.28115367889404297,
"learning_rate": 7.696600172495997e-05,
"loss": 0.670633602142334,
"step": 35
},
{
"epoch": 1.25,
"grad_norm": 0.25491470098495483,
"learning_rate": 6.933333714707094e-05,
"loss": 0.6005853176116943,
"step": 40
},
{
"epoch": 1.40625,
"grad_norm": 0.2761740982532501,
"learning_rate": 6.112604669781572e-05,
"loss": 0.5778088092803955,
"step": 45
},
{
"epoch": 1.5625,
"grad_norm": 0.24875779449939728,
"learning_rate": 5.258806764421048e-05,
"loss": 0.538189172744751,
"step": 50
},
{
"epoch": 1.71875,
"grad_norm": 0.25878462195396423,
"learning_rate": 4.397316598723385e-05,
"loss": 0.5227806568145752,
"step": 55
},
{
"epoch": 1.875,
"grad_norm": 0.32230958342552185,
"learning_rate": 3.553739402317162e-05,
"loss": 0.5064546585083007,
"step": 60
}
],
"logging_steps": 5,
"max_steps": 96,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.659128844566528e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}