Update dummy_agent_library.ipynb

When I execute
output = client.text_generation(
"The capital of france is",
max_new_tokens=100,
)

print(output)

with model meta-llama/Llama-3.2-3B-Instruct, it throws following error.

---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[5], line 3
1 # As seen in the LLM section, if we just do decoding, **the model will only stop when it predicts an EOS token**,
2 # and this does not happen here because this is a conversational (chat) model and we didn't apply the chat template it expects.
----> 3 output = client.text_generation(
4 "The capital of france is",
5 max_new_tokens=100,
6 )
8 print(output)

File c:\Python312\Lib\site-packages\huggingface_hub\inference\_client.py:2298, in InferenceClient.text_generation(self, prompt, details, stream, model, adapter_id, best_of, decoder_input_details, do_sample, frequency_penalty, grammar, max_new_tokens, repetition_penalty, return_full_text, seed, stop, stop_sequences, temperature, top_k, top_n_tokens, top_p, truncate, typical_p, watermark)
2296 model_id = model or self.model
2297 provider_helper = get_provider_helper(self.provider, task="text-generation", model=model_id)
-> 2298 request_parameters = provider_helper.prepare_request(
2299 inputs=prompt,
2300 parameters=parameters,
2301 extra_payload={"stream": stream},
2302 headers=self.headers,
2303 model=model_id,
2304 api_key=self.token,
2305 )
2307 # Handle errors separately for more precise error messages
2308 try:

File c:\Python312\Lib\site-packages\huggingface_hub\inference\_providers\_common.py:67, in TaskProviderHelper.prepare_request(self, inputs, parameters, headers, model, api_key, extra_payload)
64 api_key = self._prepare_api_key(api_key)
66 # mapped model from HF model ID
---> 67 provider_mapping_info = self._prepare_mapping_info(model)
69 # default HF headers + user headers (to customize in subclasses)
70 headers = self._prepare_headers(headers, api_key)

File c:\Python312\Lib\site-packages\huggingface_hub\inference\_providers\_common.py:131, in TaskProviderHelper._prepare_mapping_info(self, model)
128 raise ValueError(f"Model {model} is not supported by provider {self.provider}.")
130 if provider_mapping.task != self.task:
--> 131 raise ValueError(
132 f"Model {model} is not supported for task {self.task} and provider {self.provider}. "
133 f"Supported task: {provider_mapping.task}."
134 )
136 if provider_mapping.status == "staging":
137 logger.warning(
138 f"Model {model} is in staging mode for provider {self.provider}. Meant for test purposes only."
139 )

ValueError: Model meta-llama/Llama-3.2-3B-Instruct is not supported for task text-generation and provider together. Supported task: conversational.



But when I run with meta-llama/Llama-3.1-8B-Instruct, it works.


dummy_agent_library.ipynb

@@ -61,6 +61,8 @@
     "# os.environ[\"HF_TOKEN\"]=\"hf_xxxxxxxxxxx\"\n",
     "\n",
     "client = InferenceClient(\"meta-llama/Llama-3.2-3B-Instruct\")\n",
+
+    "# Model should be replaced with meta-llama/Llama-3.1-8B-Instruct or any other model that supports text_generation because meta-llama/Llama-3.2-3B-Instruct does'nt support it and throws error ValueError: Model meta-llama/Llama-3.2-3B-Instruct is not supported for task text-generation and provider together. Supported task: conversational.\n"
     "# if the outputs for next cells are wrong, the free model may be overloaded. You can also use this public endpoint that contains Llama-3.2-3B-Instruct\n",
     "#client = InferenceClient(\"https://jc26mwg228mkj8dw.us-east-1.aws.endpoints.huggingface.cloud\")"
    ]