Update README.md

README.md

@@ -36,6 +36,13 @@ pipeline_tag: text-generation
 
 **🔥  **
 
+| Model                       | HumanEval+ |
+|-----------------------------|------------|
+| WizardCoder-Python-34B-V1.0 | 64.6       |
+| GPT-3.5 (December 2023)     | 64.6       |
+| **OpenChat 3.5 1210**       | **63.4**   |
+| OpenHermes 2.5              | 41.5       |
+
   <div align="center" style="justify-content: center; align-items: center; "'>
   <img src="https://github.com/alpayariyak/openchat/blob/master/assets/Untitled%20design-17.png?raw=true" style="width: 100%;  border-radius: 0.5em">
   </div>
@@ -55,6 +62,8 @@ If you want to deploy the server as an online service, you can use `--api-keys s
 <details>
   <summary>Example request (click to expand)</summary>
 
+Default Mode (Chat & Coding)
+
 ```bash
 curl http://localhost:18888/v1/chat/completions \
   -H "Content-Type: application/json" \
@@ -64,49 +73,39 @@ curl http://localhost:18888/v1/chat/completions \
   }'
 ```
 
-Coding Mode
+Mathematical Reasoning Mode
 
 ```bash
 curl http://localhost:18888/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
     "model": "openchat_3.5",
-    "condition": "Code",
-    "messages": [{"role": "user", "content": "Write an aesthetic TODO app using HTML5 and JS, in a single file. You should use round corners and gradients to make it more aesthetic."}]
+    "condition": "Math Correct",
+    "messages": [{"role": "user", "content": "10.3 − 7988.8133 = "}]
   }'
 ```
 
 </details>
 
-| Model        | Size | Context | Weights                                                     | Serving                                                                                                     |
-|--------------|------|---------|-------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------|
-| OpenChat 3.5 | 7B   | 8192    | [Huggingface](https://huggingface.co/openchat/openchat_3.5) | `python -m ochat.serving.openai_api_server --model openchat/openchat_3.5 --engine-use-ray --worker-use-ray` |
+| Model             | Size | Context | Weights                                                          | Serving                                                                                                          |
+|-------------------|------|---------|------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------|
+| OpenChat 3.5 1210 | 7B   | 8192    | [Huggingface](https://huggingface.co/openchat/openchat_3.5_1210) | `python -m ochat.serving.openai_api_server --model openchat/openchat_3.5_1210 --engine-use-ray --worker-use-ray` |
 
-For inference with Huggingface Transformers (slow and not recommended), follow the conversation template provided below.
+### Conversation templates
 
-<details>
-  <summary>Conversation templates (click to expand)</summary>
+Default Mode (GPT4 Correct)
 
-```python
-import transformers
-tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat_3.5")
+```
+GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:
+```
 
-# Single-turn
-tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids
-assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
+Mathematical Reasoning Mode
 
-# Multi-turn
-tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids
-assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
-
-# Coding Mode
-tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
-assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]
+```
+Math Correct User: 10.3 − 7988.8133=<|end_of_turn|>Math Correct Assistant:
 ```
 
-</details>
-
-The GPT4 template is also available as the integrated `tokenizer.chat_template`, 
+The default (GPT4 Correct) template is also available as the integrated `tokenizer.chat_template`, 
 which can be used instead of manually specifying the template:
 
 ```python
@@ -121,8 +120,6 @@ assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 42
 
 ## Comparison with [X.AI Grok models](https://x.ai/)
 
-
-
 |                   | License     | # Param | Average  | MMLU | HumanEval | MATH     | GSM8k    |
 |-------------------|-------------|---------|----------|------|-----------|----------|----------|
 | OpenChat 3.5 1210 | Apache-2.0  | **7B**  | **60.1** | 65.3 | **68.9**  | **28.9** | **77.3** |