初始化项目，由ModelHub XC社区提供模型
Model: RedHatAI/Qwen3-4B-Thinking-2507-quantized.w4a16 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
210
README.md
Normal file
210
README.md
Normal file
@@ -0,0 +1,210 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
pipeline_tag: text-generation
|
||||
base_model:
|
||||
- Qwen/Qwen3-4B-Thinking-2507
|
||||
tags:
|
||||
- neuralmagic
|
||||
- redhat
|
||||
- llmcompressor
|
||||
- quantized
|
||||
- INT4
|
||||
---
|
||||
|
||||
# Qwen3-4B-Thinking-2507.w4a16
|
||||
|
||||
## Model Overview
|
||||
- **Model Architecture:** Qwen3ForCausalLM
|
||||
- **Input:** Text
|
||||
- **Output:** Text
|
||||
- **Model Optimizations:**
|
||||
- **Weight quantization:** INT4
|
||||
- **Intended Use Cases:**
|
||||
- Reasoning.
|
||||
- Function calling.
|
||||
- Subject matter experts via fine-tuning.
|
||||
- Multilingual instruction following.
|
||||
- Translation.
|
||||
- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws).
|
||||
- **Release Date:** 05/05/2025
|
||||
- **Version:** 1.0
|
||||
- **Model Developers:** RedHat (Neural Magic)
|
||||
|
||||
### Model Optimizations
|
||||
|
||||
This model was obtained by quantizing the weights of [Qwen/Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) to INT4 data type.
|
||||
This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.
|
||||
|
||||
Only the weights of the linear operators within transformers blocks are quantized.
|
||||
Weights are quantized using a symmetric per-group scheme, with group size 128.
|
||||
The [GPTQ](https://arxiv.org/abs/2210.17323) algorithm is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library.
|
||||
|
||||
|
||||
## Deployment
|
||||
|
||||
This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
model_id = "RedHatAI/Qwen3-4B-Thinking-2507.w4a16"
|
||||
number_gpus = 1
|
||||
sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=20, min_p=0, max_tokens=256)
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
|
||||
messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]
|
||||
|
||||
prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
|
||||
|
||||
llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
|
||||
|
||||
outputs = llm.generate(prompts, sampling_params)
|
||||
|
||||
generated_text = outputs[0].outputs[0].text
|
||||
print(generated_text)
|
||||
```
|
||||
|
||||
vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
|
||||
|
||||
## Creation
|
||||
|
||||
<details>
|
||||
<summary>Creation details</summary>
|
||||
This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below.
|
||||
|
||||
|
||||
```python
|
||||
from llmcompressor.modifiers.quantization import GPTQModifier
|
||||
from llmcompressor.transformers import oneshot
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
# Load model
|
||||
model_stub = "Qwen/Qwen3-4B-Thinking"
|
||||
model_name = model_stub.split("/")[-1]
|
||||
|
||||
num_samples = 1024
|
||||
max_seq_len = 8192
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(model_stub)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_stub)
|
||||
|
||||
def preprocess_fn(example):
|
||||
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
|
||||
|
||||
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
|
||||
ds = ds.map(preprocess_fn)
|
||||
|
||||
# Configure the quantization algorithm and scheme
|
||||
recipe = GPTQModifier(
|
||||
ignore: ["lm_head"]
|
||||
config_groups={"group_0": {"targets": ["Linear"], "weights": { "num_bits": 4, "type": int, "strategy": "group", "group_size": 128, "symmetric": true, "dynamic": false, "observer": "mse" } } },
|
||||
dampening_frac=0.01,
|
||||
)
|
||||
|
||||
# Apply quantization
|
||||
oneshot(
|
||||
model=model,
|
||||
dataset=ds,
|
||||
recipe=recipe,
|
||||
max_seq_length=max_seq_len,
|
||||
num_calibration_samples=num_samples,
|
||||
)
|
||||
|
||||
# Save to disk in compressed-tensors format
|
||||
save_path = model_name + "-quantized.w4a16"
|
||||
model.save_pretrained(save_path)
|
||||
tokenizer.save_pretrained(save_path)
|
||||
print(f"Model and tokenizer saved to: {save_path}")
|
||||
```
|
||||
</details>
|
||||
|
||||
|
||||
|
||||
## Evaluation
|
||||
|
||||
The model was evaluated on the ifeval, mmlu_pro and gsm8k_platinum using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), on reasoning tasks using [lighteval](https://github.com/neuralmagic/lighteval/tree/reasoning).
|
||||
[vLLM](https://docs.vllm.ai/en/stable/) was used for all evaluations.
|
||||
|
||||
|
||||
<details>
|
||||
<summary>Evaluation details</summary>
|
||||
|
||||
Deploy using vllm to create an OpenAI-compatible API endpoint:
|
||||
|
||||
- vLLM:
|
||||
```shell
|
||||
vllm serve RedHatAI/Qwen3-4B-Thinking-2507.w4a16 --max-model-len 262144 --reasoning-parser deepseek_r1
|
||||
```
|
||||
|
||||
**lm-evaluation-harness**
|
||||
```
|
||||
lm_eval --model local-chat-completions \
|
||||
--tasks mmlu_pro_chat \
|
||||
--model_args "model=RedHatAI/Qwen3-4B-Thinking-2507.w4a16,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \
|
||||
--num_fewshot 0 \
|
||||
--apply_chat_template \
|
||||
--gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000
|
||||
```
|
||||
|
||||
```
|
||||
lm_eval --model local-chat-completions \
|
||||
--tasks ifeval \
|
||||
--model_args "model=RedHatAI/Qwen3-4B-Thinking-2507.w4a16,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \
|
||||
--num_fewshot 0 \
|
||||
--apply_chat_template \
|
||||
--gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000
|
||||
```
|
||||
|
||||
```
|
||||
lm_eval --model local-chat-completions \
|
||||
--tasks gsm8k_platinum_cot_llama \
|
||||
--model_args "model=RedHatAI/Qwen3-4B-Thinking-2507.w4a16,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \
|
||||
--num_fewshot 0 \
|
||||
--apply_chat_template \
|
||||
--gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000
|
||||
```
|
||||
|
||||
**lighteval**
|
||||
|
||||
lighteval_model_arguments.yaml
|
||||
```yaml
|
||||
model_parameters:
|
||||
model_name: RedHatAI/Qwen3-4B-Thinking-2507.w4a16
|
||||
dtype: auto
|
||||
gpu_memory_utilization: 0.9
|
||||
max_model_length: 40960
|
||||
generation_parameters:
|
||||
temperature: 0.6
|
||||
top_k: 20
|
||||
min_p: 0.0
|
||||
top_p: 0.95
|
||||
max_new_tokens: 32000
|
||||
```
|
||||
|
||||
```
|
||||
lighteval endpoint litellm lighteval_model_arguments.yaml \
|
||||
"aime25|0,math_500|0,gpqa:diamond|0"
|
||||
```
|
||||
|
||||
|
||||
</details>
|
||||
|
||||
### Accuracy
|
||||
|
||||
|
||||
| Benchmark | Qwen3-4B Thinking | Qwen3-4B Thinking.w4a16 (this model) | Recovery (%) |
|
||||
|--------|-------------|-------------------|--------------|
|
||||
| GSM8k Platinum (0-shot) | 95.26 | 94.87 | 99.59 |
|
||||
| MMLU-Pro (0-shot) | 73.63 | 71.33 | 96.87 |
|
||||
| IfEval (0-shot) |90.17 | 90.21 | 100.04 |
|
||||
| AIME 2025 | 73.75 | 72.08 | 97.74 |
|
||||
| GPQA diamond | 68.94 | 63.26 | 91.76 |
|
||||
| Math 500 | 89.45 | 90.63 | 101.31 |
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
86
chat_template.jinja
Normal file
86
chat_template.jinja
Normal file
@@ -0,0 +1,86 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# 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>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\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" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n<think>\n' }}
|
||||
{%- endif %}
|
||||
103
config.json
Normal file
103
config.json
Normal file
@@ -0,0 +1,103 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"quantization_config": {
|
||||
"config_groups": {
|
||||
"group_0": {
|
||||
"format": "pack-quantized",
|
||||
"input_activations": null,
|
||||
"output_activations": null,
|
||||
"targets": [
|
||||
"Linear"
|
||||
],
|
||||
"weights": {
|
||||
"actorder": "static",
|
||||
"block_structure": null,
|
||||
"dynamic": false,
|
||||
"group_size": 128,
|
||||
"num_bits": 4,
|
||||
"observer": "mse",
|
||||
"observer_kwargs": {},
|
||||
"strategy": "group",
|
||||
"symmetric": true,
|
||||
"type": "int"
|
||||
}
|
||||
}
|
||||
},
|
||||
"format": "pack-quantized",
|
||||
"global_compression_ratio": null,
|
||||
"ignore": [
|
||||
"lm_head"
|
||||
],
|
||||
"kv_cache_scheme": null,
|
||||
"quant_method": "compressed-tensors",
|
||||
"quantization_status": "compressed",
|
||||
"sparsity_config": {},
|
||||
"transform_config": {},
|
||||
"version": "0.12.3.a20251013"
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.0"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:74d4f9c8b90d9d0766b0a68c6c150d7ee9aca4892e2975eeb81385c338401991
|
||||
size 3429751984
|
||||
27
recipe.yaml
Normal file
27
recipe.yaml
Normal file
@@ -0,0 +1,27 @@
|
||||
quant_stage:
|
||||
quant_modifiers:
|
||||
GPTQModifier:
|
||||
config_groups:
|
||||
group_0:
|
||||
targets: [Linear]
|
||||
weights:
|
||||
num_bits: 4
|
||||
type: int
|
||||
symmetric: true
|
||||
group_size: 128
|
||||
strategy: group
|
||||
block_structure: null
|
||||
dynamic: false
|
||||
actorder: !!python/object/apply:compressed_tensors.quantization.quant_args.ActivationOrdering [
|
||||
static]
|
||||
observer: mse
|
||||
observer_kwargs: {}
|
||||
input_activations: null
|
||||
output_activations: null
|
||||
format: null
|
||||
targets: [Linear]
|
||||
ignore: [lm_head]
|
||||
block_size: 128
|
||||
dampening_frac: 0.01
|
||||
actorder: static
|
||||
offload_hessians: false
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b7a6a993d40b42d517297bb247ff66679e5bc9dd7a5143be0620faf210b42861
|
||||
size 11422753
|
||||
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 262144,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user