初始化项目，由ModelHub XC社区提供模型

Model: pvlabs/Chytrej2-Mini-It
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 +1,104 @@
+---
+language:
+- en
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- llama
+- causal-lm
+- finetuned
+- chytrej
+- instruct
+- tiny
+- chatml
+library_name: transformers
+datasets:
+- HuggingFaceTB/everyday-conversations-llama3.1-2k
+base_model: pvlabs/Chytrej2-Mini
+---
+
+# Chytrej2-Mini-It
+
+A fine-tuned version of [Chytrej2-Mini](https://huggingface.co/pvlabs/Chytrej2-Mini) (20M params, LLaMA architecture) trained on conversational data. Don't expect great answers.
+
+Built by [PingVortex Labs](https://github.com/PingVortexLabs).
+
+[![Discord](https://img.shields.io/badge/Discord-5865F2?logo=discord&logoColor=white)](https://discord.gg/5SzkjVJBs2)
+
+---
+
+## Model Details
+
++ **Parameters:** 20M
++ **Context length:** 1024 tokens
++ **Language:** English only
++ **Format:** ChatML
++ **Base model:** [pvlabs/Chytrej2-Mini](https://huggingface.co/pvlabs/Chytrej2-Mini)
++ **Architecture:** LLaMA
++ **License:** Apache 2.0
+
+---
+
+## Training
+
+Fine-tuned on [HuggingFaceTB/everyday-conversations-llama3.1-2k](https://huggingface.co/datasets/HuggingFaceTB/everyday-conversations-llama3.1-2k) dataset.
+
+---
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_path = "pvlabs/Chytrej2-Mini-It"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path, dtype=torch.float16)
+model.eval()
+
+prompt = "<|im_start|>user\nHello<|im_end|>\n<|im_start|>assistant\n"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+with torch.no_grad():
+    output = model.generate(
+        **inputs,
+        max_new_tokens=200,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9,
+        eos_token_id=tokenizer.convert_tokens_to_ids("<|im_end|>"),
+        pad_token_id=tokenizer.eos_token_id,
+    )
+
+generated = tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
+print(generated)
+```
+
+---
+
+## Prompt Format (ChatML)
+
+The model uses the standard ChatML format:
+
+```
+<|im_start|>user
+Your message here<|im_end|>
+<|im_start|>assistant
+```
+
+For multi-turn, chain turns:
+
+```
+<|im_start|>user
+Hi!<|im_end|>
+<|im_start|>assistant
+Hello! How can I help you today?<|im_end|>
+<|im_start|>user
+What's 2+2?<|im_end|>
+<|im_start|>assistant
+```
+
+---
+
+*Made by [PingVortex](https://pingvortex.com).*

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 5,
+  "num_key_value_heads": 2,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.3.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc70f07fcae726a340dc15ba2ba629267e3e2dd35710f31a13b0b2fc618fff2
+size 40318264

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|endoftext|>",
+    "<|padding|>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}