Upload folder using huggingface_hub

.gitattributes

@@ -25,7 +25,6 @@
 *.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

README.md

@@ -1,3 +1,27 @@
 ---
-license: mit
+license: other
+language:
+- en
+datasets:
+- wikipedia
+pipeline_tag: text-generation
 ---
+## Model description
+This is a LLaMA-like model with only 160M parameters trained on Wikipedia and part of the C4-en and C4-realnewslike datasets. 
+
+No evaluation has been conducted yet, so use it with care.
+
+The model is mainly developed as a base Small Speculative Model in the [SpecInfer](https://arxiv.org/abs/2305.09781) paper.
+
+## Citation
+To cite the model, please use
+```bibtex
+@misc{miao2023specinfer,
+      title={SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification}, 
+      author={Xupeng Miao and Gabriele Oliaro and Zhihao Zhang and Xinhao Cheng and Zeyu Wang and Rae Ying Yee Wong and Zhuoming Chen and Daiyaan Arfeen and Reyna Abhyankar and Zhihao Jia},
+      year={2023},
+      eprint={2305.09781},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "JackFram/llama-160m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.30.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c89479bf6ca8dc8a6be5f78884caa3a5d95253f89b2a04a043720eaea479950
+size 649684840

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739c87b934a445152ffb8345ff2d3f63170842e23dfecf033618722e226d7678
+size 1299405253

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6b1e0ff24eab3b6dfe1c84f8856a5f515dc687bda2dba74710d786d64dcf79
+size 649712185

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
+size 14575

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eafe3d5e0585dde8c5033613de99a5d4f23df4284a488f4007b3944580c0b97
+size 17655

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e34eb456d2d003a2839f2daa9425e99bdd79ed7e24a1de9fc7d5738476bfb4b
+size 17655

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b374af4a2765d8771cee7a72921d3c2e438b9bee34f0b2d098ce6071afeb65e4
+size 17655

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df75d8477fcc69c7abb03025313915ebfe3ac18c54a7c57aaa455c0099e13e5
+size 17655

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbee4f91402d2995215f75eb802ad0f3303a5303d5847c5cbbf70a4ec511b9e2
+size 627

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa5aebd2b89a3a9ffc0f4b603243c329bf10889ce997948686829fc0b7b361d
+size 3899