tiennm99/cheahjs-free-llm-api-resources
1
0 Fork 0
mirror of https://github.com/tiennm99/cheahjs-free-llm-api-resources.git synced 2026-10-19 20:14:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

add vertex ai gemini experimental, hyperbolic llama 3.1 405b base (fp16)

Browse Source
This commit is contained in:
Jun Siang Cheah committed 2024-08-27 15:33:41 +01:00
1 parent 6f64b3dc62
commit 58aa632580
2 files changed
+14 -5
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+7 -3
View File
@@ -68,10 +68,14 @@ This lists various services that provide free access or credits towards API-base
<td>embedding-001</td>
<td>1500 requests/min<br>100 content/batch</td>
</tr><tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden" target="_blank">Google Cloud Vertex AI</a></td>
<td>Very stringent payment verification for Google Cloud.</td>
<td rowspan="2"><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden" target="_blank">Google Cloud Vertex AI</a></td>
<td rowspan="2">Very stringent payment verification for Google Cloud.</td>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama3-405b-instruct-maas" target="_blank">Llama 3.1 405B Instruct</a></td>
<td>Llama 3.1 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini Experimental</a></td>
<td>Experimental Gemini model. (Not the same as the experimental models on AI Studio)<br>2 requests/minute</td>
</tr><tr>
<td><a href="https://glhf.chat/" target="_blank">glhf.chat (Free Beta)</a></td>
<td></td>
@@ -92,8 +96,8 @@ This lists various services that provide free access or credits towards API-base
<td>Various open models</td>
<td></td>
</tr><tr><td rowspan="9"><a href="https://app.hyperbolic.xyz/" target="_blank">Hyperbolic (Free Testing Period)</a></td><td rowspan="9"></td><td>Hermes 3 Llama 3.1 70B</td><td>200 requests/minute</td></tr>
<tr><td>Hermes 3 Llama 3.1 70B (FP8)</td><td>200 requests/minute</td></tr>
<tr><td>Llama 3 70B Instruct</td><td>200 requests/minute</td></tr>
<tr><td>Llama 3.1 405B</td><td>200 requests/minute</td></tr>
<tr><td>Llama 3.1 405B Base (FP8)</td><td>200 requests/minute</td></tr>
<tr><td>Llama 3.1 405B Instruct</td><td>200 requests/minute</td></tr>
<tr><td>Llama 3.1 70B Instruct</td><td>200 requests/minute</td></tr>
src/pull_available_models.py
+7 -2
View File
@@ -70,6 +70,7 @@ MODEL_TO_NAME_MAPPING = {
"meta-llama/llama-3-8b-instruct:free": "Llama 3 8B Instruct",
"meta-llama/llama-3.1-8b-instruct:free": "Llama 3.1 8B Instruct",
"meta-llama/meta-llama-3-70b-instruct": "Llama 3 70B Instruct",
"meta-llama/meta-llama-3.1-405b": "Llama 3.1 405B",
"meta-llama/meta-llama-3.1-405b-fp8": "Llama 3.1 405B Base (FP8)",
"meta-llama/meta-llama-3.1-405b-instruct": "Llama 3.1 405B Instruct",
"meta-llama/meta-llama-3.1-70b-instruct": "Llama 3.1 70B Instruct",
@@ -489,10 +490,14 @@ def main():
</tr>"""
table += """<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden" target="_blank">Google Cloud Vertex AI</a></td>
<td>Very stringent payment verification for Google Cloud.</td>
<td rowspan="2"><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden" target="_blank">Google Cloud Vertex AI</a></td>
<td rowspan="2">Very stringent payment verification for Google Cloud.</td>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama3-405b-instruct-maas" target="_blank">Llama 3.1 405B Instruct</a></td>
<td>Llama 3.1 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini Experimental</a></td>
<td>Experimental Gemini model. (Not the same as the experimental models on AI Studio)<br>2 requests/minute</td>
</tr>"""
table += """<tr>