Upload folder using huggingface_hub (#2)

- 36aa1e3a1d93c775b272f4a1d9b7edb7c203266c299f7180a78dd3c4b2e6abe2 (1bdd7ea2ed895db4e60171220ba67b2c5277a114)

README.md

@@ -34,7 +34,7 @@ tags:
 
 ## Results
 
-Detailed efficiency metrics coming soon!
+![image info](./plots.png)
 
 **Frequently Asked Questions**
 - ***How does the compression work?*** The model is compressed with llm-int8.
@@ -61,7 +61,7 @@ You can run the smashed model with these steps:
    from transformers import AutoModelForCausalLM, AutoTokenizer
 
     model = AutoModelForCausalLM.from_pretrained("PrunaAI/cerebras-Cerebras-GPT-111M-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("cerebras/Cerebras-GPT-111M")
     
     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/tmppdfytjk7",
+  "_name_or_path": "/tmp/tmpnjft4zf9",
   "activation_function": "gelu",
   "architectures": [
     "GPT2LMHeadModel"
@@ -19,7 +19,7 @@
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_use_double_quant": false,
     "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 sha256:246b1bb693f512d2cb991ef63a1741a3c73b2b93fc6eab1bda76bb40d673bd90
-size 117140801
+oid sha256:068b147af4e3f55b72990ceb1334823cb1a8946fbfc51cf01f46e4b89a5c49b3
+size 120388150

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelszulz8221",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsgv4v5_bg",
         "batch_size": 1,
         "model_name": "cerebras/Cerebras-GPT-111M",
         "pruning_ratio": 0.0,