Upload folder using huggingface_hub (#3)

- 90f87707d67ece533cfcbda5938891405d4d7e77a683a12071668e36ec79dabb (524de05404e3f3eef60c129659b1cfd67bd1a88f)
- e35e34d55c44feebbb0bab5f9742a8f01c5f054e5eaa334184c8e0c1edbf3dae (24057dd3239283d3af07688f6f6fc3e1b5924952)

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/openchat-openchat_3.5-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("openchat/openchat_3.5")
     
     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/tmpdap_lyke",
+  "_name_or_path": "/tmp/tmp51g1_rii",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -18,7 +18,7 @@
   "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:c1e66a952d32931b6e2a57714311b914fde91d41e7d1f8b872db4718e251b276
-size 4125720383
+oid sha256:b74594a2ff171b437610c38f519708b0460b40a7ffe04f00ff45057978f6aab0
+size 4450870264

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsfhyzh1v3",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelssz3idgim",
         "batch_size": 1,
         "model_name": "openchat/openchat_3.5",
         "pruning_ratio": 0.0,