初始化项目，由ModelHub XC社区提供模型
Model: RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4 Source: Original Platform
This commit is contained in:
ModelHub XC
58
.gitattributes
vendored
Normal file
58
.gitattributes
vendored
Normal file
@@ -0,0 +1,58 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.pb 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
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
602089ffe66d2ecf/lighteval|gpqa:diamond|0/cd454966f6c36e03/GENERATIVE.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
602089ffe66d2ecf/lighteval|aime24|0/f524bd322cd3c513/GENERATIVE.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
602089ffe66d2ecf/lighteval|aime25|0/7f35b587257182a3/GENERATIVE.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tekken.json filter=lfs diff=lfs merge=lfs -text
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:219d3c968e8f3d521b9ffcaa7d3ebcd699725b9fffd1e6bd9a33fd2db365625e
|
||||
size 236076
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d58f6d660db34bcefdd4cb00e5849db3a87f89e3bb20bf8ad21bd9c672453b29
|
||||
size 200017
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa1d69fb3c978fb569df793d266b9a5e258fdcd0860ec6d4c8c2978e6bbdf2ab
|
||||
size 614039
|
||||
353
README.md
Normal file
353
README.md
Normal file
@@ -0,0 +1,353 @@
|
||||
---
|
||||
tags:
|
||||
- fp4
|
||||
- vllm
|
||||
language:
|
||||
- en
|
||||
- de
|
||||
- fr
|
||||
- it
|
||||
- pt
|
||||
- hi
|
||||
- es
|
||||
- th
|
||||
pipeline_tag: text-generation
|
||||
license: apache-2.0
|
||||
base_model: unsloth/Mistral-Small-3.2-24B-Instruct-2506
|
||||
---
|
||||
|
||||
# Mistral-Small-3.2-24B-Instruct-2506-NVFP4
|
||||
|
||||
## Model Overview
|
||||
- **Model Architecture:** unsloth/Mistral-Small-3.2-24B-Instruct-2506
|
||||
- **Input:** Text
|
||||
- **Output:** Text
|
||||
- **Model Optimizations:**
|
||||
- **Weight quantization:** FP4
|
||||
- **Activation quantization:** FP4
|
||||
- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
|
||||
- **Release Date:** 10/29/2025
|
||||
- **Version:** 1.0
|
||||
- **Model Developers:** RedHatAI
|
||||
|
||||
This model is a quantized version of [unsloth/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506).
|
||||
It was evaluated on a several tasks to assess the its quality in comparison to the unquatized model.
|
||||
|
||||
### Model Optimizations
|
||||
|
||||
This model was obtained by quantizing the weights and activations of [unsloth/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506) to FP4 data type, ready for inference with vLLM>=0.9.1
|
||||
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 and activations of the linear operators within transformers blocks are quantized using [LLM Compressor](https://github.com/vllm-project/llm-compressor).
|
||||
|
||||
## Deployment
|
||||
|
||||
### Use with vLLM
|
||||
|
||||
1. Initialize vLLM server:
|
||||
```
|
||||
vllm serve RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4 --tensor_parallel_size 1 --tokenizer_mode mistral
|
||||
```
|
||||
|
||||
2. Send requests to the server:
|
||||
|
||||
```python
|
||||
from openai import OpenAI
|
||||
|
||||
# Modify OpenAI's API key and API base to use vLLM's API server.
|
||||
openai_api_key = "EMPTY"
|
||||
openai_api_base = "http://<your-server-host>:8000/v1"
|
||||
|
||||
client = OpenAI(
|
||||
api_key=openai_api_key,
|
||||
base_url=openai_api_base,
|
||||
)
|
||||
|
||||
model = "RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4"
|
||||
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
|
||||
]
|
||||
|
||||
outputs = client.chat.completions.create(
|
||||
model=model,
|
||||
messages=messages,
|
||||
)
|
||||
|
||||
generated_text = outputs.choices[0].message.content
|
||||
print(generated_text)
|
||||
```
|
||||
|
||||
## Creation
|
||||
|
||||
This model was created by applying [LLM Compressor with calibration samples from UltraChat](https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_w4a4_fp4/llama3_example.py), as presented in the code snipet below.
|
||||
|
||||
<details>
|
||||
|
||||
```python
|
||||
from datasets import load_dataset
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
from llmcompressor import oneshot
|
||||
from llmcompressor.modifiers.quantization import QuantizationModifier
|
||||
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
|
||||
from llmcompressor.utils import dispatch_for_generation
|
||||
|
||||
MODEL_ID = "unsloth/Mistral-Small-3.2-24B-Instruct-2506"
|
||||
|
||||
# Load model.
|
||||
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype="auto")
|
||||
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
|
||||
|
||||
DATASET_ID = "HuggingFaceH4/ultrachat_200k"
|
||||
DATASET_SPLIT = "train_sft"
|
||||
|
||||
# Select number of samples. 512 samples is a good place to start.
|
||||
# Increasing the number of samples can improve accuracy.
|
||||
NUM_CALIBRATION_SAMPLES = 512
|
||||
MAX_SEQUENCE_LENGTH = 2048
|
||||
|
||||
# Load dataset and preprocess.
|
||||
ds = load_dataset(DATASET_ID, split=f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]")
|
||||
ds = ds.shuffle(seed=42)
|
||||
|
||||
def preprocess(example):
|
||||
return {
|
||||
"text": tokenizer.apply_chat_template(
|
||||
example["messages"],
|
||||
tokenize=False,
|
||||
)
|
||||
}
|
||||
|
||||
ds = ds.map(preprocess)
|
||||
|
||||
# Tokenize inputs.
|
||||
def tokenize(sample):
|
||||
return tokenizer(
|
||||
sample["text"],
|
||||
padding=False,
|
||||
max_length=MAX_SEQUENCE_LENGTH,
|
||||
truncation=True,
|
||||
add_special_tokens=False,
|
||||
)
|
||||
|
||||
ds = ds.map(tokenize, remove_columns=ds.column_names)
|
||||
|
||||
# Configure the quantization algorithm and scheme.
|
||||
# In this case, we:
|
||||
# * quantize the weights to fp4 with per group 16 via ptq
|
||||
# * calibrate a global_scale for activations, which will be used to
|
||||
# quantize activations to fp4 on the fly
|
||||
smoothing_strength = 0.9
|
||||
recipe = [
|
||||
SmoothQuantModifier(smoothing_strength=smoothing_strength),
|
||||
QuantizationModifier(
|
||||
ignore=["re:.*lm_head.*"],
|
||||
config_groups={
|
||||
"group_0": {
|
||||
"targets": ["Linear"],
|
||||
"weights": {
|
||||
"num_bits": 4,
|
||||
"type": "float",
|
||||
"strategy": "tensor_group",
|
||||
"group_size": 16,
|
||||
"symmetric": True,
|
||||
"observer": "mse",
|
||||
},
|
||||
"input_activations": {
|
||||
"num_bits": 4,
|
||||
"type": "float",
|
||||
"strategy": "tensor_group",
|
||||
"group_size": 16,
|
||||
"symmetric": True,
|
||||
"dynamic": "local",
|
||||
"observer": "minmax",
|
||||
},
|
||||
}
|
||||
},
|
||||
)
|
||||
]
|
||||
|
||||
# Save to disk in compressed-tensors format.
|
||||
SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-NVFP4"
|
||||
|
||||
# Apply quantization.
|
||||
oneshot(
|
||||
model=model,
|
||||
dataset=ds,
|
||||
recipe=recipe,
|
||||
max_seq_length=MAX_SEQUENCE_LENGTH,
|
||||
num_calibration_samples=NUM_CALIBRATION_SAMPLES,
|
||||
output_dir=SAVE_DIR,
|
||||
)
|
||||
|
||||
print("\n\n")
|
||||
print("========== SAMPLE GENERATION ==============")
|
||||
dispatch_for_generation(model)
|
||||
input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
|
||||
output = model.generate(input_ids, max_new_tokens=100)
|
||||
print(tokenizer.decode(output[0]))
|
||||
print("==========================================\n\n")
|
||||
|
||||
model.save_pretrained(SAVE_DIR, save_compressed=True)
|
||||
tokenizer.save_pretrained(SAVE_DIR)
|
||||
```
|
||||
</details>
|
||||
|
||||
## Evaluation
|
||||
|
||||
This model was evaluated on the well-known OpenLLM v1, OpenLLM v2 and HumanEval_64 benchmarks using [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness).
|
||||
|
||||
### Accuracy
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Category</th>
|
||||
<th>Metric</th>
|
||||
<th>unsloth/Mistral-Small-3.2-24B-Instruct-2506</th>
|
||||
<th>RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4</th>
|
||||
<th>Recovery</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<!-- OpenLLM V1 -->
|
||||
<tr>
|
||||
<td rowspan="7"><b>OpenLLM V1</b></td>
|
||||
<td>arc_challenge</td>
|
||||
<td>68.52</td>
|
||||
<td>66.98</td>
|
||||
<td>97.75</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>gsm8k</td>
|
||||
<td>89.61</td>
|
||||
<td>87.11</td>
|
||||
<td>97.21</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>hellaswag</td>
|
||||
<td>85.70</td>
|
||||
<td>85.11</td>
|
||||
<td>99.31</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>mmlu</td>
|
||||
<td>81.06</td>
|
||||
<td>79.43</td>
|
||||
<td>97.99</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>truthfulqa_mc2</td>
|
||||
<td>61.35</td>
|
||||
<td>60.34</td>
|
||||
<td>98.35</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>winogrande</td>
|
||||
<td>83.27</td>
|
||||
<td>81.61</td>
|
||||
<td>98.01</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><b>Average</b></td>
|
||||
<td><b>78.25</b></td>
|
||||
<td><b>76.76</b></td>
|
||||
<td><b>98.10</b></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="7"><b>OpenLLM V2</b></td>
|
||||
<td>BBH (3-shot)</td>
|
||||
<td>65.86</td>
|
||||
<td>64.05</td>
|
||||
<td>97.25</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MMLU-Pro (5-shot)</td>
|
||||
<td>50.84</td>
|
||||
<td>48.45</td>
|
||||
<td>95.30</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MuSR (0-shot)</td>
|
||||
<td>39.15</td>
|
||||
<td>40.21</td>
|
||||
<td>102.71</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>IFEval (0-shot)</td>
|
||||
<td>84.05</td>
|
||||
<td>84.41</td>
|
||||
<td>100.43</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>GPQA (0-shot)</td>
|
||||
<td>33.14</td>
|
||||
<td>32.55</td>
|
||||
<td>98.22</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Math-|v|-5 (4-shot)</td>
|
||||
<td>41.69</td>
|
||||
<td>37.76</td>
|
||||
<td>90.57</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><b>Average</b></td>
|
||||
<td><b>52.46</b></td>
|
||||
<td><b>51.24</b></td>
|
||||
<td><b>97.68</b></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2"><b>Coding</b></td>
|
||||
<td>HumanEval_64 pass@2</td>
|
||||
<td>88.88</td>
|
||||
<td>88.84</td>
|
||||
<td>99.95</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
|
||||
|
||||
### Reproduction
|
||||
|
||||
The results were obtained using the following commands:
|
||||
|
||||
<details>
|
||||
|
||||
```
|
||||
lm_eval \
|
||||
--model vllm \
|
||||
--model_args pretrained="RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True,enforce_eager=True\
|
||||
--apply_chat_template \
|
||||
--fewshot_as_multiturn \
|
||||
--tasks openllm \
|
||||
--batch_size auto
|
||||
```
|
||||
|
||||
|
||||
#### OpenLLM v2
|
||||
```
|
||||
lm_eval \
|
||||
--model vllm \
|
||||
--model_args pretrained="RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True,enforce_eager=True\
|
||||
--apply_chat_template \
|
||||
--fewshot_as_multiturn \
|
||||
--tasks leaderboard \
|
||||
--batch_size auto
|
||||
```
|
||||
|
||||
#### HumanEval_64
|
||||
```
|
||||
lm_eval \
|
||||
--model vllm \
|
||||
--model_args pretrained="RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True,enforce_eager=True\
|
||||
--apply_chat_template \
|
||||
--fewshot_as_multiturn \
|
||||
--tasks humaneval_64_instruct \
|
||||
--batch_size auto
|
||||
|
||||
```
|
||||
</details>
|
||||
300
chat_template.jinja
Normal file
300
chat_template.jinja
Normal file
@@ -0,0 +1,300 @@
|
||||
{#- Unsloth template fixes #}
|
||||
{%- set yesterday_day = strftime_now("%d") %}
|
||||
{%- set yesterday_month = strftime_now("%m") %}
|
||||
{%- set yesterday_year = strftime_now("%Y") %}
|
||||
{%- set today_date = yesterday_year + '-' + yesterday_month + '-' + yesterday_day %}
|
||||
{%- if yesterday_day == '01' %}
|
||||
{#- Jinja doesnt allow minus 1 date - Unsloth alternative #}
|
||||
{%- if yesterday_month == '01' %}
|
||||
{%- set yesterday_day = '31' %}
|
||||
{%- set yesterday_month = '12' %}
|
||||
{%- if yesterday_year == '2024' %}
|
||||
{%- set yesterday_year = '2023' %}
|
||||
{%- elif yesterday_year == '2025' %}
|
||||
{%- set yesterday_year = '2024' %}
|
||||
{%- elif yesterday_year == '2026' %}
|
||||
{%- set yesterday_year = '2025' %}
|
||||
{%- elif yesterday_year == '2027' %}
|
||||
{%- set yesterday_year = '2026' %}
|
||||
{%- elif yesterday_year == '2028' %}
|
||||
{%- set yesterday_year = '2027' %}
|
||||
{%- elif yesterday_year == '2029' %}
|
||||
{%- set yesterday_year = '2028' %}
|
||||
{%- elif yesterday_year == '2030' %}
|
||||
{%- set yesterday_year = '2029' %}
|
||||
{%- elif yesterday_year == '2031' %}
|
||||
{%- set yesterday_year = '2030' %}
|
||||
{%- elif yesterday_year == '2032' %}
|
||||
{%- set yesterday_year = '2031' %}
|
||||
{%- elif yesterday_year == '1970' %}
|
||||
{#- Stop llama_cpp from erroring out #}
|
||||
{%- set yesterday_year = '1970' %}
|
||||
{%- else %}
|
||||
{{- raise_exception('Unsloth custom template does not support years > 2032. Error year = [' + yesterday_year + ']') }}
|
||||
{%- endif %}
|
||||
{%- elif yesterday_month == '02' %}
|
||||
{%- set yesterday_day = '31' %}
|
||||
{%- set yesterday_month = '01' %}
|
||||
{%- elif yesterday_month == '03' %}
|
||||
{%- set yesterday_month = '02' %}
|
||||
{%- set yesterday_day = '28' %}
|
||||
{%- if yesterday_year == '2024' %}
|
||||
{%- set yesterday_day = '29' %}
|
||||
{%- elif yesterday_year == '2028' %}
|
||||
{%- set yesterday_day = '29' %}
|
||||
{%- elif yesterday_year == '2032' %}
|
||||
{%- set yesterday_day = '29' %}
|
||||
{%- elif yesterday_year == '1970' %}
|
||||
{#- Stop llama_cpp from erroring out #}
|
||||
{%- set yesterday_day = '29' %}
|
||||
{%- else %}
|
||||
{{- raise_exception('Unsloth custom template does not support years > 2032. Error year = [' + yesterday_year + ']') }}
|
||||
{%- endif %}
|
||||
{%- elif yesterday_month == '04' %}
|
||||
{%- set yesterday_day = '31' %}
|
||||
{%- set yesterday_month = '03' %}
|
||||
{%- elif yesterday_month == '05' %}
|
||||
{%- set yesterday_day = '30' %}
|
||||
{%- set yesterday_month = '04' %}
|
||||
{%- elif yesterday_month == '06' %}
|
||||
{%- set yesterday_day = '31' %}
|
||||
{%- set yesterday_month = '05' %}
|
||||
{%- elif yesterday_month == '07' %}
|
||||
{%- set yesterday_day = '30' %}
|
||||
{%- set yesterday_month = '06' %}
|
||||
{%- elif yesterday_month == '08' %}
|
||||
{%- set yesterday_day = '31' %}
|
||||
{%- set yesterday_month = '07' %}
|
||||
{%- elif yesterday_month == '09' %}
|
||||
{%- set yesterday_day = '31' %}
|
||||
{%- set yesterday_month = '08' %}
|
||||
{%- elif yesterday_month == '10' %}
|
||||
{%- set yesterday_day = '30' %}
|
||||
{%- set yesterday_month = '09' %}
|
||||
{%- elif yesterday_month == '11' %}
|
||||
{%- set yesterday_day = '31' %}
|
||||
{%- set yesterday_month = '10' %}
|
||||
{%- elif yesterday_month == '12' %}
|
||||
{%- set yesterday_day = '30' %}
|
||||
{%- set yesterday_month = '11' %}
|
||||
{%- endif %}
|
||||
{%- elif yesterday_day == '02' %}
|
||||
{%- set yesterday_day = '01' %}
|
||||
{%- elif yesterday_day == '03' %}
|
||||
{%- set yesterday_day = '02' %}
|
||||
{%- elif yesterday_day == '04' %}
|
||||
{%- set yesterday_day = '03' %}
|
||||
{%- elif yesterday_day == '05' %}
|
||||
{%- set yesterday_day = '04' %}
|
||||
{%- elif yesterday_day == '06' %}
|
||||
{%- set yesterday_day = '05' %}
|
||||
{%- elif yesterday_day == '07' %}
|
||||
{%- set yesterday_day = '06' %}
|
||||
{%- elif yesterday_day == '08' %}
|
||||
{%- set yesterday_day = '07' %}
|
||||
{%- elif yesterday_day == '09' %}
|
||||
{%- set yesterday_day = '08' %}
|
||||
{%- elif yesterday_day == '10' %}
|
||||
{%- set yesterday_day = '09' %}
|
||||
{%- elif yesterday_day == '11' %}
|
||||
{%- set yesterday_day = '10' %}
|
||||
{%- elif yesterday_day == '12' %}
|
||||
{%- set yesterday_day = '11' %}
|
||||
{%- elif yesterday_day == '13' %}
|
||||
{%- set yesterday_day = '12' %}
|
||||
{%- elif yesterday_day == '14' %}
|
||||
{%- set yesterday_day = '13' %}
|
||||
{%- elif yesterday_day == '15' %}
|
||||
{%- set yesterday_day = '14' %}
|
||||
{%- elif yesterday_day == '16' %}
|
||||
{%- set yesterday_day = '15' %}
|
||||
{%- elif yesterday_day == '17' %}
|
||||
{%- set yesterday_day = '16' %}
|
||||
{%- elif yesterday_day == '18' %}
|
||||
{%- set yesterday_day = '17' %}
|
||||
{%- elif yesterday_day == '19' %}
|
||||
{%- set yesterday_day = '18' %}
|
||||
{%- elif yesterday_day == '20' %}
|
||||
{%- set yesterday_day = '19' %}
|
||||
{%- elif yesterday_day == '21' %}
|
||||
{%- set yesterday_day = '20' %}
|
||||
{%- elif yesterday_day == '22' %}
|
||||
{%- set yesterday_day = '21' %}
|
||||
{%- elif yesterday_day == '23' %}
|
||||
{%- set yesterday_day = '22' %}
|
||||
{%- elif yesterday_day == '24' %}
|
||||
{%- set yesterday_day = '23' %}
|
||||
{%- elif yesterday_day == '25' %}
|
||||
{%- set yesterday_day = '24' %}
|
||||
{%- elif yesterday_day == '26' %}
|
||||
{%- set yesterday_day = '25' %}
|
||||
{%- elif yesterday_day == '27' %}
|
||||
{%- set yesterday_day = '26' %}
|
||||
{%- elif yesterday_day == '28' %}
|
||||
{%- set yesterday_day = '27' %}
|
||||
{%- elif yesterday_day == '29' %}
|
||||
{%- set yesterday_day = '28' %}
|
||||
{%- elif yesterday_day == '30' %}
|
||||
{%- set yesterday_day = '29' %}
|
||||
{%- elif yesterday_day == '31' %}
|
||||
{%- set yesterday_day = '30' %}
|
||||
{%- endif %}
|
||||
{#- Edits made by Unsloth #}
|
||||
{%- set yesterday_date = yesterday_year + '-' + yesterday_month + '-' + yesterday_day %}
|
||||
{%- set default_system_message = "You are Mistral-Small-3.2-24B-Instruct-2506, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYou power an AI assistant called Le Chat.\nYour knowledge base was last updated on 2023-10-01.\nThe current date is " + today_date + ".\n\nWhen you\'re not sure about some information or when the user\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\'t have the information and avoid making up anything.\nIf the user\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\").\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. \"yesterday\" is " + yesterday_date + ") and when asked about information at specific dates, you discard information that is at another date.\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\nNext sections describe the capabilities that you have.\n\n# WEB BROWSING INSTRUCTIONS\n\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\n\n# MULTI-MODAL INSTRUCTIONS\n\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\nYou cannot read nor transcribe audio files or videos.\n\n# TOOL CALLING INSTRUCTIONS\n\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\n\n1. When the request requires up-to-date information.\n2. When the request requires specific data that you do not have in your knowledge base.\n3. When the request involves actions that you cannot perform without tools.\n\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment." %}
|
||||
|
||||
{{- bos_token }}
|
||||
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- if messages[0]['content'] is string %}
|
||||
{%- set system_message = messages[0]['content'] %}
|
||||
{%- elif messages[0]['content'] is iterable %}
|
||||
{%- set system_message = messages[0]['content'][0]['text'] %}
|
||||
{%- else %}
|
||||
{%- set system_message = messages[0]['content']|string %}
|
||||
{%- endif %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_message = default_system_message %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
|
||||
|
||||
|
||||
{#- Tool description appended ONLY to last user message. Edits made by Unsloth #}
|
||||
{#- Tool description appended also if last message is tool. Edits made by Unsloth #}
|
||||
{%- set tools_description = "" %}
|
||||
{%- set has_tools = false %}
|
||||
{#- Cannot use set append_tools_index = loop.index0 since temporary variable - must use namespace #}
|
||||
{%- set ns = namespace(append_tools_index=0, append_tools=false) %}
|
||||
|
||||
{%- if tools is defined and tools is not none and tools|length > 0 %}
|
||||
|
||||
{%- set has_tools = true %}
|
||||
{%- set tools_description = "[AVAILABLE_TOOLS]" + (tools | tojson) + "[/AVAILABLE_TOOLS]" %}
|
||||
|
||||
{#- If User,Assistant,Tool,Tool we also need to append tools_description to last assistant WITHOUT tool_calls defined. Edits made by Unsloth #}
|
||||
{%- if (loop_messages|last)['role'] == 'tool' %}
|
||||
|
||||
{#- Find last assistant WITHOUT tool_calls defined #}
|
||||
{%- set ns.append_tools = true %}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message['role'] == 'assistant' %}
|
||||
|
||||
{#- Cannot use set append_tools_index = loop.index0 since temporary variable - must use namespace #}
|
||||
|
||||
{%- if message['tool_calls'] is not defined or message['tool_calls'] is none %}
|
||||
{%- set ns.append_tools_index = loop.index0 %}
|
||||
{%- endif %}
|
||||
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{%- endif %}
|
||||
|
||||
{%- endif %}
|
||||
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message['role'] == 'user' %}
|
||||
|
||||
{%- if has_tools and loop.last %}
|
||||
{{- tools_description }}
|
||||
{%- endif %}
|
||||
|
||||
{#- If directly called tools in first turn, prepend to user #}
|
||||
{%- if ns.append_tools and ns.append_tools_index == 0 %}
|
||||
{{- tools_description }}
|
||||
{%- endif %}
|
||||
|
||||
{%- if message['content'] is string %}
|
||||
{{- '[INST]' + message['content'] + '[/INST]' }}
|
||||
{%- else %}
|
||||
{{- '[INST]' }}
|
||||
{%- for block in message['content'] %}
|
||||
{%- if block['type'] == 'text' %}
|
||||
|
||||
{#- Original did not have content which is weird. Added by Un-sloth. #}
|
||||
{%- if block['text'] is defined %}
|
||||
{{- block['text'] }}
|
||||
{%- else %}
|
||||
{{- block['content'] }}
|
||||
{%- endif %}
|
||||
|
||||
{%- elif block['type'] in ['image', 'image_url'] %}
|
||||
{{- '[IMG]' }}
|
||||
{%- else %}
|
||||
{{- raise_exception('Only text and image blocks are supported in message content!') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- '[/INST]' }}
|
||||
{%- endif %}
|
||||
|
||||
{%- elif message['role'] == 'system' %}
|
||||
{%- if message['content'] is string %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
|
||||
{%- elif message['content'] is iterable %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
|
||||
{%- else %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content']|string + '[/SYSTEM_PROMPT]' }}
|
||||
{%- endif %}
|
||||
|
||||
|
||||
{%- elif message['role'] == 'assistant' %}
|
||||
{%- if message['content'] is string %}
|
||||
{{- message['content'] }}
|
||||
{%- elif message['content'] is iterable %}
|
||||
{{- message['content'][0]['text'] }}
|
||||
{%- else %}
|
||||
{{- message['content']|string }}
|
||||
{%- endif %}
|
||||
|
||||
{#- If User,Assistant,Tool,Tool we also need to append tools_description. Edits made by Unsloth #}
|
||||
|
||||
{%- if has_tools and (loop.index0 == ns.append_tools_index) %}
|
||||
{{- eos_token }}
|
||||
{{- tools_description }}
|
||||
{%- endif %}
|
||||
|
||||
{%- if message['tool_calls'] is defined and message['tool_calls'] is not none %}
|
||||
{%- for tool in message['tool_calls'] %}
|
||||
{%- if tool['id'] is not defined %}
|
||||
{{- raise_exception('Tool ID must be provided!') }}
|
||||
{%- endif %}
|
||||
{%- set tool_call_id = tool['id'] %}
|
||||
{%- if tool_call_id is not string or tool_call_id|length < 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9!") }}
|
||||
{%- endif %}
|
||||
{%- set arguments = tool['function']['arguments'] %}
|
||||
{%- if arguments is not string %}
|
||||
{%- set arguments = arguments|tojson %}
|
||||
{%- endif %}
|
||||
{#- Must list tool calls AFTER assistant. Edits made by Un-sloth #}
|
||||
{{- "[TOOL_CALLS]" + tool['function']['name'] + "[CALL_ID]" + tool_call_id + "[ARGS]" + arguments }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
|
||||
{#- Must not add EOS if added tools_description. Unsloth edits. #}
|
||||
{%- if (loop.index0 != ns.append_tools_index) %}
|
||||
{{- eos_token }}
|
||||
{%- endif %}
|
||||
|
||||
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
||||
{%- if message.content is defined and message.content.content is defined %}
|
||||
{%- set content = message.content.content %}
|
||||
{%- else %}
|
||||
{%- set content = message.content %}
|
||||
{%- endif %}
|
||||
{%- if message['tool_call_id'] is not defined %}
|
||||
{{- raise_exception('tool_call_id must be provided!') }}
|
||||
{%- endif %}
|
||||
{%- set tool_call_id = message['tool_call_id'] %}
|
||||
{%- if tool_call_id is not string or tool_call_id|length < 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9!") }}
|
||||
{%- endif %}
|
||||
{{- "[TOOL_RESULTS]" + tool_call_id + "[TOOL_CONTENT]" + content|string + "[/TOOL_RESULTS]" }}
|
||||
|
||||
{%- else %}
|
||||
{{- raise_exception('Only user, systemm assistant and tool roles are supported in the custom template made by Unsloth!') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{#- Copyright 2025-present Unsloth. Apache 2.0 License. #}
|
||||
270
config.json
Normal file
270
config.json
Normal file
@@ -0,0 +1,270 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Mistral3ForConditionalGeneration"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"image_token_index": 10,
|
||||
"model_type": "mistral3",
|
||||
"multimodal_projector_bias": false,
|
||||
"pad_token_id": 11,
|
||||
"projector_hidden_act": "gelu",
|
||||
"quantization_config": {
|
||||
"config_groups": {
|
||||
"group_0": {
|
||||
"format": "nvfp4-pack-quantized",
|
||||
"input_activations": {
|
||||
"actorder": null,
|
||||
"block_structure": null,
|
||||
"dynamic": "local",
|
||||
"group_size": 16,
|
||||
"num_bits": 4,
|
||||
"observer": "minmax",
|
||||
"observer_kwargs": {},
|
||||
"strategy": "tensor_group",
|
||||
"symmetric": true,
|
||||
"type": "float"
|
||||
},
|
||||
"output_activations": null,
|
||||
"targets": [
|
||||
"Linear"
|
||||
],
|
||||
"weights": {
|
||||
"actorder": null,
|
||||
"block_structure": null,
|
||||
"dynamic": false,
|
||||
"group_size": 16,
|
||||
"num_bits": 4,
|
||||
"observer": "mse",
|
||||
"observer_kwargs": {},
|
||||
"strategy": "tensor_group",
|
||||
"symmetric": true,
|
||||
"type": "float"
|
||||
}
|
||||
}
|
||||
},
|
||||
"format": "nvfp4-pack-quantized",
|
||||
"global_compression_ratio": null,
|
||||
"ignore": [
|
||||
"model.vision_tower.transformer.layers.0.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.0.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.0.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.0.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.0.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.0.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.0.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.1.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.1.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.1.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.1.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.1.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.1.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.1.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.2.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.2.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.2.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.2.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.2.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.2.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.2.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.3.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.3.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.3.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.3.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.3.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.3.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.3.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.4.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.4.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.4.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.4.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.4.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.4.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.4.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.5.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.5.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.5.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.5.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.5.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.5.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.5.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.6.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.6.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.6.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.6.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.6.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.6.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.6.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.7.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.7.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.7.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.7.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.7.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.7.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.7.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.8.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.8.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.8.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.8.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.8.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.8.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.8.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.9.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.9.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.9.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.9.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.9.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.9.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.9.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.10.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.10.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.10.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.10.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.10.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.10.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.10.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.11.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.11.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.11.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.11.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.11.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.11.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.11.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.12.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.12.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.12.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.12.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.12.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.12.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.12.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.13.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.13.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.13.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.13.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.13.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.13.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.13.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.14.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.14.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.14.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.14.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.14.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.14.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.14.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.15.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.15.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.15.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.15.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.15.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.15.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.15.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.16.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.16.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.16.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.16.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.16.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.16.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.16.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.17.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.17.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.17.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.17.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.17.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.17.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.17.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.18.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.18.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.18.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.18.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.18.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.18.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.18.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.19.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.19.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.19.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.19.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.19.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.19.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.19.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.20.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.20.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.20.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.20.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.20.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.20.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.20.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.21.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.21.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.21.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.21.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.21.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.21.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.21.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.22.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.22.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.22.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.22.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.22.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.22.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.22.attention.o_proj",
|
||||
"model.vision_tower.transformer.layers.23.feed_forward.gate_proj",
|
||||
"model.vision_tower.transformer.layers.23.feed_forward.up_proj",
|
||||
"model.vision_tower.transformer.layers.23.feed_forward.down_proj",
|
||||
"model.vision_tower.transformer.layers.23.attention.k_proj",
|
||||
"model.vision_tower.transformer.layers.23.attention.v_proj",
|
||||
"model.vision_tower.transformer.layers.23.attention.q_proj",
|
||||
"model.vision_tower.transformer.layers.23.attention.o_proj",
|
||||
"model.multi_modal_projector.patch_merger.merging_layer",
|
||||
"model.multi_modal_projector.linear_1",
|
||||
"model.multi_modal_projector.linear_2",
|
||||
"lm_head"
|
||||
],
|
||||
"kv_cache_scheme": null,
|
||||
"quant_method": "compressed-tensors",
|
||||
"quantization_status": "compressed",
|
||||
"sparsity_config": {},
|
||||
"transform_config": {},
|
||||
"version": "0.11.1.a20250929"
|
||||
},
|
||||
"spatial_merge_size": 2,
|
||||
"text_config": {
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 32768,
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000000.0,
|
||||
"sliding_window": null,
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.56.1",
|
||||
"unsloth_fixed": true,
|
||||
"vision_config": {
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1024,
|
||||
"image_size": 1540,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"model_type": "pixtral",
|
||||
"num_attention_heads": 16,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 24,
|
||||
"patch_size": 14,
|
||||
"rope_theta": 10000.0
|
||||
},
|
||||
"vision_feature_layer": -1
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 131072,
|
||||
"pad_token_id": 11,
|
||||
"temperature": 0.15,
|
||||
"transformers_version": "4.56.1"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2cc0279337fdd97f82327325758788610a47e04959f0ce6e0e3053131148ee74
|
||||
size 4939410608
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:336e466e3b0ff4e6c1e2f22d53add7e3b6be5690b903cee291f9fe0fce80e1a9
|
||||
size 4991611888
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b003847e04b71b76f21d54ede497f50132fe9a483ddc18a81785b7e0b14a51b5
|
||||
size 4794356016
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5b72834082387ce74af5414bf353165eab35661f3261f7c9c9f16da505b64e93
|
||||
size 1342177424
|
||||
1433
model.safetensors.index.json
Normal file
1433
model.safetensors.index.json
Normal file
File diff suppressed because it is too large
Load Diff
32
preprocessor_config.json
Normal file
32
preprocessor_config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"disable_grouping": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "PixtralImageProcessorFast",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"patch_size": 14,
|
||||
"processor_class": "PixtralProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 1540
|
||||
}
|
||||
}
|
||||
8
processor_config.json
Normal file
8
processor_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"image_break_token": "[IMG_BREAK]",
|
||||
"image_end_token": "[IMG_END]",
|
||||
"image_token": "[IMG]",
|
||||
"patch_size": 14,
|
||||
"processor_class": "PixtralProcessor",
|
||||
"spatial_merge_size": 2
|
||||
}
|
||||
43
recipe.yaml
Normal file
43
recipe.yaml
Normal file
@@ -0,0 +1,43 @@
|
||||
default_stage:
|
||||
default_modifiers:
|
||||
SmoothQuantModifier:
|
||||
smoothing_strength: 0.9
|
||||
mappings:
|
||||
- !!python/tuple
|
||||
- ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj']
|
||||
- re:.*input_layernorm
|
||||
- !!python/tuple
|
||||
- ['re:.*gate_proj', 're:.*up_proj']
|
||||
- re:.*post_attention_layernorm
|
||||
ignore: []
|
||||
QuantizationModifier:
|
||||
config_groups:
|
||||
group_0:
|
||||
targets: [Linear]
|
||||
weights:
|
||||
num_bits: 4
|
||||
type: float
|
||||
symmetric: true
|
||||
group_size: 16
|
||||
strategy: tensor_group
|
||||
block_structure: null
|
||||
dynamic: false
|
||||
actorder: null
|
||||
observer: mse
|
||||
observer_kwargs: {}
|
||||
input_activations:
|
||||
num_bits: 4
|
||||
type: float
|
||||
symmetric: true
|
||||
group_size: 16
|
||||
strategy: tensor_group
|
||||
block_structure: null
|
||||
dynamic: local
|
||||
actorder: null
|
||||
observer: minmax
|
||||
observer_kwargs: {}
|
||||
output_activations: null
|
||||
format: null
|
||||
targets: [Linear]
|
||||
ignore: ['re:.*lm_head.*', 're:.*multi_modal_projector.*', 're:.*vision_tower.*', 're:.*model.norm.*',
|
||||
're:.*embed_tokens.*']
|
||||
1032
special_tokens_map.json
Normal file
1032
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tekken.json
Normal file
3
tekken.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6e2501687ccd0e1f30f36319eaf2b46958b897811e246cd8eb5d385b9e3de7d1
|
||||
size 19399895
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:23ad081f384b2bdb3c97f6e5461dfce52c1174c7328854a55006988f0fef9da7
|
||||
size 17078019
|
||||
9021
tokenizer_config.json
Normal file
9021
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user