sharpenb commited on
Commit
0c763f6
1 Parent(s): 8bbd687

Upload folder using huggingface_hub (#3)

Browse files

- e134953e8e9313a2d7f12a2ecec709d793ac03d465a95c1c468e86891d762a0d (cff667308514eb7bae7b52e6ba3f6c81a8f99dcf)

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/TinyLlama-TinyLlama-1.1B-intermediate-step-1431k-3T-bnb-4bit-smashed",
64
- trust_remote_code=True)
65
  tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T")
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/TinyLlama-TinyLlama-1.1B-intermediate-step-1431k-3T-bnb-4bit-smashed",
64
+ trust_remote_code=True, device_map='auto')
65
  tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T")
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/tmpqgdkq_rj",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -20,7 +20,7 @@
20
  "quantization_config": {
21
  "bnb_4bit_compute_dtype": "bfloat16",
22
  "bnb_4bit_quant_type": "fp4",
23
- "bnb_4bit_use_double_quant": true,
24
  "llm_int8_enable_fp32_cpu_offload": false,
25
  "llm_int8_has_fp16_weight": false,
26
  "llm_int8_skip_modules": [
 
1
  {
2
+ "_name_or_path": "/tmp/tmptaz43u2x",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
20
  "quantization_config": {
21
  "bnb_4bit_compute_dtype": "bfloat16",
22
  "bnb_4bit_quant_type": "fp4",
23
+ "bnb_4bit_use_double_quant": false,
24
  "llm_int8_enable_fp32_cpu_offload": false,
25
  "llm_int8_has_fp16_weight": false,
26
  "llm_int8_skip_modules": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:667dfbfe30ce1a4986988fe3cc4196f1cd069a59cd01f9e8202fcbc370ef6453
3
- size 762453335
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f474629295a69e593b6737ee45cbad88b4faa950bd3ad484e6e586e96769e5
3
+ size 807426286
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/modelsigd2k76z",
12
  "batch_size": 1,
13
  "model_name": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
14
  "pruning_ratio": 0.0,
 
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/models36mu6te2",
12
  "batch_size": 1,
13
  "model_name": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
14
  "pruning_ratio": 0.0,