RyanYr commited on
Commit
1bef897
1 Parent(s): fbf2b63

Model save

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- base_model: RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6
3
  library_name: transformers
4
- model_name: reflect_llm8B_llmMstlrg-om2-80k-SftT2Spsdp0to20kT02_b1.0
5
  tags:
6
  - generated_from_trainer
7
  - trl
@@ -9,9 +9,9 @@ tags:
9
  licence: license
10
  ---
11
 
12
- # Model Card for reflect_llm8B_llmMstlrg-om2-80k-SftT2Spsdp0to20kT02_b1.0
13
 
14
- This model is a fine-tuned version of [RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6](https://huggingface.co/RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -20,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
20
  from transformers import pipeline
21
 
22
  question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
- generator = pipeline("text-generation", model="RyanYr/reflect_llm8B_llmMstlrg-om2-80k-SftT2Spsdp0to20kT02_b1.0", device="cuda")
24
  output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
  print(output["generated_text"])
26
  ```
27
 
28
  ## Training procedure
29
 
30
- [<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/yyr/huggingface/runs/agrn59vv)
31
 
32
  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).
33
 
 
1
  ---
2
+ base_model: RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1
3
  library_name: transformers
4
+ model_name: reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b0.1
5
  tags:
6
  - generated_from_trainer
7
  - trl
 
9
  licence: license
10
  ---
11
 
12
+ # Model Card for reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b0.1
13
 
14
+ This model is a fine-tuned version of [RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1](https://huggingface.co/RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
20
  from transformers import pipeline
21
 
22
  question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="RyanYr/reflect_llm8B_om2-mstlrg300k460kLlm33130k_SftDpo-MgSpsdpT1_b0.1", device="cuda")
24
  output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
  print(output["generated_text"])
26
  ```
27
 
28
  ## Training procedure
29
 
30
+ [<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/yyr/huggingface/runs/6wi6rmp6)
31
 
32
  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).
33
 
last_checkpoint/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "RyanYr/reflect_llama8B_llama-mstlrg-om2-80k_sft-t2_lr1e-6",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "RyanYr/reflect_llm8B_om2-mstlrg-300k460k-t12_llm33-130k-t12_SFTt1-lr1e-6_DPOt1",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
last_checkpoint/model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54082993138518dcbd2df172e57f16a1fc90b5d3de73894e05ba334102200100
3
  size 4976706864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b66dfdb5c16b09d7603757c03ac3107e96de9c8f2bb66ff0369b3cb5d039a0
3
  size 4976706864
last_checkpoint/model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f0c08a34beefb8b507cc997700c533b80d0baa7829bd8c3e865aea2c5727623
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6509c94aa84e67d3038a6c8eb82174c30b511493cf1af0fb929de99d9457cc
3
  size 4999802720
last_checkpoint/model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7910d4f405f95202052a4cd9d48f36fa08f8989cf1bf98ab8798e0252fd80b84
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8f057acc7cba4b9e633c283196dfd4d715e93896f99b1d6f255b9eba3748fb
3
  size 4915916176
last_checkpoint/model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f066fb7da617469f49ca365bb9bf3fbcc8c30bb6b9d2b7c608a85a5f7381540
3
  size 1168147000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e691c1564837cd65afca3d275858ddb2b65352f903f513b149a97c211cd7d1
3
  size 1168147000
last_checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da61ce58627e264908468aa0fb4bf1bd7e305bbba34058c49399bdc105072242
3
  size 8056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5606f156e21af77aef1bc054d2396be4c8d76fd96441b071e84d4fe3084b5310
3
  size 8056