初始化项目，由ModelHub XC社区提供模型
Model: duyntnet/Hermes-2-Pro-Llama-3-8B-imatrix-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
62
.gitattributes
vendored
Normal file
62
.gitattributes
vendored
Normal file
@@ -0,0 +1,62 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Hermes-2-Pro-Llama-3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ1_M.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ1_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fb1fdf95cbd3a498d0a6eb7384f5745a3cd108fd83de0f1c6a1d9f8ca6f759d
|
||||
size 2162106336
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ1_S.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ1_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:23f9d25055445bfdb2ef80e05ef1cd27356356c39a39a6fe51658a7e67dd6127
|
||||
size 2019762144
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ2_M.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d659c273bab10427377bd823882111fa2c47d3cd2f236a1409adbacaa34c1107
|
||||
size 2948428768
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ2_S.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ2_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:118faa7f1ebd722f20d6133856212bd4140faaafeff3fdf83bda68383a807a3b
|
||||
size 2758636512
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ2_XS.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ2_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4e7870b58a09e6a2c8e7a266c9ce2cc88af238341e12d24e3a1f2aa87044ba14
|
||||
size 2605916128
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ2_XXS.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ2_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1b1dd3e2a0f4bdce88ea02a1e13214d4d0d1d38670f9e6ad920870088a93588b
|
||||
size 2399346656
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ3_M.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6a6b6ef6e7682b82cc3346598fed0872ffc630c9dab51580019b192974e11b58
|
||||
size 3784988640
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ3_S.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ3_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f923dfbb933d0a1b00247b47fb03ce2bed5603a07e56f6cf9961802442face21
|
||||
size 3682490336
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ3_XS.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b2e57a105356b61d7b3b67adc95f59da775d64de3006dbb557fb5c3542af3b4f
|
||||
size 3518912480
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ3_XXS.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9a10653dfe899d5ad6dc8a949361b665a35438958a23f24409358c58c6a46c6e
|
||||
size 3275060192
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ4_NL.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d96df573b0eb6eb6f8f0f8923eca34b9f100c1ef04cf2f63ea3e0015ba239d0b
|
||||
size 4678171616
|
||||
3
Hermes-2-Pro-Llama-3-8B-IQ4_XS.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c34964f67ccfdaee1b9eafe232c404806264f8a63bd21a96968b730cd1d8bbe
|
||||
size 4447841248
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q2_K.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0fc94a0e2bd507ba91262d81a8a8fb598eb0158b5ee5bdf4fc693e50b8718478
|
||||
size 3179283424
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q2_K_S.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q2_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2768af00a7018ec450f90bb2eafca35a9c495fa4eb4e33a01b293fc43ac58c80
|
||||
size 2988966880
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:62299a6ae924e01252ccd8953541e80b9801bc71c0553d65c18ed670cb503478
|
||||
size 4322121696
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0199aeea61b8cd2de9bf7fc044124070e6abfc00cc75858e05ec8a0cdf847227
|
||||
size 4019083232
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:179af705b30a12e1c07d99190eb5b8635996e64b1be982d5f15ede127fd22704
|
||||
size 3664664544
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q4_0.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1df118a950753f3c89df3bde550457a49767d16b51a511e9d686eb3e6d35e6fb
|
||||
size 4676074464
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q4_1.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:de647c953117077e1d333c7cb176a056f4855ab16de02e7742af4319f226d540
|
||||
size 5130443744
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8fc7dd1cf245fa56a47780cb1bfc5f7ce364571d43a663e955dd0859cf008798
|
||||
size 4920916960
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2508ec80f2f9208eea0d7b83116cb3db81d71d2103b32a798a1acbe9f31f8ff6
|
||||
size 4692851680
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q5_0.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:07d7f07e90784ac6eee818f140d2e74bc232e97b4acbe0893f24185d27c9f9c6
|
||||
size 5614173152
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q5_1.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q5_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:836c69e534897b73cbadbd363d354eef7b4365a9add5b924b9b4ff6b9801abaa
|
||||
size 6068542432
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:708e7ad3e2a24f021447742e4b25462f31911a967a898b47b98669507bfaadb9
|
||||
size 5733186528
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ad094610f08038a6b73e94469f91dee76bbeaabf39adf2aa871af3ed886dcd27
|
||||
size 5599493088
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q6_K.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1ef5e1dcf4be64c3fe2c21d9c5f940563c283b90db95ae58675ffde813a879bd
|
||||
size 6596222944
|
||||
3
Hermes-2-Pro-Llama-3-8B-Q8_0.gguf
Normal file
3
Hermes-2-Pro-Llama-3-8B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a8f51dac7c8897b7d0abb178489f909728dc08d77153c6cbd0dfb7d1840a0713
|
||||
size 8541050848
|
||||
122
README.md
Normal file
122
README.md
Normal file
@@ -0,0 +1,122 @@
|
||||
---
|
||||
license: other
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
inference: false
|
||||
tags:
|
||||
- transformers
|
||||
- gguf
|
||||
- imatrix
|
||||
- Hermes-2-Pro-Llama-3-8B
|
||||
---
|
||||
Quantizations of https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B
|
||||
|
||||
|
||||
# From original readme
|
||||
|
||||
## Prompt Format
|
||||
|
||||
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
|
||||
|
||||
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
|
||||
|
||||
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
|
||||
|
||||
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
|
||||
|
||||
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
|
||||
```
|
||||
<|im_start|>system
|
||||
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
|
||||
<|im_start|>user
|
||||
Hello, who are you?<|im_end|>
|
||||
<|im_start|>assistant
|
||||
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
|
||||
```
|
||||
|
||||
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
|
||||
`tokenizer.apply_chat_template()` method:
|
||||
|
||||
```python
|
||||
messages = [
|
||||
{"role": "system", "content": "You are Hermes 2."},
|
||||
{"role": "user", "content": "Hello, who are you?"}
|
||||
]
|
||||
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
|
||||
model.generate(**gen_input)
|
||||
```
|
||||
|
||||
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
|
||||
that the model continues with an assistant response.
|
||||
|
||||
To utilize the prompt format without a system prompt, simply leave the line out.
|
||||
|
||||
## Prompt Format for Function Calling
|
||||
|
||||
Our model was trained on specific system prompts and structures for Function Calling.
|
||||
|
||||
You should use the system role with this message, followed by a function signature json as this example shows here.
|
||||
```
|
||||
<|im_start|>system
|
||||
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
|
||||
<tool_call>
|
||||
{"arguments": <args-dict>, "name": <function-name>}
|
||||
</tool_call><|im_end|>
|
||||
```
|
||||
|
||||
To complete the function call, create a user prompt that follows the above system prompt, like so:
|
||||
```
|
||||
<|im_start|>user
|
||||
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
|
||||
```
|
||||
|
||||
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
|
||||
```
|
||||
<|im_start|>assistant
|
||||
<tool_call>
|
||||
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
|
||||
</tool_call><|im_end|>
|
||||
```
|
||||
|
||||
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
|
||||
```
|
||||
<|im_start|>tool
|
||||
<tool_response>
|
||||
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
|
||||
</tool_response>
|
||||
<|im_end|>
|
||||
```
|
||||
|
||||
The assistant will then read in that data from the function's response, and generate a natural language response:
|
||||
```
|
||||
<|im_start|>assistant
|
||||
The stock fundamentals data for Tesla (TSLA) are as follows:
|
||||
- **Symbol**: TSLA
|
||||
- **Company Name**: Tesla, Inc.
|
||||
- **Sector**: Consumer Cyclical
|
||||
- **Industry**: Auto Manufacturers
|
||||
- **Market Capitalization**: $566,160,130,480
|
||||
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
|
||||
- **Price-to-Book Ratio (PB Ratio)**: 9.04
|
||||
- **Dividend Yield**: N/A
|
||||
- **Trailing Earnings Per Share (EPS)**: $4.3
|
||||
- **Beta Value of the Stock**: 2.42
|
||||
- **52-Week High Price of the Stock**: $299.29
|
||||
- **52-Week Low Price of the Stock**: $152.37
|
||||
|
||||
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
|
||||
```
|
||||
|
||||
## Prompt Format for JSON Mode / Structured Outputs
|
||||
|
||||
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
|
||||
|
||||
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
|
||||
|
||||
```
|
||||
<|im_start|>system
|
||||
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
|
||||
```
|
||||
|
||||
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
|
||||
Reference in New Issue
Block a user