Upload folder using huggingface_hub

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+inference: true
+widget:
+- text: Hello!
+  example_title: Hello world
+  group: Python
+---
+
+This model is for debugging. It is randomly initialized using the config from [deepseek-ai/DeepSeek-V2-Chat-0628](https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat-0628) but with smaller size. 
+
+Codes:
+```python
+from huggingface_hub import create_repo, upload_folder
+from transformers import (
+    pipeline,
+    set_seed,
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    GenerationConfig,
+)
+import torch
+import transformers
+import os
+
+model_id = "deepseek-ai/DeepSeek-V2-Chat-0628"
+repo_id = "yujiepan/deepseek-v2-0628-tiny-random"
+save_path = f"/tmp/{repo_id}"
+
+config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
+config._name_or_path = model_id
+config.hidden_size = 8
+config.intermediate_size = 16
+config.moe_intermediate_size = 4
+config.num_attention_heads = 2
+config.num_key_value_heads = 2
+config.num_hidden_layers = 2
+config.kv_lora_rank = 2
+config.q_lora_rank = 2
+config.v_head_dim = 2
+config.qk_nope_head_dim = 2
+config.qk_rope_head_dim = 2
+config.torch_dtype = "bfloat16"
+print(config)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+tokenizer.save_pretrained(save_path)
+
+model = AutoModelForCausalLM.from_config(
+    config, torch_dtype=torch.bfloat16, attn_implementation="eager", trust_remote_code=True
+)
+model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True)
+
+set_seed(42)
+with torch.no_grad():
+    for _, p in sorted(model.named_parameters()):
+        torch.nn.init.uniform_(p, -0.1, 0.1)
+
+model.save_pretrained(save_path)
+
+# pipe = pipeline("text-generation", model=save_path, device="cuda", trust_remote_code=True)
+# print(pipe("Hello World!"))
+
+# messages = [
+#     {"role": "system", "content": "You are a robot."},
+#     {"role": "user", "content": "Hi!"},
+# ]
+# chatbot = pipeline("text-generation", model=save_path, max_length=1000, max_new_tokens=16, trust_remote_code=True)
+# print(chatbot(messages))
+
+messages = [{"role": "user", "content": "Write a piece of quicksort code in C++"}]
+input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
+outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)
+result = tokenizer.decode(outputs[0][input_tensor.shape[1] :], skip_special_tokens=True)
+print(result)
+```

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-V2-Chat-0628",
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "deepseek-ai/DeepSeek-V2-Chat-0628--configuration_deepseek.DeepseekV2Config",
+    "AutoModel": "deepseek-ai/DeepSeek-V2-Chat-0628--modeling_deepseek.DeepseekV2Model",
+    "AutoModelForCausalLM": "deepseek-ai/DeepSeek-V2-Chat-0628--modeling_deepseek.DeepseekV2ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 16,
+  "kv_lora_rank": 2,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 4,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 160,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 2,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "q_lora_rank": 2,
+  "qk_nope_head_dim": 2,
+  "qk_rope_head_dim": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 16.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 3,
+  "topk_method": "group_limited_greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 2,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "do_sample": true,
+  "eos_token_id": 100001,
+  "temperature": 0.3,
+  "top_p": 0.95,
+  "transformers_version": "4.43.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b122160ec62929db6035f95cdb01447f94b00c107060732a325b3fcd3635031
+size 3368856

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,162 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "<｜completion｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100009": {
+      "content": "<｜tool▁calls▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "<｜tool▁calls▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "<｜tool▁call▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "<｜tool▁call▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "<｜tool▁outputs▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "<｜tool▁outputs▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100015": {
+      "content": "<｜tool▁output▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100016": {
+      "content": "<｜tool▁output▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100017": {
+      "content": "<｜tool▁sep｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<｜User｜>' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ '<｜Assistant｜>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<｜Assistant｜>' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}