Upload folder using huggingface_hub

.gitattributes

@@ -50,3 +50,12 @@ gemma-4-E2B-it-int4-aggr-v2/gemma-4-E2B-it-int4-aggr-v2.cellmd filter=lfs diff=l
 gemma-4-E2B-it-int4-aggr-v2/gemma-4-E2B-it-int4-aggr-v2.tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Bonsai-1.7B_v2/Bonsai-1.7B_v2.cellm filter=lfs diff=lfs merge=lfs -text
 lfm2.5-350m-v1/lfm2.5-350m-v1.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/qwen3-0.6b-f16-new.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/qwen3-0.6b-f16.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/qwen3-0.6b-int4-g128.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/qwen3-0.6b-int4-g32.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/qwen3-0.6b-int4.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/qwen3-0.6b-int8.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/qwen3-0.6b-mixed-int4.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/qwen3-0.6b-test-i4.cellm filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen3-0.6b-v1/README.md

@@ -0,0 +1,49 @@
+# Qwen3-0.6B (cellm)
+
+Qwen3-0.6B base model converted to cellm format at various quantization levels.
+
+This is a base (pretrained) model, not instruction-tuned. It works in text completion mode but does not follow chat templates.
+
+## Model details
+
+- **Base model**: Qwen/Qwen3-0.6B
+- **Architecture**: Standard transformer with grouped-query attention
+- **Hidden size**: 1024
+- **Attention**: 16 heads, 128 head dim, attn_dim = 2048
+- **Vocab**: 151,936
+
+## Variants
+
+| File | Format | Size | Quality |
+|------|--------|------|---------|
+| qwen3-0.6b-f16.cellm | f16 | 1.4 GB | Repetitive but on-topic |
+| qwen3-0.6b-f16-new.cellm | f16 (rebuilt) | 1.4 GB | Same as above |
+| qwen3-0.6b-int8.cellm | int8 | 866 MB | Repetitive but on-topic |
+| qwen3-0.6b-int4-g32.cellm | int4 g32 | 830 MB | Noisy, sometimes on-topic |
+| qwen3-0.6b-mixed-int4.cellm | mixed int4 | 810 MB | Mostly repetitive |
+| qwen3-0.6b-int4-g128.cellm | int4 g128 | 590 MB | Mostly repetitive |
+| qwen3-0.6b-test-i4.cellm | int4 test | 582 MB | Fragmented |
+| qwen3-0.6b-int4.cellm | int4 aggressive | 360 MB | Fragmented |
+
+All variants share one tokenizer.json.
+
+## Usage
+
+```sh
+./target/release/infer \
+  --model qwen3-0.6b-f16.cellm \
+  --tokenizer tokenizer.json \
+  --prompt "Explain what a computer is:" \
+  --gen 40 --temperature 0.7 --backend cpu --kv-encoding f16
+```
+
+## Notes
+
+- This is a 0.6B base model. Output quality is limited across all quantizations.
+- Use temperature 0.7+ to avoid repetition loops.
+- f16 and int8 are the most coherent. Below int8, quality drops.
+- For instruction-following, use Qwen3.5-0.8B instead.
+
+## License
+
+Apache 2.0 (same as upstream Qwen3)

qwen3-0.6b-v1/qwen3-0.6b-f16-new.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ac1e945b9ee9b0fdf0410fcff42e8b8413194a5ef5d4aca8c46c66c60f4a4d
+size 1503304448

qwen3-0.6b-v1/qwen3-0.6b-f16.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ac1e945b9ee9b0fdf0410fcff42e8b8413194a5ef5d4aca8c46c66c60f4a4d
+size 1503304448

qwen3-0.6b-v1/qwen3-0.6b-int4-g128.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ef2b7838efcdcf5e094dc08d6d706a9af93923754d7a40c05dffa9bf200c2f
+size 618664768

qwen3-0.6b-v1/qwen3-0.6b-int4-g32.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3c2587c542cf1771b71e10bdf022e0efe0d9b334c0a54eb952efca7ac7a2f7
+size 870251520

qwen3-0.6b-v1/qwen3-0.6b-int4.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1a1f6d812c9d6fc3309982bdd2983c8bb6c3031a93498260a9ab37eba94a57
+size 377274176

qwen3-0.6b-v1/qwen3-0.6b-int8.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd22eea57a3d4c3d55487c70315675231fbc9f6540cd6f91dd5fe2255e775bf
+size 908336128

qwen3-0.6b-v1/qwen3-0.6b-mixed-int4.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b4b7f83b96431d78f442cb7d291f338d516c95df318b41fed8e4f11bae6ccb
+size 849607424

qwen3-0.6b-v1/qwen3-0.6b-test-i4.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168d58198b103bb3cb6083b3198547ffafb9adb243eb563a0d3cadb5b9b1d16f
+size 610343872

qwen3-0.6b-v1/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654