thanks to ozcur ❤

README.md

@@ -0,0 +1,24 @@
+This is 4-bit quantization of [chavinlo/alpaca-native](https://huggingface.co/chavinlo/alpaca-native) (`cecc16d`) via [qwopqwop200/GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa) (`5cdfad2`).
+
+Quantization invoked as such:
+
+`llama.py /output/path c4 --wbits 4 --groupsize 128 --save alpaca7b-4bit.pt`
+
+Inference example from the GPTQ repo and commit referenced above:
+
+```
+(gptq) [root@gpu03 GPTQ-for-LLaMa]# CUDA_VISIBLE_DEVICES=0 python llama_inference.py /root/alpaca-native-4bit --wbits 4 --groupsize 128 --load /root/alpaca-native-4bit/alpaca7b-4bit.pt --max_length 300 --text "$(cat test_prompt.txt)"
+Loading model ...
+Done.
+  ### Instruction: What is an alpaca? How is it different from a llama?
+### Response:  Alpacas are soft and gentle, while llamas are stubborn and independent.</s>
+(gptq) [root@gpu03 GPTQ-for-LLaMa]# CUDA_VISIBLE_DEVICES=0 python llama_inference.py /root/alpaca-native-4bit --wbits 4 --groupsize 128 --load /root/alpaca-native-4bit/alpaca7b-4bit.pt --max_length 300 --text "$(cat test_prompt.txt)"
+Loading model ...
+Done.
+  ### Instruction: What is an alpaca? How is it different from a llama?
+### Response:  An alpaca is a small, domesticated species of livestock from the Andes region of South America. It is typically kept as a pet, and its fibers can be used for various purposes, such as making clothing and crafts. Alpacas are typically brown or black, and their ears and tails are often moved.
+Although it is different from a llama, the two animals are often compared to when referring to their behavior.</s>
+(gptq) [root@gpu03 GPTQ-for-LLaMa]# md5sum /root/alpaca-native-4bit/alpaca7b-4bit.pt
+74849953cc54e313b972d2cc9a05c24b  /root/alpaca-native-4bit/alpaca7b-4bit.pt
+(gptq) [root@gpu03 GPTQ-for-LLaMa]#
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

alpaca7b-4bit.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fbb7f91919b08a203944e4450099f5896c486fb97af3f3b125cc64dcd048d9
+size 4521138824

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "decapoda-research/llama-7b-hf",
+  "architectures": [
+    "LLaMAForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 512,
+  "padding_side": "right",
+  "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--decapoda-research--llama-7b-hf/snapshots/5f98eefcc80e437ef68d457ad7bf167c2c6a1348/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": ""
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e749976892247caff7e8a6860fabeeac4d8b97c8d8a36665746cd35ed5a2bb
+size 3707