Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
axolotl
conversational
text-generation-inference
Inference Endpoints
ehartford commited on
Commit
3dc4484
1 Parent(s): b9fd220

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -23
README.md CHANGED
@@ -1,13 +1,59 @@
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
- model-index:
5
- - name: qwen-out
6
- results: []
 
 
 
 
 
 
 
7
  ---
8
 
9
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
- should probably proofread and complete it, then remove this comment. -->
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
 
12
  [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
13
  <details><summary>See axolotl config</summary>
@@ -376,24 +422,6 @@ special_tokens:
376
 
377
  </details><br>
378
 
379
- # qwen-out
380
-
381
- This model was trained from scratch on the None dataset.
382
- It achieves the following results on the evaluation set:
383
- - Loss: 0.3931
384
-
385
- ## Model description
386
-
387
- More information needed
388
-
389
- ## Intended uses & limitations
390
-
391
- More information needed
392
-
393
- ## Training and evaluation data
394
-
395
- More information needed
396
-
397
  ## Training procedure
398
 
399
  ### Training hyperparameters
 
1
  ---
2
+ license: other
3
+ base_model: Qwen/Qwen1.5-110B
4
  tags:
5
  - generated_from_trainer
6
+ - axolotl
7
+ datasets:
8
+ - cognitivecomputations/Dolphin-2.9
9
+ - teknium/OpenHermes-2.5
10
+ - m-a-p/CodeFeedback-Filtered-Instruction
11
+ - cognitivecomputations/dolphin-coder
12
+ - cognitivecomputations/samantha-data
13
+ - microsoft/orca-math-word-problems-200k
14
+ - Locutusque/function-calling-chatml
15
+ - internlm/Agent-FLAN
16
  ---
17
 
18
+ # Dolphin 2.9.1 Qwen 110b 🐬
19
+
20
+ Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
21
+
22
+ Discord: https://discord.gg/8fbBeC7ZGx
23
+
24
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
25
+
26
+ Our appreciation for the sponsors of Dolphin 2.9.1:
27
+ - [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xH100 node
28
+
29
+ This model is based on Qwen1.5-110B, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE)
30
+
31
+ The base model has 32k context, and the full-weight fine-tuning was with 8k sequence length.
32
+
33
+ This model was trained FFT on parameters selected by [Laser Scanner](https://github.com/cognitivecomputations/laserRMT/blob/main/laser_scanner.py), using ChatML prompt template format.
34
+
35
+ example:
36
+
37
+ ```
38
+ <|im_start|>system
39
+ You are Dolphin, a helpful AI assistant.<|im_end|>
40
+ <|im_start|>user
41
+ {prompt}<|im_end|>
42
+ <|im_start|>assistant
43
+
44
+ ```
45
+
46
+ Dolphin-2.9.1 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
47
+
48
+ Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
49
+
50
+ Dolphin is licensed according to Meta's Llama license. We grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. Dolphin was trained on data generated from GPT4, among other models.
51
+
52
+ ## Evals
53
+
54
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/U86Zu-MzLq4rECJRAAvgq.png)
55
+
56
+ ## Training
57
 
58
  [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
59
  <details><summary>See axolotl config</summary>
 
422
 
423
  </details><br>
424
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
425
  ## Training procedure
426
 
427
  ### Training hyperparameters