初始化项目，由ModelHub XC社区提供模型

Model: Havoc999/tiny-openhermes
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+language:
+- en
+license: apache-2.0
+datasets:
+- teknium/OpenHermes-2.5
+tags:
+- instruction-tuning
+- chatbot
+- trl
+- openhermes
+pipeline_tag: text-generation
+---
+
+# 🤖 Tiny OpenHermes — LoRA Fine-Tuned on OpenHermes-2.5
+
+Fine-tuned **[TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)** on the
+[teknium/OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5) dataset
+using LoRA (rank 32) via TRL's SFTTrainer on Kaggle Dual T4 GPU.
+
+
+LoRA rank	32
+LoRA alpha	64
+Epochs	1
+Peak LR	2e-4
+Effective batch	64 (4/GPU × 2 GPUs × 8 accum)
+Precision	float16
+Hardware	Kaggle Dual T4 (2 × 16 GiB)
+
+⚠️ Limitations
+English-primary (OpenHermes-2.5 is predominantly English)
+
+May hallucinate facts — verify important claims
+
+1.1 B parameter model: complex multi-step reasoning can fail
+
+Not RLHF-aligned for safety beyond TinyLlama's base alignment
+
+
+
+## Benchmark Results
+
+The model was evaluated using standard NLP benchmarks via the Language Model Evaluation Harness. It demonstrates moderate baseline capabilities in everyday physical reasoning but requires improvement in complex scientific knowledge and multi-step reasoning.
+
+| Benchmark | Tasks (Samples) | Metric | Raw Score (acc) | Normalized Score (acc_norm) |
+| :--- | :---: | :---: | :---: | :---: |
+| **PIQA** (Physical Commonsense) | 1,838 | Accuracy | 72.58% | **72.03%** |
+| **HellaSwag** (Commonsense Reasoning) | 10,042 | Accuracy | 44.69% | **59.20%** |
+| **ARC-Challenge** (Advanced Science) | 1,172 | Accuracy | 25.43% | **29.69%** |
+| **MMLU** (mathemaatics) | 1531 | Accuracy | 26.13% | **26.13%** |
+
+
+## 🚀 Quick Start
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "Havoc999/tiny-openhermes", torch_dtype=torch.float16
+).cuda()
+tok = AutoTokenizer.from_pretrained("Havoc999/tiny-openhermes")
+
+prompt = "<|user|>\nExplain gravity simply.</s>\n<|assistant|>\n"
+ids = tok(prompt, return_tensors="pt").input_ids.cuda()
+out = model.generate(ids, max_new_tokens=200, temperature=0.7, do_sample=True)
+print(tok.decode(out[0, ids.shape:], skip_special_tokens=True))

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "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,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401dadff6ad29d93528a04482ae924ed797e56669f3218a6811ddb047ec3f12f
+size 2200119864

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}