Upload folder using huggingface_hub

README.md

@@ -0,0 +1,123 @@
+---
+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 [openbmb/MiniCPM4-8B](https://huggingface.co/openbmb/MiniCPM4-8B).
+
+### Example usage:
+
+```python
+import torch
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "tiny-random/minicpm4"
+
+device = "cuda"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, torch_dtype=torch.bfloat16, device_map=device, trust_remote_code=True)
+
+# User can directly use the chat interface
+# responds, history = model.chat(tokenizer, "Write an article about Artificial Intelligence.", temperature=0.7, top_p=0.7)
+# print(responds)
+
+# User can also use the generate interface
+messages = [
+    {"role": "user", "content": "Write an article about Artificial Intelligence."},
+]
+prompt_text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([prompt_text], return_tensors="pt").to(device)
+
+model_outputs = model.generate(
+    **model_inputs,
+    max_new_tokens=32,
+    top_p=0.7,
+    temperature=0.7
+)
+output_token_ids = [
+    model_outputs[i][len(model_inputs[i]):] for i in range(len(model_inputs['input_ids']))
+]
+
+responses = tokenizer.batch_decode(output_token_ids, skip_special_tokens=True)[0]
+print(responses)
+```
+
+### Codes to create this repo:
+
+```python
+import json
+from pathlib import Path
+
+import torch
+
+import accelerate
+from huggingface_hub import hf_hub_download
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    GenerationConfig,
+    set_seed,
+)
+
+source_model_id = "openbmb/MiniCPM4-8B"
+save_folder = "/tmp/tiny-random/minicpm4"
+
+processor = AutoTokenizer.from_pretrained(source_model_id)
+processor.save_pretrained(save_folder)
+
+with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
+    config_json = json.load(f)
+config_json["hidden_size"] = 64
+config_json['intermediate_size'] = 128
+config_json['num_attention_heads'] = 2
+config_json['num_key_value_heads'] = 1
+config_json['dim_model_base'] = 32
+config_json['num_hidden_layers'] = 2
+config_json['tie_word_embeddings'] = True
+for k, v in config_json['auto_map'].items():
+    config_json['auto_map'][k] = f'{source_model_id}--{v}'
+automap = config_json['auto_map']
+factor = config_json['rope_scaling']['long_factor']
+config_json['rope_scaling']['long_factor'] = factor[:16]
+config_json['rope_scaling']['short_factor'] = factor[:16]
+with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
+    json.dump(config_json, f, indent=2)
+
+config = AutoConfig.from_pretrained(
+    save_folder,
+    trust_remote_code=True,
+)
+print(config)
+torch.set_default_dtype(torch.bfloat16)
+model = AutoModelForCausalLM.from_config(config, trust_remote_code=True)
+torch.set_default_dtype(torch.float32)
+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)
+        pass
+model.save_pretrained(save_folder)
+with open(f"{save_folder}/config.json", "r", encoding='utf-8') as f:
+    config_json = json.load(f)
+    config_json['auto_map'] = automap
+with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
+    json.dump(config_json, f, indent=2)
+for python_file in Path(save_folder).glob('*.py'):
+    python_file.unlink()
+```

added_tokens.json

@@ -0,0 +1,10 @@
+{
+  "<|execute_end|>": 73444,
+  "<|execute_start|>": 73443,
+  "<|fim_middle|>": 73446,
+  "<|fim_prefix|>": 73445,
+  "<|fim_suffix|>": 73447,
+  "<|im_end|>": 73440,
+  "<|im_start|>": 73441,
+  "<|tool_call|>": 73442
+}

config.json

@@ -0,0 +1,81 @@
+{
+  "architectures": [
+    "MiniCPMForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "openbmb/MiniCPM4-8B--configuration_minicpm.MiniCPMConfig",
+    "AutoModel": "openbmb/MiniCPM4-8B--modeling_minicpm.MiniCPMModel",
+    "AutoModelForCausalLM": "openbmb/MiniCPM4-8B--modeling_minicpm.MiniCPMForCausalLM",
+    "AutoModelForSeq2SeqLM": "openbmb/MiniCPM4-8B--modeling_minicpm.MiniCPMForCausalLM",
+    "AutoModelForSequenceClassification": "openbmb/MiniCPM4-8B--modeling_minicpm.MiniCPMForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "dim_model_base": 32,
+  "eos_token_id": [
+    2,
+    73440
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "initializer_range": 0.1,
+  "intermediate_size": 128,
+  "max_position_embeddings": 32768,
+  "model_type": "minicpm",
+  "mup_denominator": 32,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "long_factor": [
+      0.9977997200264581,
+      1.014658295992452,
+      1.0349680404997148,
+      1.059429246056193,
+      1.0888815016813513,
+      1.1243301355211495,
+      1.166977103606075,
+      1.2182568066927284,
+      1.2798772354275727,
+      1.3538666751582975,
+      1.4426259039919596,
+      1.5489853358570191,
+      1.6762658237220625,
+      1.8283407612492941,
+      2.0096956085876183,
+      2.225478927469756
+    ],
+    "original_max_position_embeddings": 32768,
+    "rope_type": "longrope",
+    "short_factor": [
+      0.9977997200264581,
+      1.014658295992452,
+      1.0349680404997148,
+      1.059429246056193,
+      1.0888815016813513,
+      1.1243301355211495,
+      1.166977103606075,
+      1.2182568066927284,
+      1.2798772354275727,
+      1.3538666751582975,
+      1.4426259039919596,
+      1.5489853358570191,
+      1.6762658237220625,
+      1.8283407612492941,
+      2.0096956085876183,
+      2.225478927469756
+    ]
+  },
+  "rope_theta": 10000.0,
+  "scale_depth": 1.4,
+  "scale_emb": 12,
+  "sparse_config": null,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 73448
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    73440
+  ],
+  "pad_token_id": 2,
+  "temperature": 0.8,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3",
+  "trust_remote_code": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146c31f9e7684c662fb314c0132dcb6b71ee3c746aedc864a3739bd99541865b
+size 9551568

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>",
+    "<|tool_call|>",
+    "<|execute_start|>",
+    "<|execute_end|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb74d51116831c3bf65db812c553f94ab0c88dcf97a5bbb37e3504f6d359c530
+size 1181204

tokenizer_config.json

@@ -0,0 +1,118 @@
+{
+  "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
+    },
+    "73440": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73441": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73442": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73443": {
+      "content": "<|execute_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73444": {
+      "content": "<|execute_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73445": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73446": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73447": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>",
+    "<|tool_call|>",
+    "<|execute_start|>",
+    "<|execute_end|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}