初始化项目，由ModelHub XC社区提供模型
Model: EphAsad/Atem-1.7B Source: Original Platform
This commit is contained in:
ModelHub XC
43
.gitattributes
vendored
Normal file
43
.gitattributes
vendored
Normal file
@@ -0,0 +1,43 @@
|
||||
*.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
|
||||
Qwen3-1.7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen3-1.7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen3-1.7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-1.7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-1.7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-1.7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Logo.png filter=lfs diff=lfs merge=lfs -text
|
||||
3
Atem-1.7B.Q4_K_M.gguf
Normal file
3
Atem-1.7B.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:468e13062fa69b650c781ee30f037993175671be246b2069d1d3777b59f74109
|
||||
size 1107409664
|
||||
3
Atem-1.7B.Q5_K_M.gguf
Normal file
3
Atem-1.7B.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:854a78deb78266a9f1f59250fe3c5a283d333be7699e7d6bafae3d9317061a13
|
||||
size 1257880320
|
||||
3
Atem-1.7B.Q8_0.gguf
Normal file
3
Atem-1.7B.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1464b1b04ed8a2bc460c5a35984de0014350ebc1d9663c1d0f793cb2fa831905
|
||||
size 1834427136
|
||||
3
Logo.png
Normal file
3
Logo.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:036d268ac79d1a5355a5ea602fc02ba312f4938c3506ddfa148ec7de44b69607
|
||||
size 981796
|
||||
59
Modelfile
Normal file
59
Modelfile
Normal file
@@ -0,0 +1,59 @@
|
||||
|
||||
FROM Atem-1.7B.Q8_0.gguf
|
||||
TEMPLATE """{{- if .Messages }}
|
||||
{{- if or .System .Tools }}<|im_start|>system
|
||||
{{- if .System }}
|
||||
{{ .System }}
|
||||
{{- end }}
|
||||
{{- if .Tools }}
|
||||
|
||||
# Tools
|
||||
|
||||
You may call one or more functions to assist with the user query.
|
||||
|
||||
You are provided with function signatures within <tools></tools> XML tags:
|
||||
<tools>
|
||||
{{- range .Tools }}
|
||||
{"type": "function", "function": {{ .Function }}}
|
||||
{{- end }}
|
||||
</tools>
|
||||
|
||||
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||
<tool_call>
|
||||
{"name": <function-name>, "arguments": <args-json-object>}
|
||||
</tool_call>
|
||||
{{- end }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- range $i, $_ := .Messages }}
|
||||
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
||||
{{- if eq .Role "user" }}<|im_start|>user
|
||||
{{ .Content }}<|im_end|>
|
||||
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
||||
{{ if .Content }}{{ .Content }}
|
||||
{{- else if .ToolCalls }}<tool_call>
|
||||
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
|
||||
{{ end }}</tool_call>
|
||||
{{- end }}{{ if not $last }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- else if eq .Role "tool" }}<|im_start|>user
|
||||
<tool_response>
|
||||
{{ .Content }}
|
||||
</tool_response><|im_end|>
|
||||
{{ end }}
|
||||
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
{{- else }}
|
||||
{{- if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}{{ if .Prompt }}<|im_start|>user
|
||||
{{ .Prompt }}<|im_end|>
|
||||
{{ end }}<|im_start|>assistant
|
||||
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
|
||||
PARAMETER stop "<|im_end|>"
|
||||
PARAMETER stop "<|im_start|>"
|
||||
PARAMETER temperature 0.6
|
||||
PARAMETER min_p 0.0
|
||||
PARAMETER top_k 20
|
||||
PARAMETER top_p 0.95
|
||||
PARAMETER repeat_penalty 1
|
||||
378
README.md
Normal file
378
README.md
Normal file
@@ -0,0 +1,378 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-1.7B
|
||||
tags:
|
||||
- unsloth
|
||||
- lora
|
||||
- qwen3
|
||||
- reasoning
|
||||
- distillation
|
||||
- chain-of-thought
|
||||
datasets:
|
||||
- mitroitskii/OpenR1-Math-220k-formatted
|
||||
- Jackrong/Claude-opus-4.6-TraceInversion-9000x
|
||||
- Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned
|
||||
- WithinUsAI/MiniMax_M2.7_Distilled_5k
|
||||
- FreedomIntelligence/medical-o1-reasoning-SFT
|
||||
- Modotte/CodeX-2M-Thinking
|
||||
- trjxter/DeepSeek-V4-Pro-Reasoning-8000x
|
||||
- nvidia/OpenCodeReasoning
|
||||
- openai/gsm8k
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
|
||||
|
||||
# Atem-1.7B
|
||||
|
||||
*Ancient logic. Modern intelligence.*
|
||||
|
||||
A 1.7B reasoning model trained via a single CoT-preserving SFT pass directly on Qwen3-1.7B, distilling multi-domain reasoning capability from frontier teacher models while keeping the base model's native thinking capability intact.
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Atem-1.7B is a 1.7B parameter reasoning model built via a single supervised fine-tuning pass on raw Qwen3-1.7B, using the same CoT-preserving single-pass design as Atem-4B and Atem-8B. It is the most compute-efficient model in the Atem series, completing training in under 2.5 hours on an A100-SXM4 80GB while maintaining 2.95% proportional LoRA capacity — close to the series-wide 3% target.
|
||||
|
||||
This model includes GSM8K-format training examples (5K no-think records) to partially restore the `####` answer convention that the reasoning corpus otherwise overwrites — an improvement over Atem-4B and Atem-8B, which did not include these.
|
||||
|
||||
---
|
||||
|
||||
## Model Details
|
||||
|
||||
| Property | Value |
|
||||
| --- | --- |
|
||||
| **Base model** | Qwen/Qwen3-1.7B |
|
||||
| **Training method** | Single-pass CoT-Preserving LoRA SFT |
|
||||
| **LoRA config** | r=48, alpha=96, dropout=0.05 |
|
||||
| **Target modules** | q, k, v, o, gate, up, down projections |
|
||||
| **Parameters** | ~1.77B |
|
||||
| **Trainable (LoRA) params** | 52,297,728 (2.95% of base) |
|
||||
| **Training records** | 62,301 (after token-length filtering) |
|
||||
| **Think / No-think split** | 85% / 15% |
|
||||
| **Epochs** | 2 (ceiling; early stopping patience=3, never triggered) |
|
||||
| **Effective batch size** | 64 (batch 16 × grad accum 4) |
|
||||
| **Learning rate** | 1e-4, cosine schedule, 5% warmup |
|
||||
| **Max sequence length** | 6,144 tokens |
|
||||
| **Precision** | bfloat16 (full 16-bit LoRA, not QLoRA) |
|
||||
| **Hardware** | NVIDIA A100-SXM4 80GB |
|
||||
| **Runtime** | 2h28m |
|
||||
| **License** | Apache 2.0 |
|
||||
|
||||
---
|
||||
|
||||
## Design Notes
|
||||
|
||||
**Single combined pass.** The same single CoT-preserving pass design used across Atem-4B and Atem-8B — no erase-then-rebuild pipeline. Reasoning capability is built directly on the base model's intact native foundation.
|
||||
|
||||
**r=48 for proportional capacity.** r=32 on a 1.7B model represents only 2.05% of the model's parameters — the same shrinking-fraction problem observed across the series as model size grows. r=48 recovers 2.95% proportional capacity, close to the series-wide ~3% target and significantly better than r=32 would have provided.
|
||||
|
||||
**GSM8K format restoration.** The standard Atem training corpus uses `\boxed{}` notation throughout. Atem-4B and Atem-8B both showed a systematic GSM8K strict-match regression as a result of this format shift. Atem-1.7B is the first in the series to include 5,000 GSM8K-format training examples (from `openai/gsm8k`) in the no-think pool, partially re-establishing the `#### answer` convention alongside `\boxed{}`.
|
||||
|
||||
**Full 16-bit LoRA.** At 1.7B the model weights occupy only ~3.4GB, leaving over 75GB of A100 headroom. Full 16-bit LoRA is used throughout — faster and marginally more accurate than QLoRA without any VRAM constraint.
|
||||
|
||||
---
|
||||
|
||||
## Intended Use
|
||||
|
||||
Atem-1.7B is suited for reasoning tasks on resource-constrained hardware — edge devices, local deployment, and applications where a 4B+ model is impractical:
|
||||
|
||||
- Multi-step mathematical reasoning
|
||||
- Code explanation, implementation, and debugging
|
||||
- Analytical reasoning across diverse domains
|
||||
- Commonsense reasoning and physical intuition
|
||||
- Logic and argument evaluation
|
||||
|
||||
For higher capability at the cost of resource requirements, Atem-4B and Atem-8B provide progressively stronger results on the same reasoning tasks.
|
||||
|
||||
---
|
||||
|
||||
## Training Data
|
||||
|
||||
Atem-1.7B was trained on the same eight-source reasoning corpus as Atem-4B and Atem-8B, with the addition of 5,000 GSM8K-format records to partially restore the `####` answer convention. All sources include explicit chain-of-thought reasoning traces; 85% of training records were formatted with full think traces and 15% as direct answers.
|
||||
|
||||
| Dataset | Records | Source / Teacher |
|
||||
| --- | --- | --- |
|
||||
| mitroitskii/OpenR1-Math-220k-formatted | ~10,938 | DeepSeek-R1 — Mathematics (correctness-filtered) |
|
||||
| Jackrong/Claude-opus-4.6-TraceInversion-9000x | 7,000 | Claude Opus 4.6 — Trace Inversion |
|
||||
| Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned (General-Math) | 8,000 | Kimi K2.5 — Mathematical Reasoning |
|
||||
| Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned (General-Distillation) | 8,000 | Kimi K2.5 — General Reasoning |
|
||||
| Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned (PHD-Science) | 8,000 | Kimi K2.5 — Scientific Reasoning |
|
||||
| WithinUsAI/MiniMax_M2.7_Distilled_5k | 5,000 | MiniMax M2.7 |
|
||||
| FreedomIntelligence/medical-o1-reasoning-SFT | 7,500 | Medical reasoning (English config) |
|
||||
| Modotte/CodeX-2M-Thinking | 15,000 | Mixed — Coding with CoT |
|
||||
| trjxter/DeepSeek-V4-Pro-Reasoning-8000x | ~8,014 | DeepSeek-V4-Pro |
|
||||
| nvidia/OpenCodeReasoning | 15,000 | Mixed — Competitive coding |
|
||||
| openai/gsm8k (no-think) | 5,000 | GSM8K `#### answer` format restoration |
|
||||
| **Total (pre-filter pool)** | **96,017** | |
|
||||
| **Total (post-filter, trained on)** | **62,301** | |
|
||||
|
||||
Non-English reasoning traces (primarily CJK) were filtered at the trace level using an ASCII-ratio threshold and retained as no-think records. The 34.3% filter rate is consistent with Atem-4B (32.7%) and Atem-8B (34.3%) at the same 6,144-token ceiling.
|
||||
|
||||
---
|
||||
|
||||
## Training Configuration
|
||||
|
||||
```python
|
||||
# Key hyperparameters
|
||||
lora_r = 48
|
||||
lora_alpha = 96
|
||||
lora_dropout = 0.05
|
||||
max_seq_length = 6144
|
||||
learning_rate = 1e-4
|
||||
lr_scheduler = 'cosine'
|
||||
warmup_ratio = 0.05
|
||||
batch_size = 16
|
||||
grad_accumulation = 4 # effective batch size: 64
|
||||
num_epochs = 2 # ceiling — early stopping patience=3
|
||||
eval_steps = 150
|
||||
early_stopping_patience = 3
|
||||
early_stopping_threshold = 0.001
|
||||
nothink_ratio = 0.15
|
||||
load_in_4bit = False # full 16-bit LoRA
|
||||
dtype = bfloat16
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Loss Curve
|
||||
|
||||
| Step | Train Loss | Val Loss |
|
||||
| --- | --- | --- |
|
||||
| 150 | 1.0706 | 1.0833 |
|
||||
| 300 | 1.0385 | 1.0520 |
|
||||
| 450 | 1.0566 | 1.0372 |
|
||||
| 600 | 0.9990 | 1.0255 |
|
||||
| 750 | 1.0082 | 1.0158 |
|
||||
| 900 | 0.9887 | 1.0091 |
|
||||
| 1050 | 0.9294 | 1.0051 |
|
||||
| 1200 | 0.8906 | 1.0020 |
|
||||
| 1350 | 0.9331 | 0.9993 |
|
||||
| 1500 | 0.9780 | 0.9973 |
|
||||
| 1650 | 0.9467 | 0.9963 |
|
||||
| 1800 | 0.9341 | 0.9957 |
|
||||
| Final (1948) | **0.9902** (avg) | **0.9956** |
|
||||
|
||||
Train loss is noisier than in larger Atem models — characteristic of smaller models with a diverse multi-domain corpus. Validation loss improved monotonically across all 13 checkpoints without exception. Early stopping was configured but never triggered.
|
||||
|
||||
---
|
||||
|
||||
## Evaluation
|
||||
|
||||
### Benchmark Results
|
||||
|
||||
Evaluated against base Qwen3-1.7B (`Qwen/Qwen3-1.7B`) using lm-evaluation-harness. Both models were loaded in 4-bit for evaluation. Statistical significance (σ) is provided as context for interpreting each result — at 1.7B scale, several deltas that appear directionally positive are within sampling noise due to test set size.
|
||||
|
||||
| Task | Base (Qwen3-1.7B) | Atem-1.7B | Delta | σ |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| ARC-Challenge (0-shot, acc_norm) | 40.7% | 42.2% | +1.5pp ✓ | 0.7σ |
|
||||
| GSM8K strict (5-shot, exact_match) | 62.0% | 58.7% | −3.3pp ⚠ | 1.7σ |
|
||||
| HellaSwag (0-shot, acc_norm) | 59.4% | **61.3%** | **+1.9pp** ✓ | 2.8σ |
|
||||
| MMLU (0-shot, acc) | 55.4% | 56.2% | +0.8pp ✓ | 1.3σ |
|
||||
| Winogrande (0-shot, acc) | 61.8% | 61.1% | −0.7pp ⚠ | 0.4σ |
|
||||
| PIQA (0-shot, acc) | 71.4% | 71.4% | +0.0pp — | 0.0σ |
|
||||
| OpenBookQA (0-shot, acc_norm) | 36.0% | **39.0%** | +3.0pp ✓ | 1.0σ |
|
||||
| BoolQ (0-shot, acc) | 76.5% | 76.0% | −0.5pp — | 0.5σ |
|
||||
|
||||
**HellaSwag (+1.9pp, 2.8σ)** is the only clearly statistically significant positive result. It uses normalised log-likelihood scoring over multiple-choice options — format-independent and not influenced by generation style. This is also the most consistent signal across the full Atem series (1.7B: +1.9pp, 4B: +2.9pp, 8B: +1.7pp), confirming genuine commonsense reasoning transfer from the CoT training corpus.
|
||||
|
||||
**OpenBookQA (+3.0pp)** is directionally strong but the test set is only 500 questions, giving 1.0σ — treat this as encouraging rather than conclusive.
|
||||
|
||||
**Winogrande (−0.7pp, ⚠)** despite the flag is 0.4σ and statistically indistinguishable from noise. Not a meaningful regression.
|
||||
|
||||
**MMLU (+0.8pp, 1.3σ)** is borderline. Consistent with the series pattern — neither model has a knowledge breadth advantage after CoT training.
|
||||
|
||||
Results at 1.7B are generally less pronounced than at 4B and 8B, as expected: smaller models with proportionally larger parameter changes per training step exhibit noisier benchmark behaviour, and the absolute capability headroom above random baselines is narrower.
|
||||
|
||||
### GSM8K — Formatting Shift
|
||||
|
||||
The strict-match regression (−3.3pp) follows the same pattern established at 4B and 8B: the training corpus uses `\boxed{}` notation, systematically shifting away from the `####` format that lm_eval's strict-match extraction expects. At 1.7B the base model scores 62.0% — above the threshold where formatting effects dominate over raw capability gains (the 0.6B base at 26.7% was below this threshold and actually improved on strict-match).
|
||||
|
||||
Atem-1.7B is the first model in the series to include GSM8K-format (`#### answer`) training examples. At 5,000 records out of 62,301 total (8%), this partially offsets the shift but does not eliminate it — larger proportions would be needed for full recovery. Based on the flexible-extraction recovery rate confirmed at 8B (68% of regression recovered), the estimated true capability gap is approximately −1.1pp rather than −3.3pp.
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
### Transformers
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
|
||||
model_name = "EphAsad/Atem-1.7B"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Explain why the harmonic mean is used for average speeds rather than the arithmetic mean."
|
||||
}
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt"
|
||||
).to(model.device)
|
||||
|
||||
with torch.no_grad():
|
||||
output = model.generate(
|
||||
input_ids=inputs,
|
||||
max_new_tokens=2000,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
top_k=20,
|
||||
do_sample=True,
|
||||
repetition_penalty=1.1,
|
||||
)
|
||||
|
||||
response = tokenizer.decode(
|
||||
output[0][inputs.shape[1]:],
|
||||
skip_special_tokens=True
|
||||
)
|
||||
print(response)
|
||||
```
|
||||
|
||||
### Unsloth (faster inference)
|
||||
|
||||
```python
|
||||
from unsloth import FastLanguageModel
|
||||
import torch
|
||||
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
model_name="EphAsad/Atem-1.7B",
|
||||
max_seq_length=6144,
|
||||
dtype=torch.bfloat16,
|
||||
load_in_4bit=True,
|
||||
)
|
||||
FastLanguageModel.for_inference(model)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the time complexity of merge sort and why?"
|
||||
}
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt"
|
||||
).to("cuda")
|
||||
|
||||
with torch.no_grad():
|
||||
output = model.generate(
|
||||
input_ids=inputs,
|
||||
max_new_tokens=2000,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
top_k=20,
|
||||
do_sample=True,
|
||||
)
|
||||
|
||||
print(tokenizer.decode(
|
||||
output[0][inputs.shape[1]:],
|
||||
skip_special_tokens=True
|
||||
))
|
||||
```
|
||||
|
||||
### Ollama
|
||||
|
||||
```bash
|
||||
# Recommended — best speed/quality balance
|
||||
ollama run hf.co/EphAsad/Atem-1.7B:Q4_K_M
|
||||
|
||||
# Higher quality
|
||||
ollama run hf.co/EphAsad/Atem-1.7B:Q5_K_M
|
||||
|
||||
# Near-lossless
|
||||
ollama run hf.co/EphAsad/Atem-1.7B:Q8_0
|
||||
```
|
||||
|
||||
### llama.cpp
|
||||
|
||||
```bash
|
||||
llama-server -hf EphAsad/Atem-1.7B:Q4_K_M
|
||||
```
|
||||
|
||||
### Sampling Parameters
|
||||
|
||||
Use `temperature=0.6, top_p=0.95, top_k=20` — Qwen3's published recommendation for thinking mode. Do not use greedy decoding with thinking mode enabled.
|
||||
|
||||
### System Prompt
|
||||
|
||||
Atem-1.7B's identity is baked into the chat template and activates automatically without an explicit system message. For manual override:
|
||||
|
||||
```
|
||||
You are Atem, a precise and analytical reasoning assistant. You approach
|
||||
every problem methodically — identifying core concepts, reasoning step by
|
||||
step, and arriving at well-supported conclusions. You show your thinking
|
||||
clearly and are thorough, direct, and intellectually honest.
|
||||
```
|
||||
|
||||
### Available Files
|
||||
|
||||
| File | Size | Description |
|
||||
| --- | --- | --- |
|
||||
| `model.safetensors` | 3.44 GB | Full bfloat16 merged weights (single shard) |
|
||||
| `Atem-1.7b.Q4_K_M.gguf` | 1.11 GB | 4-bit quantised — recommended |
|
||||
| `Atem-1.7b.Q5_K_M.gguf` | 1.26 GB | 5-bit quantised |
|
||||
| `Atem-1.7b.Q8_0.gguf` | 1.83 GB | 8-bit quantised — near-lossless |
|
||||
|
||||
---
|
||||
|
||||
## Known Limitations
|
||||
|
||||
**GSM8K formatting shift.** As documented in the evaluation section, the training corpus uses `\boxed{}` for mathematical answers. Despite the inclusion of 5,000 GSM8K-format examples, the strict-match regression persists at −3.3pp. The estimated true capability gap under flexible extraction is approximately −1.1pp. Future runs with a higher proportion of GSM8K-format examples would reduce this further.
|
||||
|
||||
**Statistical modesty at 1.7B.** Most benchmark deltas at this scale are within sampling noise — HellaSwag is the exception (2.8σ). This is expected: 1.7B models have narrower performance headroom and proportionally larger variance per benchmark question. The reasoning improvements are real but harder to detect reliably at smaller scale.
|
||||
|
||||
**6,144 token sequence ceiling.** The longest reasoning traces (advanced mathematics, competitive programming) were dropped during formatting. The model has not been trained on very long chain-of-thought traces.
|
||||
|
||||
**No RLHF or DPO.** Atem-1.7B has not undergone preference optimisation.
|
||||
|
||||
---
|
||||
|
||||
## Roadmap
|
||||
|
||||
- **Atem-14B:** Single CoT-preserving pass on Qwen3-14B, r=128 (3.10% proportional capacity), with expanded GSM8K-format and camel-ai/chemistry additions to the corpus
|
||||
|
||||
---
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@misc{atem_1b7_2026,
|
||||
author = {Asad, Zain},
|
||||
title = {Atem-1.7B: A 1.7B CoT-Preserving Reasoning Model via
|
||||
Single-Pass SFT on Qwen3},
|
||||
year = {2026},
|
||||
publisher = {HuggingFace},
|
||||
howpublished = {\url{https://huggingface.co/EphAsad/Atem-1.7B}},
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
Released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), consistent with the base model Qwen/Qwen3-1.7B.
|
||||
|
||||
---
|
||||
|
||||
Built independently by Zain Asad — [EphAsad](https://huggingface.co/EphAsad)
|
||||
100
chat_template.jinja
Normal file
100
chat_template.jinja
Normal file
@@ -0,0 +1,100 @@
|
||||
{%- 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\n' + 'You are Atem, a precise and analytical reasoning assistant. You approach every problem methodically — identifying core concepts, reasoning step by step, and arriving at well-supported conclusions. You show your thinking clearly and are thorough, direct, and intellectually honest.' + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for forward_message in messages %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- set message = messages[index] %}
|
||||
{%- set current_content = message.content if message.content is not none else '' %}
|
||||
{%- set tool_start = '<tool_response>' %}
|
||||
{%- set tool_start_length = tool_start|length %}
|
||||
{%- set start_of_message = current_content[:tool_start_length] %}
|
||||
{%- set tool_end = '</tool_response>' %}
|
||||
{%- set tool_end_length = tool_end|length %}
|
||||
{%- set start_pos = (current_content|length) - tool_end_length %}
|
||||
{%- if start_pos < 0 %}
|
||||
{%- set start_pos = 0 %}
|
||||
{%- endif %}
|
||||
{%- set end_of_message = current_content[start_pos:] %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
|
||||
{%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
|
||||
{%- set reasoning_content = (reasoning_content.split('<think>')|last).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' }}
|
||||
{{- message.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' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
64
config.json
Normal file
64
config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"torch_dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151669,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.5.5",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_length": 40960,
|
||||
"pad_token_id": 151669,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d18db0bccebeedd6e619d6b109f5c2ef45f3aa619d0ba40fa528d0e3ad3b5653
|
||||
size 3441185608
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
|
||||
size 11423114
|
||||
234
tokenizer_config.json
Normal file
234
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user