Upload OpenAssistant/falcon-7b-sft-top1-696 ctranslate fp16 weights

README.md

@@ -0,0 +1,182 @@
+---
+license: apache-2.0
+language:
+- en
+- de
+- es
+- fr
+tags:
+- ctranslate2
+- int8
+- float16
+- sft
+pipeline_tag: text-generation
+widget:
+- text: >-
+    <|prompter|>What is a meme, and what's the history behind this
+    word?<|endoftext|><|assistant|>
+- text: <|prompter|>What's the Earth total population<|endoftext|><|assistant|>
+- text: >-
+    <|prompter|>Write a story about future of AI
+    development<|endoftext|><|assistant|>
+datasets:
+- OpenAssistant/oasst1
+library_name: transformers
+---
+# # Fast-Inference with Ctranslate2
+Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.
+
+quantized version of [OpenAssistant/falcon-7b-sft-top1-696](https://huggingface.co/OpenAssistant/falcon-7b-sft-top1-696)
+```bash
+pip install hf-hub-ctranslate2>=2.10.0 ctranslate2>=3.16.0
+```
+
+```python
+# from transformers import AutoTokenizer
+model_name = "michaelfeil/ct2fast-falcon-7b-sft-top1-696"
+
+from hf_hub_ctranslate2 import GeneratorCT2fromHfHub
+model = GeneratorCT2fromHfHub(
+        # load in int8 on CUDA
+        model_name_or_path=model_name,
+        device="cuda",
+        compute_type="int8_float16",
+        # tokenizer=AutoTokenizer.from_pretrained("{ORG}/{NAME}")
+)
+outputs = model.generate(
+    text=["def fibonnaci(", "User: How are you doing? Bot:"],
+    max_length=64,
+    include_prompt_in_result=False
+)
+print(outputs)
+```
+
+Checkpoint compatible to [ctranslate2>=3.16.0](https://github.com/OpenNMT/CTranslate2)
+and [hf-hub-ctranslate2>=2.10.0](https://github.com/michaelfeil/hf-hub-ctranslate2)
+- `compute_type=int8_float16` for `device="cuda"`
+- `compute_type=int8`  for `device="cpu"`
+
+Converted on 2023-06-16 using
+```
+ct2-transformers-converter --model OpenAssistant/falcon-7b-sft-top1-696 --output_dir ~/tmp-ct2fast-falcon-7b-sft-top1-696 --force --copy_files tokenizer.json README.md tokenizer_config.json generation_config.json special_tokens_map.json .gitattributes --quantization int8_float16 --trust_remote_code
+```
+
+# Licence and other remarks:
+This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.
+
+# Original description
+    
+
+# Open-Assistant Falcon 7B SFT OASST-TOP1 Model
+
+This model is a fine-tuning of TII's [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b) LLM.
+It was trained with 11,123 top-1 (high-quality) demonstrations of the OASST data set (exported on June 2, 2023) with a batch size of 128 for 8 epochs with LIMA style dropout (p=0.2) and a context-length of 2048 tokens.
+
+## Model Details
+
+- **Finetuned from:** [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b)
+- **Model type:** Causal decoder-only transformer language model
+- **Language:** English, German, Spanish, French (and limited capabilities in Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish);
+- **Weights & Biases:** [Training log](https://wandb.ai/open-assistant/public-sft/runs/25apbcld) (Checkpoint: 696 steps)
+- **Code:** [Open-Assistant/model/model_training](https://github.com/LAION-AI/Open-Assistant/tree/main/model/model_training)
+- **Demo:** [Continuations for 250 random prompts](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Fchat-gpt%2F2023-04-11_gpt-3.5-turbo_lottery.json%0Ahttps%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-06-05_OpenAssistant_falcon-7b-sft-top1-696_sampling_noprefix2.json)
+- **License:** Apache 2.0
+- **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)
+
+
+## Prompting
+
+Two special tokens are used to mark the beginning of user and assistant turns:
+`<|prompter|>` and `<|assistant|>`. Each turn ends with a `<|endoftext|>` token.
+
+Input prompt example:
+```
+<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
+```
+The input ends with the `<|assistant|>` token to signal that the model should 
+start generating the assistant reply.
+
+
+## Sample Code
+
+```python
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "OpenAssistant/falcon-7b-sft-top1-696"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+    device_map="auto",
+)
+
+input_text="<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>"
+
+sequences = pipeline(
+    input_text,
+    max_length=500,
+    do_sample=True,
+    return_full_text=False,
+    top_k=10,
+    num_return_sequences=1,
+    eos_token_id=tokenizer.eos_token_id,
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
+```
+
+
+## Configuration Details
+
+Model:
+```
+falcon-7b:
+  dtype: bf16
+  log_dir: "falcon_log_7b"
+  learning_rate: 1e-5
+  model_name: "tiiuae/falcon-7b"
+  deepspeed_config: configs/zero_config.json
+  output_dir: falcon
+  weight_decay: 0.0
+  max_length: 2048
+  save_strategy: steps
+  eval_steps: 80
+  save_steps: 80
+  warmup_steps: 20
+  gradient_checkpointing: true
+  gradient_accumulation_steps: 4
+  per_device_train_batch_size: 4
+  per_device_eval_batch_size: 8
+  num_train_epochs: 8
+  save_total_limit: 4
+  residual_dropout: 0.2
+  residual_dropout_lima: true
+```
+
+Dataset:
+```
+oasst-top1:
+  # oasst_export: 11123 (100.00%)
+  datasets:
+    - oasst_export:
+        lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk" # sft-8.0
+        input_file_path: 2023-06-02_oasst_all_labels.jsonl.gz
+        val_split: 0.05
+        top_k: 1
+```
+
+Train command:
+```
+deepspeed trainer_sft.py --configs defaults falcon-7b oasst-top1 --cache_dir <data_cache_dir> --output_dir <output_path> --deepspeed
+```
+
+Export command:
+```
+python export_model.py --dtype bf16 --hf_repo_name OpenAssistant/falcon-7b-sft-top1 --trust_remote_code --auth_token <auth_token> <output_path> --max_shard_size 2GB
+```

config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "layer_norm_epsilon": null,
+  "unk_token": "<|endoftext|>"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.28.0.dev0"
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e95c31f80654d9eea02b3fdf7f1961ea88260040a5b496c80c2ed6e4e66a7ef
+size 6926465766

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    ">>QUESTION<<",
+    ">>MIDDLE<<",
+    ">>ANSWER<<",
+    "<|system|>",
+    ">>COMMENT<<",
+    ">>TITLE<<",
+    "<|assistant|>",
+    ">>INTRODUCTION<<",
+    "<|prefix_begin|>",
+    "<|prefix_end|>",
+    ">>PREFIX<<",
+    ">>DOMAIN<<",
+    ">>SUMMARY<<",
+    ">>SUFFIX<<",
+    "<|prompter|>",
+    ">>ABSTRACT<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "sep_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}