Josephgflowers/TinyLlama-v1.1-Agent-Rag-Nerd-v1
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: Josephgflowers/TinyLlama-v1.1-Agent-Rag-Nerd-v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-03 11:21:14 +08:00
commit b5e9a925ca
10 changed files with 277 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
.gitattributes vendored Normal file
View File

@@ -0,0 +1,49 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

9
README.md Normal file
View File

@@ -0,0 +1,9 @@
---
license: mit
---
This model is a fine-tuned version of https://huggingface.co/Josephgflowers/TinyLlama-v1.1-Tiny-Agent-Test on an Agent based dataset of tool usage, function calling, programming, STEM data,
NER data, address parsing, RAG, and summary.
Special Thanks to https://nationtech.io/ for their generous sponorship in training this model.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6328952f798f8d122ce62a44/TRMquVVcSYpatpeF4V2NE.png)

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "/home/joe/Music/tiny-agent",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.41.1",
"use_cache": false,
"vocab_size": 32000
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"bos_token_id": 1,
"eos_token_id": 2,
"max_length": 2048,
"pad_token_id": 0,
"transformers_version": "4.41.1"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c6bd20809e816078ca78e1c0d6e593c0cef4c9d7734c45f9c7b165a84135eea
size 2200119664

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf467c9e0f536bda271283c6ef85eb1a943e3196b621c8a912d64953b205df83
size 1842795

43
tokenizer_config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 2048,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

103
trainer_state.json Normal file
View File

@@ -0,0 +1,103 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.29612081729345574,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.029612081729345572,
"grad_norm": 1.3230875730514526,
"learning_rate": 4.851939591353272e-05,
"loss": 0.7815,
"step": 100
},
{
"epoch": 0.059224163458691144,
"grad_norm": 1.2026115655899048,
"learning_rate": 4.703879182706544e-05,
"loss": 0.7442,
"step": 200
},
{
"epoch": 0.08883624518803672,
"grad_norm": 1.3409602642059326,
"learning_rate": 4.5558187740598166e-05,
"loss": 0.7353,
"step": 300
},
{
"epoch": 0.11844832691738229,
"grad_norm": 1.6831313371658325,
"learning_rate": 4.407758365413089e-05,
"loss": 0.697,
"step": 400
},
{
"epoch": 0.14806040864672787,
"grad_norm": 1.5774145126342773,
"learning_rate": 4.259697956766361e-05,
"loss": 0.7392,
"step": 500
},
{
"epoch": 0.17767249037607344,
"grad_norm": 1.1909443140029907,
"learning_rate": 4.1145987562925676e-05,
"loss": 0.7317,
"step": 600
},
{
"epoch": 0.207284572105419,
"grad_norm": 1.3016351461410522,
"learning_rate": 3.968018951732307e-05,
"loss": 0.6802,
"step": 700
},
{
"epoch": 0.23689665383476458,
"grad_norm": 0.9892593622207642,
"learning_rate": 3.819958543085579e-05,
"loss": 0.7211,
"step": 800
},
{
"epoch": 0.26650873556411014,
"grad_norm": 1.4809260368347168,
"learning_rate": 3.671898134438851e-05,
"loss": 0.7031,
"step": 900
},
{
"epoch": 0.29612081729345574,
"grad_norm": 0.9776161909103394,
"learning_rate": 3.5238377257921236e-05,
"loss": 0.7068,
"step": 1000
}
],
"logging_steps": 100,
"max_steps": 3377,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 7.6272529047552e+16,
"train_batch_size": 6,
"trial_name": null,
"trial_params": null
}