Upload folder using huggingface_hub

README.md

@@ -0,0 +1,74 @@
+---
+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 [tiiuae/falcon-mamba-7b](https://huggingface.co/tiiuae/falcon-mamba-7b) but with smaller size. 
+
+Codes:
+```python
+import os
+
+import torch
+
+from huggingface_hub import create_repo, upload_folder
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    GenerationConfig,
+    AutoConfig,
+    pipeline,
+    set_seed,
+)
+
+model_id = "tiiuae/falcon-mamba-7b"
+repo_id = "yujiepan/falcon-mamba-tiny-random"
+save_path = f"/tmp/{repo_id}"
+os.system(f'rm -rf {save_path}')
+
+config = AutoConfig.from_pretrained(model_id)
+config.use_cache = True
+config.num_hidden_layers = 2
+config.hidden_size = 8
+config.intermediate_size = 16
+config.state_size = 8
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+tokenizer.save_pretrained(save_path)
+
+model = AutoModelForCausalLM.from_config(
+    config, torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+)
+model.generation_config = GenerationConfig.from_pretrained(
+    model_id,
+    trust_remote_code=True,
+)
+
+set_seed(42)
+num_params = 0
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        print(name, p.shape)
+        torch.nn.init.uniform_(p, -0.5, 0.5)
+        num_params += p.numel()
+print("Total number of parameters:", num_params)
+model.save_pretrained(save_path)
+
+pipe = pipeline(
+    "text-generation",
+    model=save_path,
+    device="cpu",
+    trust_remote_code=True,
+    max_new_tokens=20,
+)
+print(pipe("Hello World!"))
+
+# create_repo(repo_id, exist_ok=True)
+# upload_folder(repo_id=repo_id, folder_path=save_path, repo_type='model')
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "tiiuae/falcon-mamba-7b",
+  "architectures": [
+    "FalconMambaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "conv_kernel": 4,
+  "eos_token_id": 11,
+  "expand": 16,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.1,
+  "intermediate_size": 16,
+  "layer_norm_epsilon": 1e-05,
+  "mixer_rms_eps": 1e-06,
+  "model_type": "falcon_mamba",
+  "num_hidden_layers": 2,
+  "pad_token_id": 11,
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "state_size": 8,
+  "tie_word_embeddings": false,
+  "time_step_floor": 0.0001,
+  "time_step_init_scheme": "random",
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 256,
+  "time_step_scale": 1.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "use_mambapy": false,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 11,
+  "pad_token_id": 11,
+  "transformers_version": "4.45.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c906d1cda0ef7996efab32cf97b7394d6241c4a575bfc3eedd926cbcc2454a30
+size 2119944

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,123 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}