Upload folder using huggingface_hub (#3)

- 555b8665ea4f57cb272d908bd8d0535d7d486e7bed529c1faeae9ec81eeecab3 (8307c49ffcf37e343f7a5a298979df4120ce1eef)
- d85f477508f583854d96e35f07ebcc54525dc33e0ed1a7db641394dd76272818 (c58c776c6f6290f363f71919b1c080c8da03248c)

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/cyberagent-calm2-7b-chat-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("cyberagent/calm2-7b-chat")
     
     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/tmp2qoz9e4g",
+  "_name_or_path": "/tmp/tmp_q1qdd1d",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -21,7 +21,7 @@
   "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 sha256:8e7c44a89f8a4c494af42f10c9653bd4853e7228b98502aeefc044e5e9659e61
-size 4407107629
+oid sha256:69c42d98b4b165e0cb5eb76d6213dcc273f931d8a3475dedeb123789f3cc2c91
+size 4708787368

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsu7elb7yi",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsa15t0nm0",
         "batch_size": 1,
         "model_name": "cyberagent/calm2-7b-chat",
         "pruning_ratio": 0.0,