Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+language:
+  - en
+tags:
+  - text-generation
+base_model: JackFram/llama-68m
+datasets:
+  - THUDM/webglm-qa
+  - databricks/databricks-dolly-15k
+  - cognitivecomputations/wizard_vicuna_70k_unfiltered
+  - totally-not-an-llm/EverythingLM-data-V3
+  - Amod/mental_health_counseling_conversations
+  - sablo/oasst2_curated
+  - starfishmedical/webGPT_x_dolly
+  - Open-Orca/OpenOrca
+  - mlabonne/chatml_dpo_pairs
+widget:
+  - text: |-
+      <|im_start|>system
+      You are a knowledgeable assistant. Help the user as much as you can.<|im_end|>
+      <|im_start|>user
+      How to become healthier?<|im_end|>
+      <|im_start|>assistant
+  - text: |-
+      <|im_start|>system
+      You are a career counselor. The user will provide you with an individual looking for guidance in their professional life, and your task is to assist them in determining what careers they are most suited for based on their skills, interests, and experience. You should also conduct research into the various options available, explain the job market trends in different industries, and advice on which qualifications would be beneficial for pursuing particular fields.<|im_end|>
+      <|im_start|>user
+      Heya!<|im_end|>
+      <|im_start|>assistant
+      Hi! How may I help you?<|im_end|>
+      <|im_start|>user
+      I am interested in developing a career in software engineering. What would you recommend me to do?<|im_end|>
+      <|im_start|>assistant
+  - text: |-
+      <|im_start|>user
+      Hey! Got a question for you!<|im_end|>
+      <|im_start|>assistant
+      Sure! What's it?<|im_end|>
+      <|im_start|>user
+      I'm planning to travel to the Bahamas! Can you give me some tips?<|im_end|>
+      <|im_start|>assistant
+  - text: |-
+      <|im_start|>system
+      You are a very creative assistant. User will give you a task, which you should complete with all your knowledge.<|im_end|>
+      <|im_start|>user
+      Write the background story of an RPG game about wizards and dragons in a sci-fi world.<|im_end|>
+      <|im_start|>assistant
+inference:
+  parameters:
+    max_new_tokens: 64
+    penalty_alpha: 0.5
+    top_k: 4
+---
+
+# A Llama Chat Model of 68M Parameters
+
+- Base model: [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m)
+- Datasets:
+  - [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa)
+  - [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k)
+  - [cognitivecomputations/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/cognitivecomputations/wizard_vicuna_70k_unfiltered)
+  - [totally-not-an-llm/EverythingLM-data-V3](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3)
+  - [Amod/mental_health_counseling_conversations](https://huggingface.co/datasets/Amod/mental_health_counseling_conversations)
+  - [sablo/oasst2_curated](https://huggingface.co/datasets/sablo/oasst2_curated)
+  - [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly)
+  - [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)
+  - [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs)
+- Availability in other ML formats:
+  - ONNX: [Felladrin/onnx-Llama-68M-Chat-v1](https://huggingface.co/Felladrin/onnx-Llama-68M-Chat-v1)
+
+## Recommended Prompt Format
+
+```
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{user_message}<|im_end|>
+<|im_start|>assistant
+```
+
+## Recommended Inference Parameters
+
+```yml
+penalty_alpha: 0.5
+top_k: 4
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": ["LlamaForCausalLM"],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "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": 2,
+  "num_key_value_heads": 12,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-6,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bf4d8d47e9d27cd68543726e6e6192fbc7a2ed061f9d1c3a6cc2a5c452ffbc
+size 272123144

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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
+    }
+  },
+  "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": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}