Instructions to use yoinked/simai-codegen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use yoinked/simai-codegen with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B") model = PeftModel.from_pretrained(base_model, "yoinked/simai-codegen") - Transformers
How to use yoinked/simai-codegen with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="yoinked/simai-codegen") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yoinked/simai-codegen", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use yoinked/simai-codegen with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yoinked/simai-codegen" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yoinked/simai-codegen", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/yoinked/simai-codegen
- SGLang
How to use yoinked/simai-codegen 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 "yoinked/simai-codegen" \ --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": "yoinked/simai-codegen", "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 "yoinked/simai-codegen" \ --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": "yoinked/simai-codegen", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use yoinked/simai-codegen with Docker Model Runner:
docker model run hf.co/yoinked/simai-codegen
Upload folder using huggingface_hub
Browse files- README.md +3 -3
- adapter_config.json +49 -47
- adapter_model.safetensors +2 -2
- chat_template.jinja +54 -54
- tokenizer_config.json +30 -30
README.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: Qwen/Qwen2.5-Coder-
|
| 3 |
library_name: peft
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
-
- base_model:adapter:Qwen/Qwen2.5-Coder-
|
| 7 |
- lora
|
| 8 |
- transformers
|
| 9 |
---
|
|
@@ -204,4 +204,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 204 |
[More Information Needed]
|
| 205 |
### Framework versions
|
| 206 |
|
| 207 |
-
- PEFT 0.
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-1.5B
|
| 3 |
library_name: peft
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B
|
| 7 |
- lora
|
| 8 |
- transformers
|
| 9 |
---
|
|
|
|
| 204 |
[More Information Needed]
|
| 205 |
### Framework versions
|
| 206 |
|
| 207 |
+
- PEFT 0.20.0
|
adapter_config.json
CHANGED
|
@@ -1,48 +1,50 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alora_invocation_tokens": null,
|
| 3 |
-
"alpha_pattern": {},
|
| 4 |
-
"arrow_config": null,
|
| 5 |
-
"auto_mapping": null,
|
| 6 |
-
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-
|
| 7 |
-
"bias": "none",
|
| 8 |
-
"corda_config": null,
|
| 9 |
-
"ensure_weight_tying": false,
|
| 10 |
-
"eva_config": null,
|
| 11 |
-
"exclude_modules": null,
|
| 12 |
-
"fan_in_fan_out": false,
|
| 13 |
-
"inference_mode": true,
|
| 14 |
-
"init_lora_weights": true,
|
| 15 |
-
"layer_replication": null,
|
| 16 |
-
"layers_pattern": null,
|
| 17 |
-
"layers_to_transform": null,
|
| 18 |
-
"loftq_config": {},
|
| 19 |
-
"lora_alpha": 32,
|
| 20 |
-
"lora_bias": false,
|
| 21 |
-
"lora_dropout": 0.05,
|
| 22 |
-
"lora_ga_config": null,
|
| 23 |
-
"megatron_config": null,
|
| 24 |
-
"megatron_core": "megatron.core",
|
| 25 |
-
"modules_to_save": null,
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
|
|
|
|
|
|
| 48 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"monteclora_config": null,
|
| 27 |
+
"peft_type": "LORA",
|
| 28 |
+
"peft_version": "0.20.0",
|
| 29 |
+
"qalora_group_size": 16,
|
| 30 |
+
"r": 16,
|
| 31 |
+
"rank_pattern": {},
|
| 32 |
+
"revision": null,
|
| 33 |
+
"target_modules": [
|
| 34 |
+
"q_proj",
|
| 35 |
+
"up_proj",
|
| 36 |
+
"o_proj",
|
| 37 |
+
"down_proj",
|
| 38 |
+
"v_proj",
|
| 39 |
+
"gate_proj",
|
| 40 |
+
"k_proj"
|
| 41 |
+
],
|
| 42 |
+
"target_parameters": null,
|
| 43 |
+
"task_type": "CAUSAL_LM",
|
| 44 |
+
"trainable_token_indices": null,
|
| 45 |
+
"use_bdlora": null,
|
| 46 |
+
"use_dora": false,
|
| 47 |
+
"use_qalora": false,
|
| 48 |
+
"use_rslora": false,
|
| 49 |
+
"velora_config": null
|
| 50 |
}
|
adapter_model.safetensors
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:f458cffcfbeaad641a48d7a89adfdbbe50e01f93d25038dd616608c462700b5d
|
| 3 |
+
size 73911112
|
chat_template.jinja
CHANGED
|
@@ -1,54 +1,54 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
-
{{- messages[0]['content'] }}
|
| 5 |
-
{%- else %}
|
| 6 |
-
{{- 'You are a helpful assistant.' }}
|
| 7 |
-
{%- endif %}
|
| 8 |
-
{{- "\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>" }}
|
| 9 |
-
{%- for tool in tools %}
|
| 10 |
-
{{- "\n" }}
|
| 11 |
-
{{- tool | tojson }}
|
| 12 |
-
{%- endfor %}
|
| 13 |
-
{{- "\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" }}
|
| 14 |
-
{%- else %}
|
| 15 |
-
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
-
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
-
{%- else %}
|
| 18 |
-
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
-
{%- endif %}
|
| 20 |
-
{%- endif %}
|
| 21 |
-
{%- for message in messages %}
|
| 22 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
-
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
-
{%- elif message.role == "assistant" %}
|
| 25 |
-
{{- '<|im_start|>' + message.role }}
|
| 26 |
-
{%- if message.content %}
|
| 27 |
-
{{- '\n' + message.content }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{%- for tool_call in message.tool_calls %}
|
| 30 |
-
{%- if tool_call.function is defined %}
|
| 31 |
-
{%- set tool_call = tool_call.function %}
|
| 32 |
-
{%- endif %}
|
| 33 |
-
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
-
{{- tool_call.name }}
|
| 35 |
-
{{- '", "arguments": ' }}
|
| 36 |
-
{{- tool_call.arguments | tojson }}
|
| 37 |
-
{{- '}\n</tool_call>' }}
|
| 38 |
-
{%- endfor %}
|
| 39 |
-
{{- '<|im_end|>\n' }}
|
| 40 |
-
{%- elif message.role == "tool" %}
|
| 41 |
-
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
-
{{- '<|im_start|>user' }}
|
| 43 |
-
{%- endif %}
|
| 44 |
-
{{- '\n<tool_response>\n' }}
|
| 45 |
-
{{- message.content }}
|
| 46 |
-
{{- '\n</tool_response>' }}
|
| 47 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
-
{{- '<|im_end|>\n' }}
|
| 49 |
-
{%- endif %}
|
| 50 |
-
{%- endif %}
|
| 51 |
-
{%- endfor %}
|
| 52 |
-
{%- if add_generation_prompt %}
|
| 53 |
-
{{- '<|im_start|>assistant\n' }}
|
| 54 |
-
{%- endif %}
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
tokenizer_config.json
CHANGED
|
@@ -1,30 +1,30 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": null,
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|endoftext|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"<|im_start|>",
|
| 10 |
-
"<|im_end|>",
|
| 11 |
-
"<|object_ref_start|>",
|
| 12 |
-
"<|object_ref_end|>",
|
| 13 |
-
"<|box_start|>",
|
| 14 |
-
"<|box_end|>",
|
| 15 |
-
"<|quad_start|>",
|
| 16 |
-
"<|quad_end|>",
|
| 17 |
-
"<|vision_start|>",
|
| 18 |
-
"<|vision_end|>",
|
| 19 |
-
"<|vision_pad|>",
|
| 20 |
-
"<|image_pad|>",
|
| 21 |
-
"<|video_pad|>"
|
| 22 |
-
],
|
| 23 |
-
"is_local": false,
|
| 24 |
-
"local_files_only": false,
|
| 25 |
-
"model_max_length": 32768,
|
| 26 |
-
"pad_token": "<|endoftext|>",
|
| 27 |
-
"split_special_tokens": false,
|
| 28 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
-
"unk_token": null
|
| 30 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 32768,
|
| 26 |
+
"pad_token": "<|endoftext|>",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|