Text Generation
Transformers
Safetensors
French
English
qwen2
chat
qwen
qwen2.5
finetune
french
english
conversational
text-generation-inference
Instructions to use MaziyarPanahi/calme-3.1-instruct-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MaziyarPanahi/calme-3.1-instruct-3b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MaziyarPanahi/calme-3.1-instruct-3b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-3.1-instruct-3b") model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.1-instruct-3b", device_map="auto") 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 MaziyarPanahi/calme-3.1-instruct-3b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MaziyarPanahi/calme-3.1-instruct-3b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MaziyarPanahi/calme-3.1-instruct-3b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/MaziyarPanahi/calme-3.1-instruct-3b
- SGLang
How to use MaziyarPanahi/calme-3.1-instruct-3b 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 "MaziyarPanahi/calme-3.1-instruct-3b" \ --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": "MaziyarPanahi/calme-3.1-instruct-3b", "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 "MaziyarPanahi/calme-3.1-instruct-3b" \ --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": "MaziyarPanahi/calme-3.1-instruct-3b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use MaziyarPanahi/calme-3.1-instruct-3b with Docker Model Runner:
docker model run hf.co/MaziyarPanahi/calme-3.1-instruct-3b
3aff618fc084c047c37e55c56b78e9e422c36e9db59c1fb5e0877d5c03f46f76
Browse files- config.json +4 -5
- generation_config.json +10 -2
- model-00003-of-00003.safetensors +1 -1
- model.safetensors.index.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Qwen/Qwen2.5-3B",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
-
"eos_token_id":
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 2048,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 11008,
|
| 13 |
"max_position_embeddings": 32768,
|
| 14 |
-
"max_window_layers":
|
| 15 |
"model_type": "qwen2",
|
| 16 |
"num_attention_heads": 16,
|
| 17 |
"num_hidden_layers": 36,
|
|
@@ -24,7 +24,6 @@
|
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.45.2",
|
| 26 |
"use_cache": true,
|
| 27 |
-
"use_mrope": false,
|
| 28 |
"use_sliding_window": false,
|
| 29 |
-
"vocab_size":
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 2048,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 11008,
|
| 13 |
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 70,
|
| 15 |
"model_type": "qwen2",
|
| 16 |
"num_attention_heads": 16,
|
| 17 |
"num_hidden_layers": 36,
|
|
|
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.45.2",
|
| 26 |
"use_cache": true,
|
|
|
|
| 27 |
"use_sliding_window": false,
|
| 28 |
+
"vocab_size": 151936
|
| 29 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 151643,
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"transformers_version": "4.45.2"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
"transformers_version": "4.45.2"
|
| 14 |
}
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1138810568
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e754184c6cd33f0cf6edc6386cbec2b000c295527bd66e809fba64a4fc35fbff
|
| 3 |
size 1138810568
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 11041464320
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
tokenizer_config.json
CHANGED
|
@@ -195,7 +195,7 @@
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
-
"chat_template": "{% if
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
|
|
|
| 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",
|