Hugging Face's logo

Vaishu16
/
SmolLM2-FT-DPO

Text Generation
Transformers
Safetensors
llama
trl
dpo
smol-course
module_1
orpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Vaishu16 commited on
Commit
a8c50fd
·
verified ·
1 Parent(s): 73ee794

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. README.md +1 -0
  2. config.json +1 -7
  3. model.safetensors +1 -1
README.md CHANGED
@@ -5,6 +5,7 @@ tags:
5
  - dpo
6
  - smol-course
7
  - module_1
 
8
  ---
9
 
10
  # Model Card for Model ID
 
5
  - dpo
6
  - smol-course
7
  - module_1
8
+ - orpo
9
  ---
10
 
11
  # Model Card for Model ID
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -27,12 +27,6 @@
27
  "rope_theta": 100000,
28
  "tie_word_embeddings": true,
29
  "torch_dtype": "float32",
30
- "transformers.js_config": {
31
- "kv_cache_dtype": {
32
- "fp16": "float16",
33
- "q4f16": "float16"
34
- }
35
- },
36
  "transformers_version": "4.47.1",
37
  "use_cache": false,
38
  "vocab_size": 49152
 
1
  {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
27
  "rope_theta": 100000,
28
  "tie_word_embeddings": true,
29
  "torch_dtype": "float32",
 
 
 
 
 
 
30
  "transformers_version": "4.47.1",
31
  "use_cache": false,
32
  "vocab_size": 49152
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d7e230d1cebb131df08d9717d3f7afde689d26a8905f9087a4f49e16f341292
3
  size 538090408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34d63b79a99e4dd6948371b31bad7cb2790ee1914d273dae5a931dabb836883
3
  size 538090408