Instructions to use katanemo/Arch-Function-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use katanemo/Arch-Function-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="katanemo/Arch-Function-7B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("katanemo/Arch-Function-7B") model = AutoModelForCausalLM.from_pretrained("katanemo/Arch-Function-7B") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use katanemo/Arch-Function-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "katanemo/Arch-Function-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "katanemo/Arch-Function-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/katanemo/Arch-Function-7B
- SGLang
How to use katanemo/Arch-Function-7B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "katanemo/Arch-Function-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "katanemo/Arch-Function-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "katanemo/Arch-Function-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "katanemo/Arch-Function-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use katanemo/Arch-Function-7B with Docker Model Runner:
docker model run hf.co/katanemo/Arch-Function-7B
Upload folder using huggingface_hub
Browse files- config.json +6 -2
- generation_config.json +1 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +2 -3
config.json
CHANGED
|
@@ -17,12 +17,16 @@
|
|
| 17 |
"num_hidden_layers": 28,
|
| 18 |
"num_key_value_heads": 4,
|
| 19 |
"rms_norm_eps": 1e-06,
|
| 20 |
-
"rope_scaling": null,
|
| 21 |
"rope_theta": 1000000.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"sliding_window": null,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
"use_cache": false,
|
| 27 |
"use_sliding_window": false,
|
| 28 |
"vocab_size": 152064
|
|
|
|
| 17 |
"num_hidden_layers": 28,
|
| 18 |
"num_key_value_heads": 4,
|
| 19 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 20 |
"rope_theta": 1000000.0,
|
| 21 |
+
"rope_scaling": {
|
| 22 |
+
"factor": 4.0,
|
| 23 |
+
"original_max_position_embeddings": 32768,
|
| 24 |
+
"type": "yarn"
|
| 25 |
+
},
|
| 26 |
"sliding_window": null,
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.43.2",
|
| 30 |
"use_cache": false,
|
| 31 |
"use_sliding_window": false,
|
| 32 |
"vocab_size": 152064
|
generation_config.json
CHANGED
|
@@ -10,5 +10,5 @@
|
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
| 13 |
-
"transformers_version": "4.
|
| 14 |
}
|
|
|
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.43.2"
|
| 14 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:395357dd1e8faf701220b23ca62ccdea71bab37dc30972b650bf4416cd8aa436
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:683a3bb00a549e8d9ae5298511157e302b20b656ae8ac7cb76f073622104852c
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e96fa5c4cc6ef3d71516c01451491b52182743bcab5f034c8086f4c4e346ca3
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:325c12cf5ebc490dca50fcbc94a8015dd5c0b71628434ea8b142949cf6a16c22
|
| 3 |
size 1089994880
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539
|
| 3 |
+
size 7031645
|
tokenizer_config.json
CHANGED
|
@@ -195,14 +195,13 @@
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"model_max_length": 131072,
|
| 203 |
"pad_token": "<|endoftext|>",
|
| 204 |
-
"padding_side": "right",
|
| 205 |
"split_special_tokens": false,
|
| 206 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
"unk_token": null
|
| 208 |
-
}
|
|
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"model_max_length": 131072,
|
| 203 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 204 |
"split_special_tokens": false,
|
| 205 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
"unk_token": null
|
| 207 |
+
}
|