Hugging Face's logo

Romain-XV
/
80808422-ea8e-4824-ae24-7f3c88698326

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
mistral
Generated from Trainer
axolotl
dpo
trl
conversational
text-generation-inference
Model card Files Metrics Community
Romain-XV commited on
Commit
3f1e348
·
verified ·
1 Parent(s): 8c77563

End of training

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. adapter_model.bin +1 -1
  3. config.json +1 -2
  4. pytorch_model-00001-of-00004.bin +1 -1
  5. pytorch_model-00002-of-00004.bin +1 -1
  6. pytorch_model-00003-of-00004.bin +1 -1
README.md CHANGED
@@ -28,7 +28,7 @@ print(output["generated_text"])
28
 
29
  ## Training procedure
30
 
31
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/romain_fnc-xventures/Gradients-On-Demand/runs/cx014uko)
32
 
33
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
34
 
 
28
 
29
  ## Training procedure
30
 
31
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/romain_fnc-xventures/Gradients-On-Demand/runs/b1pe3qef)
32
 
33
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
34
 
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca8bc6b9c40dbee3cbe94d2e96d13382a54c668c52be8a8936201a7579286ff5
3
  size 671250634
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079085281394f6c8f684d345baf657566ba7cdf0378dcc96b554d1fe41473087
3
  size 671250634
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_attn_implementation_autoset": true,
3
  "_name_or_path": "Intel/neural-chat-7b-v3-3",
4
  "architectures": [
5
  "MistralForCausalLM"
@@ -21,7 +20,7 @@
21
  "rope_theta": 10000.0,
22
  "sliding_window": 4096,
23
  "tie_word_embeddings": false,
24
- "torch_dtype": "float16",
25
  "transformers_version": "4.46.0",
26
  "use_cache": false,
27
  "vocab_size": 32000
 
1
  {
 
2
  "_name_or_path": "Intel/neural-chat-7b-v3-3",
3
  "architectures": [
4
  "MistralForCausalLM"
 
20
  "rope_theta": 10000.0,
21
  "sliding_window": 4096,
22
  "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
  "transformers_version": "4.46.0",
25
  "use_cache": false,
26
  "vocab_size": 32000
pytorch_model-00001-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87b1be796accf9c1d5c1d8e61a38e19815df6b4a8498d9902a9c7dd9fc950c30
3
  size 4924890283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9ee5fd5003382acc32bd7aa2e800c7785d6b28445e3473155e9d208e53364cd
3
  size 4924890283
pytorch_model-00002-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f8b004977369a194b567c72f53fa619a75100b00faa509c470df040e844589
3
  size 4993591120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a8e8c82b33c9a733d59c7538fd6c1b407009993cf5fb2a9fa251a8300450cd8
3
  size 4993591120
pytorch_model-00003-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cee96edb8f65dc813341d8c2d46a3b9c55e3356749b6235184aef0ee838d77bd
3
  size 4974198733
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86aeb528daf86754a53010f0b2a7df413b88323b312f4db64116b18228e0184f
3
  size 4974198733