Upload folder using huggingface_hub (#2)

- 68fcfdc46790dc73f25d72d0b122fa7eb8fc376f103e22314ded253a38973ae6 (d806d9150d281881ef2f7ab19d99dbbc2d46daf5)
- 7ec5f9ab945c15be43e592333ca2c842d409c794db22741abe3553315bcbc642 (256c472c50a01980865d531841134e62e9435119)

README.md

@@ -1,6 +1,6 @@
 ---
 thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
-base_model: NousResearch/Llama-2-7b-chat-hf
+base_model: PrunaAI/NousResearch-Llama-2-7b-chat-hf-HQQ-4bit-smashed
 metrics:
 - memory_disk
 - memory_inference
@@ -38,7 +38,7 @@ tags:
 ![image info](./plots.png)
 
 **Frequently Asked Questions**
-- ***How does the compression work?*** The model is compressed with hqq.
+- ***How does the compression work?*** The model is compressed with [.
 - ***How does the model quality change?*** The quality of the model output might vary compared to the base model.
 - ***How is the model efficiency evaluated?*** These results were obtained on HARDWARE_NAME with configuration described in `model/smash_config.json` and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.
 - ***What is the model format?*** We use safetensors.
@@ -52,22 +52,18 @@ tags:
 
 You can run the smashed model with these steps:
 
-0. Check requirements from the original repo NousResearch/Llama-2-7b-chat-hf installed. In particular, check python, cuda, and transformers versions.
+0. Check requirements from the original repo PrunaAI/NousResearch-Llama-2-7b-chat-hf-HQQ-4bit-smashed installed. In particular, check python, cuda, and transformers versions.
 1. Make sure that you have installed quantization related packages.
     ```bash
-    pip install hqq
+    REQUIREMENTS_INSTRUCTIONS
     ```
 2. Load & run the model.
     ```python 
    from transformers import AutoModelForCausalLM, AutoTokenizer
-    from hqq.engine.hf import HQQModelForCausalLM
- from hqq.models.hf.base import AutoHQQHFModel
-
-   try:
-     model = HQQModelForCausalLM.from_quantized("PrunaAI/NousResearch-Llama-2-7b-chat-hf-HQQ-4bit-smashed", device_map='auto')
-    except: 
-     model = AutoHQQHFModel.from_quantized("PrunaAI/NousResearch-Llama-2-7b-chat-hf-HQQ-4bit-smashed")
-   tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf")
+   IMPORTS
+
+   MODEL_LOAD
+   tokenizer = AutoTokenizer.from_pretrained("PrunaAI/NousResearch-Llama-2-7b-chat-hf-HQQ-4bit-smashed")
     
    input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
     
@@ -81,7 +77,7 @@ The configuration info are in `smash_config.json`.
 
 ## Credits & License
 
-The license of the smashed model follows the license of the original model. Please check the license of the original model NousResearch/Llama-2-7b-chat-hf before using this model which provided the base model. The license  of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
+The license of the smashed model follows the license of the original model. Please check the license of the original model PrunaAI/NousResearch-Llama-2-7b-chat-hf-HQQ-4bit-smashed before using this model which provided the base model. The license  of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
 
 ## Want to compress other models?
 

results.json

@@ -0,0 +1,17 @@
+{
+    "current_gpu_type": "NVIDIA A100-PCIE-40GB",
+    "current_gpu_total_memory": 40339.3125,
+    "perplexity": 8.223958015441895,
+    "token_generation_latency_sync": 152.242822265625,
+    "token_generation_latency_async": 152.41347402334213,
+    "token_generation_throughput_sync": 0.0065684541649868675,
+    "token_generation_throughput_async": 0.006561099708591709,
+    "token_generation_CO2_emissions": null,
+    "token_generation_energy_consumption": null,
+    "inference_latency_sync": 240.43939819335938,
+    "inference_latency_async": 180.1711082458496,
+    "inference_throughput_sync": 0.004159052166632892,
+    "inference_throughput_async": 0.005550279452327428,
+    "inference_CO2_emissions": null,
+    "inference_energy_consumption": null
+}