初始化项目，由ModelHub XC社区提供模型

Model: tiny-random/llama-3.3-dim64
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,103 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+inference: true
+widget:
+  - text: Hello!
+    example_title: Hello world
+    group: Python
+---
+
+This tiny model is for debugging. It is randomly initialized with the config adapted from [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct).
+
+### Example usage:
+
+```python
+from transformers import pipeline
+model_id = "tiny-random/llama-3.3-dim64"
+pipe = pipeline(
+    "text-generation", model=model_id, device="cuda",
+    trust_remote_code=True, max_new_tokens=3,
+)
+print(pipe("Hello World!"))
+```
+
+### Codes to create this repo:
+
+```python
+import torch
+
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    GenerationConfig,
+    pipeline,
+    set_seed,
+)
+
+source_model_id = "meta-llama/Llama-3.3-70B-Instruct"
+save_folder = "/tmp/tiny-random/llama-3.3-dim64"
+
+tokenizer = AutoTokenizer.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+tokenizer.save_pretrained(save_folder)
+
+config = AutoConfig.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+config.hidden_size = 64
+config.intermediate_size = 128
+config.num_attention_heads = 2
+config.num_key_value_heads = 1
+config.head_dim = 32
+config.num_hidden_layers = 2
+config.tie_word_embeddings = True
+
+model = AutoModelForCausalLM.from_config(
+    config,
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+)
+model.generation_config = GenerationConfig.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+set_seed(42)
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        torch.nn.init.normal_(p, 0, 0.2)
+        print(name, p.shape)
+model.save_pretrained(save_folder)
+```
+
+### Printing the model:
+
+```text
+LlamaForCausalLM(
+  (model): LlamaModel(
+    (embed_tokens): Embedding(128256, 64)
+    (layers): ModuleList(
+      (0-1): 2 x LlamaDecoderLayer(
+        (self_attn): LlamaAttention(
+          (q_proj): Linear(in_features=64, out_features=64, bias=False)
+          (k_proj): Linear(in_features=64, out_features=32, bias=False)
+          (v_proj): Linear(in_features=64, out_features=32, bias=False)
+          (o_proj): Linear(in_features=64, out_features=64, bias=False)
+        )
+        (mlp): LlamaMLP(
+          (gate_proj): Linear(in_features=64, out_features=128, bias=False)
+          (up_proj): Linear(in_features=64, out_features=128, bias=False)
+          (down_proj): Linear(in_features=128, out_features=64, bias=False)
+          (act_fn): SiLU()
+        )
+        (input_layernorm): LlamaRMSNorm((64,), eps=1e-05)
+        (post_attention_layernorm): LlamaRMSNorm((64,), eps=1e-05)
+      )
+    )
+    (norm): LlamaRMSNorm((64,), eps=1e-05)
+    (rotary_emb): LlamaRotaryEmbedding()
+  )
+  (lm_head): Linear(in_features=64, out_features=128256, bias=False)
+)
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 128,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.3",
+  "trust_remote_code": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9eeff558ffba042b2780e6fb4926c2aec2769b9d918458f1f5d7f20aaeafad
+size 16567032

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920