MEME-KING16/granite-3.2-8b-claude-opus-full-ft
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: MEME-KING16/granite-3.2-8b-claude-opus-full-ft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-27 08:35:17 +08:00
commit 69848a00fc
48 changed files with 1226164 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
checkpoint-300/chat_template.jinja Normal file
View File

@@ -0,0 +1,8 @@
{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user
' + message['content'] + '<|im_end|>
'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant
' + message['content'] + '<|im_end|>
' }}{% else %}{{ '<|im_start|>system
' + message['content'] + '<|im_end|>
' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}

37
checkpoint-300/config.json Normal file
View File

@@ -0,0 +1,37 @@
{
"architectures": [
"GraniteForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attention_multiplier": 0.0078125,
"bos_token_id": 49155,
"dtype": "bfloat16",
"embedding_multiplier": 12.0,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12800,
"logits_scaling": 16.0,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_name": "unsloth/granite-3.2-8b-instruct",
"model_type": "granite",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"pad_token_id": 4,
"residual_multiplier": 0.22,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000000.0,
"rope_type": "default"
},
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"unsloth_fixed": true,
"unsloth_version": "2026.3.3",
"use_cache": false,
"vocab_size": 49155
}

10
checkpoint-300/generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"bos_token_id": 49155,
"eos_token_id": [
0
],
"max_length": 131072,
"pad_token_id": 4,
"transformers_version": "5.2.0"
}

3
checkpoint-300/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94f3b84d88e1f1b950a8780c4923d27a42eec4917c054d2ce5409f14c79a6f25
size 16341738952

3
checkpoint-300/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf1123ace49d03285e9c49420de50d320ecde4febcdcdc77350355f49f9e0039
size 32683715489

3
checkpoint-300/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f118a3f586351417bd05f009d8dd34f692f77467b6f137e63a016f383f4a8907
size 1465

244972
checkpoint-300/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

11
checkpoint-300/tokenizer_config.json Normal file
View File

@@ -0,0 +1,11 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|end_of_text|>",
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<fim_pad>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "�"
}

244
checkpoint-300/trainer_state.json Normal file
View File

@@ -0,0 +1,244 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.2732447817836814,
"eval_steps": 500,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07590132827324478,
"grad_norm": 22.0,
"learning_rate": 9e-08,
"loss": 1.0496648788452148,
"step": 10
},
{
"epoch": 0.15180265654648956,
"grad_norm": 21.5,
"learning_rate": 1.8999999999999998e-07,
"loss": 1.0672600746154786,
"step": 20
},
{
"epoch": 0.22770398481973433,
"grad_norm": 23.375,
"learning_rate": 2.9e-07,
"loss": 1.074104118347168,
"step": 30
},
{
"epoch": 0.3036053130929791,
"grad_norm": 19.0,
"learning_rate": 3.8999999999999997e-07,
"loss": 1.0784456253051757,
"step": 40
},
{
"epoch": 0.3795066413662239,
"grad_norm": 21.25,
"learning_rate": 4.9e-07,
"loss": 1.0631229400634765,
"step": 50
},
{
"epoch": 0.45540796963946867,
"grad_norm": 18.625,
"learning_rate": 5.9e-07,
"loss": 1.0021364212036132,
"step": 60
},
{
"epoch": 0.5313092979127134,
"grad_norm": 19.625,
"learning_rate": 6.9e-07,
"loss": 1.0368730545043945,
"step": 70
},
{
"epoch": 0.6072106261859582,
"grad_norm": 13.1875,
"learning_rate": 7.9e-07,
"loss": 0.9585152626037597,
"step": 80
},
{
"epoch": 0.683111954459203,
"grad_norm": 10.4375,
"learning_rate": 8.9e-07,
"loss": 0.8780872344970703,
"step": 90
},
{
"epoch": 0.7590132827324478,
"grad_norm": 6.84375,
"learning_rate": 9.9e-07,
"loss": 0.8695860862731933,
"step": 100
},
{
"epoch": 0.8349146110056926,
"grad_norm": 3.3125,
"learning_rate": 9.977206495402552e-07,
"loss": 0.8098324775695801,
"step": 110
},
{
"epoch": 0.9108159392789373,
"grad_norm": 2.96875,
"learning_rate": 9.898680903107666e-07,
"loss": 0.8349854469299316,
"step": 120
},
{
"epoch": 0.9867172675521821,
"grad_norm": 2.9375,
"learning_rate": 9.76502534086636e-07,
"loss": 0.8502012252807617,
"step": 130
},
{
"epoch": 1.060721062618596,
"grad_norm": 2.78125,
"learning_rate": 9.577743974243872e-07,
"loss": 0.7735446929931641,
"step": 140
},
{
"epoch": 1.1366223908918407,
"grad_norm": 3.359375,
"learning_rate": 9.338944475962236e-07,
"loss": 0.8373490333557129,
"step": 150
},
{
"epoch": 1.2125237191650853,
"grad_norm": 2.59375,
"learning_rate": 9.051314306058933e-07,
"loss": 0.8185565948486329,
"step": 160
},
{
"epoch": 1.2884250474383303,
"grad_norm": 2.9375,
"learning_rate": 8.718090467093653e-07,
"loss": 0.8056498527526855,
"step": 170
},
{
"epoch": 1.364326375711575,
"grad_norm": 2.59375,
"learning_rate": 8.343023074779368e-07,
"loss": 0.8409146308898926,
"step": 180
},
{
"epoch": 1.4402277039848197,
"grad_norm": 3.390625,
"learning_rate": 7.930333154015465e-07,
"loss": 0.7972420215606689,
"step": 190
},
{
"epoch": 1.5161290322580645,
"grad_norm": 2.546875,
"learning_rate": 7.484665135288213e-07,
"loss": 0.8233073234558106,
"step": 200
},
{
"epoch": 1.5920303605313093,
"grad_norm": 2.640625,
"learning_rate": 7.011034586046176e-07,
"loss": 0.8327888488769531,
"step": 210
},
{
"epoch": 1.6679316888045541,
"grad_norm": 2.65625,
"learning_rate": 6.514771765283942e-07,
"loss": 0.7899296283721924,
"step": 220
},
{
"epoch": 1.7438330170777987,
"grad_norm": 2.984375,
"learning_rate": 6.001461636573396e-07,
"loss": 0.7956095695495605,
"step": 230
},
{
"epoch": 1.8197343453510437,
"grad_norm": 3.625,
"learning_rate": 5.47688101463849e-07,
"loss": 0.8178939819335938,
"step": 240
},
{
"epoch": 1.8956356736242883,
"grad_norm": 2.828125,
"learning_rate": 4.946933552828719e-07,
"loss": 0.8414199829101563,
"step": 250
},
{
"epoch": 1.9715370018975333,
"grad_norm": 2.375,
"learning_rate": 4.417583303145147e-07,
"loss": 0.797624921798706,
"step": 260
},
{
"epoch": 2.0455407969639468,
"grad_norm": 2.890625,
"learning_rate": 3.894787596537351e-07,
"loss": 0.8394969940185547,
"step": 270
},
{
"epoch": 2.121442125237192,
"grad_norm": 2.375,
"learning_rate": 3.384429998839375e-07,
"loss": 0.799235200881958,
"step": 280
},
{
"epoch": 2.1973434535104364,
"grad_norm": 2.46875,
"learning_rate": 2.8922540968615283e-07,
"loss": 0.8156853675842285,
"step": 290
},
{
"epoch": 2.2732447817836814,
"grad_norm": 2.421875,
"learning_rate": 2.423798859812275e-07,
"loss": 0.8007305145263672,
"step": 300
}
],
"logging_steps": 10,
"max_steps": 396,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.3395087704745574e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-300/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c046e33cd8fc19c158792bb00b2580a5dcc0c5b7d92fa961dea01e4c3b0aa96
size 5585