sharpenb commited on
Commit
209e527
1 Parent(s): 5909864

Upload folder using huggingface_hub (#3)

Browse files

- f2a89abc70008def73b02c9aff29257f9e3b2b3c5a402bf30d7d473050139b72 (8c62f6c7d01ae87ca2ec773cccb081277587599f)

Files changed (5) hide show
  1. README.md +2 -2
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. plots.png +0 -0
  5. smash_config.json +1 -1
README.md CHANGED
@@ -34,7 +34,7 @@ tags:
34
 
35
  ## Results
36
 
37
- Detailed efficiency metrics coming soon!
38
 
39
  **Frequently Asked Questions**
40
  - ***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:
61
  from transformers import AutoModelForCausalLM, AutoTokenizer
62
 
63
  model = AutoModelForCausalLM.from_pretrained("PrunaAI/echarlaix-tiny-random-mistral-bnb-4bit-smashed",
64
- trust_remote_code=True)
65
  tokenizer = AutoTokenizer.from_pretrained("echarlaix/tiny-random-mistral")
66
 
67
  input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
 
34
 
35
  ## Results
36
 
37
+ ![image info](./plots.png)
38
 
39
  **Frequently Asked Questions**
40
  - ***How does the compression work?*** The model is compressed with llm-int8.
 
61
  from transformers import AutoModelForCausalLM, AutoTokenizer
62
 
63
  model = AutoModelForCausalLM.from_pretrained("PrunaAI/echarlaix-tiny-random-mistral-bnb-4bit-smashed",
64
+ trust_remote_code=True, device_map='auto')
65
  tokenizer = AutoTokenizer.from_pretrained("echarlaix/tiny-random-mistral")
66
 
67
  input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/tmp/tmpit1eecui",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
@@ -22,7 +22,7 @@
22
  "quantization_config": {
23
  "bnb_4bit_compute_dtype": "bfloat16",
24
  "bnb_4bit_quant_type": "fp4",
25
- "bnb_4bit_use_double_quant": true,
26
  "llm_int8_enable_fp32_cpu_offload": false,
27
  "llm_int8_has_fp16_weight": false,
28
  "llm_int8_skip_modules": [
 
1
  {
2
+ "_name_or_path": "/tmp/tmp7m1_kbqa",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
 
22
  "quantization_config": {
23
  "bnb_4bit_compute_dtype": "bfloat16",
24
  "bnb_4bit_quant_type": "fp4",
25
+ "bnb_4bit_use_double_quant": false,
26
  "llm_int8_enable_fp32_cpu_offload": false,
27
  "llm_int8_has_fp16_weight": false,
28
  "llm_int8_skip_modules": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acae8e1bc8d6e4eebe85d0c499ac98d692ffb025946cf88accd26d8b28969df8
3
- size 4130904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8465167e8113d3a48c51378e63113e6a3d39efb9bdaad0f84d77d445bd4855c9
3
+ size 4112630
plots.png ADDED
smash_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
- "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsptckisrj",
12
  "batch_size": 1,
13
  "model_name": "echarlaix/tiny-random-mistral",
14
  "pruning_ratio": 0.0,
 
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsrfk5yr9w",
12
  "batch_size": 1,
13
  "model_name": "echarlaix/tiny-random-mistral",
14
  "pruning_ratio": 0.0,