tiennm99/cheahjs-free-llm-api-resources
1
0 Fork 0
mirror of https://github.com/tiennm99/cheahjs-free-llm-api-resources.git synced 2026-10-14 08:18:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: update models

Browse Source
This commit is contained in:
Jun Siang Cheah committed 2024-11-24 11:27:00 +00:00
1 parent 3c2523bded
commit efc103bb26
2 files changed
+16 -1
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+2 -1
View File
@@ -185,7 +185,7 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Phi-3-small instruct (128k)</td><td></td></tr>
<tr><td>Phi-3-small instruct (8k)</td><td></td></tr>
<tr><td>Phi-3.5-mini instruct (128k)</td><td></td></tr>
<tr><td rowspan="10"><a href="https://endpoints.ai.cloud.ovh.net/" target="_blank">OVH AI Endpoints (Free Alpha)</a></td><td rowspan="10">Token expires every week.</td><td>CodeLlama 13B Instruct</td><td>12 requests/minute</td></tr>
<tr><td rowspan="11"><a href="https://endpoints.ai.cloud.ovh.net/" target="_blank">OVH AI Endpoints (Free Alpha)</a></td><td rowspan="11">Token expires every week.</td><td>CodeLlama 13B Instruct</td><td>12 requests/minute</td></tr>
<tr><td>Codestral Mamba 7B v0.1</td><td>12 requests/minute</td></tr>
<tr><td>Llama 2 13B Chat</td><td>12 requests/minute</td></tr>
<tr><td>Llama 3 70B Instruct</td><td>12 requests/minute</td></tr>
@@ -193,6 +193,7 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Llama 3.1 70B Instruct</td><td>12 requests/minute</td></tr>
<tr><td>Mathstral 7B v0.1</td><td>12 requests/minute</td></tr>
<tr><td>Mistral 7B Instruct</td><td>12 requests/minute</td></tr>
<tr><td>Mistral Nemo 2407</td><td>12 requests/minute</td></tr>
<tr><td>Mixtral 8x22B Instruct</td><td>12 requests/minute</td></tr>
<tr><td>Mixtral 8x7B Instruct</td><td>12 requests/minute</td></tr>
<tr><td rowspan="40"><a href="https://developers.cloudflare.com/workers-ai" target="_blank">Cloudflare Workers AI</a></td><td rowspan="40"><a href="https://developers.cloudflare.com/workers-ai/platform/pricing/#free-allocation">10,000 tokens/day</a></td><td>Deepseek Coder 6.7B Base (AWQ)</td><td></td></tr>
src/pull_available_models.py
+14
View File
@@ -143,6 +143,11 @@ MODEL_TO_NAME_MAPPING = {
"lfm-40b": "Liquid LFM 40B",
"qwen/qwen2.5-coder-32b-instruct": "Qwen2.5 Coder 32B Instruct",
"thedrummer/unslopnemo-12b:free": "UnslopNemo 12B",
"mistral-nemo-instruct-2407": "Mistral Nemo 2407",
"google/gemini-exp-1121:free": "Gemini Experimental 1121",
"meta-llama/llama-3.1-70b-instruct-fp8": "Llama 3.1 70B Instruct (FP8)",
"google/learnlm-1.5-pro-experimental:free": "LearnLM 1.5 Pro Experimental",
"google/gemini-exp-1114:free": "Gemini Experimental 1114",
}
@@ -171,6 +176,12 @@ LAMBDA_IGNORED_MODELS = {
"hermes3-405b-fp8-128k"
}
OPENROUTER_IGNORED_MODELS = {
'google/gemini-exp-1121:free',
'google/learnlm-1.5-pro-experimental:free',
'google/gemini-exp-1114:free'
} # Ignore gemini experimental free models because rate limits mean they are unusable.
def get_model_name(id):
id = id.lower()
@@ -278,6 +289,9 @@ def fetch_openrouter_models(logger):
continue
if ":free" not in model["id"]:
continue
if model["id"] in OPENROUTER_IGNORED_MODELS:
logger.debug(f"Ignoring model {model['id']}")
continue
ret_models.append(
{
"id": model["id"],