Upload VMware/open-llama-13b-open-instruct ctranslate fp16 weights

README.md

@@ -0,0 +1,113 @@
+---
+tags:
+- ctranslate2
+- int8
+- float16
+
+license: cc
+datasets:
+- VMware/open-instruct-v1-oasst-dolly-hhrlhf
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+---
+# # Fast-Inference with Ctranslate2
+Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.
+
+quantized version of [VMware/open-llama-13b-open-instruct](https://huggingface.co/VMware/open-llama-13b-open-instruct)
+```bash
+pip install hf-hub-ctranslate2>=2.12.0 ctranslate2>=3.16.0
+```
+
+```python
+# from transformers import AutoTokenizer
+model_name = "michaelfeil/ct2fast-open-llama-13b-open-instruct"
+
+
+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>=2.12.0](https://github.com/michaelfeil/hf-hub-ctranslate2)
+- `compute_type=int8_float16` for `device="cuda"`
+- `compute_type=int8`  for `device="cpu"`
+
+Converted on 2023-06-27 using
+```
+ct2-transformers-converter --model VMware/open-llama-13b-open-instruct --output_dir ~/tmp-ct2fast-open-llama-13b-open-instruct --force --copy_files 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
+    
+
+# VMware/open-llama-13B-open-instruct
+Instruction-tuned version of the fully trained Open LLama 13B model. The model is open for <b>COMMERCIAL USE</b>. <br>
+
+<b> NOTE </b> : The model was trained using the Alpaca prompt template \
+<b> NOTE </b> : Fast tokenizer results in incorrect encoding, set the ```use_fast = False``` parameter, when instantiating the tokenizer\
+<b> NOTE </b> : The model might struggle with code as the tokenizer merges multiple spaces
+
+## License
+- <b>Commercially Viable </b>
+- Instruction dataset, [VMware/open-instruct-v1-oasst-dolly-hhrlhf](https://huggingface.co/datasets/VMware/open-instruct-v1-oasst-dolly-hhrlhf) is under cc-by-sa-3.0
+- Language Model, ([openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b)) is under apache-2.0
+
+
+## Nomenclature 
+
+- Model : Open-llama
+- Model Size: 13B parameters
+- Dataset: Open-instruct-v1 (oasst,dolly, hhrlhf)
+
+## Use in Transformers
+
+```
+import os
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = 'VMware/open-llama-13b-open-instruct'
+
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
+
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map='sequential')
+
+prompt_template = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
+
+prompt = 'Explain in simple terms how the attention mechanism of a transformer model works'
+
+
+inputt = prompt_template.format(instruction= prompt)
+input_ids = tokenizer(inputt, return_tensors="pt").input_ids.to("cuda")
+
+output1 = model.generate(input_ids, max_length=512)
+input_length = input_ids.shape[1]
+output1 = output1[:, input_length:]
+output = tokenizer.decode(output1[0])
+
+print(output)
+```
+  
+## Finetuning details
+The finetuning scripts will be available in our [RAIL Github Repository](https://github.com/vmware-labs/research-and-development-artificial-intelligence-lab/tree/main/instruction-tuning)
+## Evaluation
+
+<B>TODO</B>

config.json

@@ -0,0 +1,27 @@
+{
+    "_name_or_path": "/home/gollapudit/peft/open_llama_13b_open_instruct",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 2048,
+    "model_type": "llama",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.28.1",
+    "use_cache": true,
+    "vocab_size": 32000,
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "layer_norm_epsilon": null,
+    "unk_token": "<unk>"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdbda702db933751d9e9bfc3b7be138c71c7d9f48f3239c905931f385872e40e
+size 13025087966

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}