You can deploy this model and start earning money today!

RichardErkhov/
mjm4dl_-_gemma_slot_intent_v2_64_e2_cosine_sched-gguf

Name: mjm4dl_-_gemma_slot_intent_v2_64_e2_cosine_sched-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

gemma_slot_intent_v2_64_e2_cosine_sched - GGUF

Name	Quant method	Size
gemma_slot_intent_v2_64_e2_cosine_sched.Q2_K.gguf	Q2_K	1.15GB
gemma_slot_intent_v2_64_e2_cosine_sched.IQ3_XS.gguf	IQ3_XS	1.22GB
gemma_slot_intent_v2_64_e2_cosine_sched.IQ3_S.gguf	IQ3_S	1.27GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q3_K_S.gguf	Q3_K_S	1.27GB
gemma_slot_intent_v2_64_e2_cosine_sched.IQ3_M.gguf	IQ3_M	1.3GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q3_K.gguf	Q3_K	1.36GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q3_K_M.gguf	Q3_K_M	1.36GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q3_K_L.gguf	Q3_K_L	1.44GB
gemma_slot_intent_v2_64_e2_cosine_sched.IQ4_XS.gguf	IQ4_XS	1.47GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q4_0.gguf	Q4_0	1.52GB
gemma_slot_intent_v2_64_e2_cosine_sched.IQ4_NL.gguf	IQ4_NL	1.53GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q4_K_S.gguf	Q4_K_S	1.53GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q4_K.gguf	Q4_K	1.59GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q4_K_M.gguf	Q4_K_M	1.59GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q4_1.gguf	Q4_1	1.64GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q5_0.gguf	Q5_0	1.75GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q5_K_S.gguf	Q5_K_S	1.75GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q5_K.gguf	Q5_K	1.79GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q5_K_M.gguf	Q5_K_M	1.79GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q5_1.gguf	Q5_1	1.87GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q6_K.gguf	Q6_K	2.0GB
gemma_slot_intent_v2_64_e2_cosine_sched.Q8_0.gguf	Q8_0	2.59GB

Original model description:

base_model: unsloth/gemma-2-2b-it language:

This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.