[WIP] Upload folder using huggingface_hub (multi-commit 50f58f06ead177f88836447a20b19f26d917b831c1a3f9b9bac44727fbfd886e)

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: pruna-engine
 thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
 metrics:
 - memory_disk
@@ -7,8 +8,6 @@ metrics:
 - inference_throughput
 - inference_CO2_emissions
 - inference_energy_consumption
-tags:
-- pruna-ai
 ---
 <!-- header start -->
 <!-- 200823 -->
@@ -22,7 +21,7 @@ tags:
 [![Twitter](https://img.shields.io/twitter/follow/PrunaAI?style=social)](https://twitter.com/PrunaAI)
 [![GitHub](https://img.shields.io/github/followers/PrunaAI?label=Follow%20%40PrunaAI&style=social)](https://github.com/PrunaAI)
 [![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue)](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following)
-[![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.gg/rskEr4BZJx)
+[![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.gg/CP4VSgck)
 
 # Simply make AI models cheaper, smaller, faster, and greener!
 
@@ -30,11 +29,11 @@ tags:
 - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
 - Request access to easily compress your *own* AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
 - Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/)
-- Join Pruna AI community on Discord [here](https://discord.gg/rskEr4BZJx) to share feedback/suggestions or get help.
+- Join Pruna AI community on Discord [here](https://discord.gg/CP4VSgck) to share feedback/suggestions or get help.
 
 ## Results
 
-![image info](./plots.png)
+Detailed efficiency metrics coming soon!
 
 **Frequently Asked Questions**
 - ***How does the compression work?*** The model is compressed with llm-int8.
@@ -61,7 +60,7 @@ You can run the smashed model with these steps:
    from transformers import AutoModelForCausalLM, AutoTokenizer
 
     model = AutoModelForCausalLM.from_pretrained("PrunaAI/facebook-xglm-564M-bnb-4bit-smashed",
-                                                 trust_remote_code=True, device_map='auto')
+                                                 trust_remote_code=True)
     tokenizer = AutoTokenizer.from_pretrained("facebook/xglm-564M")
     
     input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/tmpgk6v805a",
+  "_name_or_path": "/tmp/tmpefd80oyd",
   "activation_dropout": 0,
   "activation_function": "gelu",
   "architectures": [
@@ -22,7 +22,7 @@
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
+    "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": [

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f33f43b53b8dc0965d37aa2c883cfa627dffb944e418f68e68b21b33cceaf6
-size 694930096
+oid sha256:e3122b51cea3efb16f5ea48225496917166269d0fb1774a765e6126d7b6a8f49
+size 681040709

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models8vfpiksw",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsuf8rvw4z",
         "batch_size": 1,
         "model_name": "facebook/xglm-564M",
         "pruning_ratio": 0.0,