diff --git a/README.md b/README.md index f386e77..fa65e00 100644 --- a/README.md +++ b/README.md @@ -93,7 +93,7 @@ This lists various services that provide free access or credits towards API-base Mistral 7B Instruct12 requests/minute Mixtral 8x22B Instruct12 requests/minute Mixtral 8x7B Instruct12 requests/minute -Cloudflare Workers AI10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models.Deepseek Coder 6.7B Base (AWQ) +Cloudflare Workers AI10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models.Deepseek Coder 6.7B Base (AWQ) Deepseek Coder 6.7B Instruct (AWQ) Deepseek Math 7B Instruct Discolm German 7B v1 (AWQ) @@ -110,6 +110,8 @@ This lists various services that provide free access or credits towards API-base Llama 3 8B Instruct Llama 3 8B Instruct (AWQ) Llama 3.1 8B Instruct +Llama 3.1 8B Instruct (AWQ) +Llama 3.1 8B Instruct (FP8) LlamaGuard 7B (AWQ) Mistral 7B Instruct v0.1 Mistral 7B Instruct v0.1 (AWQ) @@ -197,7 +199,7 @@ This lists various services that provide free access or credits towards API-base Jamba/Jurrasic-2 - AI21 + NLP Cloud $15 Phone number verification Various open models diff --git a/src/README_template.md b/src/README_template.md index 534df6b..029650e 100644 --- a/src/README_template.md +++ b/src/README_template.md @@ -75,7 +75,7 @@ This lists various services that provide free access or credits towards API-base Jamba/Jurrasic-2 - AI21 + NLP Cloud $15 Phone number verification Various open models diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 7c7b846..98cb082 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -18,6 +18,8 @@ MODEL_TO_NAME_MAPPING = { "@cf/meta/llama-3-8b-instruct-awq": "Llama 3 8B Instruct (AWQ)", "@cf/meta/llama-3-8b-instruct": "Llama 3 8B Instruct", "@cf/meta/llama-3.1-8b-instruct": "Llama 3.1 8B Instruct", + "@cf/meta/llama-3.1-8b-instruct-awq": "Llama 3.1 8B Instruct (AWQ)", + "@cf/meta/llama-3.1-8b-instruct-fp8": "Llama 3.1 8B Instruct (FP8)", "@cf/microsoft/phi-2": "Phi-2", "@cf/mistral/mistral-7b-instruct-v0.1-vllm": "Mistral 7B Instruct v0.1", "@cf/mistral/mistral-7b-instruct-v0.1": "Mistral 7B Instruct v0.1", @@ -410,7 +412,7 @@ def main(): embedding-001 1500 requests/min
100 content/batch """ - + table += """ glhf.chat (Free Beta)